Merge pull request 'fix: count a run completed at the DONE transition, not after it (researchx#28)' (#29) from po/fix-cost-counter-race into main

Reviewed-on: #29

.ciagent/ARCHITECTURE.md

@@ -47,7 +47,7 @@ FastAPI routes: POST /api/runs, GET /api/methodologies, GET /api/runs/{id}, appr
 - **DependsOn:** engine, methodologies, config
 
 ### 7. Frontend (Next.js App Router, TypeScript strict)
-App shell (root layout, P5): persistent sidebar (primary nav — New research / Library / Settings; adapter connection-status dots as a v2 preview) + top bar (⌘K navigation palette — screens + stored reports; avatar button → user menu with the local single-user profile). Screens: Ask (question + optional context), Choose (methodology cards with ETA/cost/why-recommended; dials behind "advanced"), Plan & Run (approve/edit plan, live SSE trace, pause/cancel), Reading Room v0 (rendered report, hover-a-citation → exact quoted passage, ledger panel, Markdown/JSON export), Library (P5: folder-structure report storage — auto-categorized folders, recency/title sorting, report cards into the Reading Room; cross-report Connections panel — shared-sources ⇄ / related-topic → edges; project graph + task inbox as v2-preview panels), Settings (P5: masked API-key status, storage directory, default methodology + resolved 12-dial display, appearance preview, about/version).
+App shell (root layout, P5): persistent sidebar (primary nav — New research / Library / Settings; adapter connection-status dots as a v2 preview) + top bar (⌘K navigation palette — screens + stored reports; avatar button → user menu with the local single-user profile). Screens: Ask (question + optional context; open-question suggestions below the form — follow-ups from unanswered questions of past runs, click-fills-the-box, REQ-67; opt-in Refine dialogue — inline drawer, scripted clarifying exchange, composed refined question + suggested context, REQ-68), Choose (methodology cards with ETA/cost/why-recommended; dials behind "advanced"), Plan & Run (approve/edit plan, live SSE trace, pause/cancel), Reading Room v0 (rendered report, hover-a-citation → exact quoted passage, ledger panel, Markdown/JSON export), Library (P5: folder-structure report storage — auto-categorized folders, recency/title sorting, report cards into the Reading Room; cross-report Connections panel — shared-sources ⇄ / related-topic → edges; project graph + task inbox as v2-preview panels), Settings (P5: masked API-key status, storage directory, default methodology + resolved 12-dial display, appearance preview, about/version).
 
 - **Boundaries:** consumes the typed `ApiClient` interface only — components never import the mock client directly. In v0.1 the interface is bound to `MockApiClient` (fixture data + scripted event replay); in v0.2 phase 3 the binding swaps to the OpenAPI-generated client with no component changes.
 - **DependsOn:** ApiClient contract (v0.1: mock; v0.2: API layer)
@@ -58,7 +58,7 @@ v0.1 (prototype): Ask (question + context) → Choose (methodology slug + dial o
 v0.2 (MVP): Ask (question + context) → Choose (methodology slug + dial overrides) → POST /api/runs → engine PLANNING (planner model via model adapter, dial bundle resolved) → AWAITING_APPROVAL (plan persisted; SSE events; user approves/edits) → SEARCHING (search adapter, routing per dials) → EXTRACTING (fetch pages → evidence store, stable passage IDs) → REFLECTING (planner model; depth loop per dials) → SYNTHESIZING (writer model; context = evidence passages only, per-claim citation markers) → VERIFYING (liveness pass, quote anchoring, confidence labels) → DONE (report + ledger + checklist persisted to storage; Reading Room renders; export).
 
 ## Build Order
-Milestone v0.1 (prototype): 1. Frontend scaffold + ApiClient/MockApiClient boundary → 2. Ask + Choose → 3. Plan & Run + Reading Room v0 → 4. v2 mockups + polish + 3-click validation → 5. review + owner approval gate (owner returned gate feedback → extension cycle: 5. app shell + research library + settings + avatar → 6. final review + approval re-presentation + ship).
+Milestone v0.1 (prototype): 1. Frontend scaffold + ApiClient/MockApiClient boundary → 2. Ask + Choose → 3. Plan & Run + Reading Room v0 → 4. v2 mockups + polish + 3-click validation → 5. review + owner approval gate (owner returned gate feedback → extension cycle: 5. app shell + research library + settings + avatar → 6. final review + approval re-presentation (2nd owner gate feedback: 7. ask suggestions + refine dialogue → 8. final re-review + ship)).
 
 Milestone v0.2 (MVP, gated on v0.1 approval):
 1. Methodology framework (dial schema + 2 seed methodologies + registry)

.ciagent/CHECKPOINT.json

@@ -1,8 +1,8 @@
 {
-  "phase": 7,
-  "stage": "execute",
-  "milestone": "v0.1",
-  "phase_role": "execution",
+  "phase": 5,
+  "stage": "complete",
+  "milestone": "v0.2",
+  "phase_role": "final",
   "attempts": 0,
-  "updated_at": "2026-09-27T05:10:00Z"
-}
+  "updated_at": "2026-09-27T16:30:00Z"
+}

.ciagent/GRILL.md

@@ -0,0 +1,219 @@
+# CIAgent Grill Report
+
+## Run: 2026-09-27 11:25 (mode: mechanical, focus: all)
+
+### Verdict: Proceed  (confidence: 0.72)
+
+The plan is sound with fixable gaps. The evidence base is unusually strong for a project at P0: a shipped and owner-approved v0.1 (9 tags, decision commit 3fd0e10), a locked two-milestone structure, a typed frontend boundary already in the tree (client.ts), a research file with concrete API shapes, and honest `---ci---` reporting throughout. But the grill found **two internal contradictions and one measurability hole** that would each have surfaced at P3 as rework: (1) PLAN.md P1 claims REQ-07/REQ-12 delivery while ROADMAP/REQUIREMENTS/PLAN's own frontmatter map them to P2; (2) the approved prototype's ApiClient documents seven v0.2 endpoint mappings (`GET /api/graph`, `GET /api/tasks`, `GET /api/library`, `GET /api/library/connections`, `GET /api/suggestions`, `POST /api/refine/*`, `PUT /api/config`) that REQ-25 does not include — a hidden-scope grenade wired to the P3 swap; (3) REQ-23's ≥99% liveness bar cannot be proven in the zero-key test suite it is scheduled into. All three are absorbed below as binding decisions. The MVP does not overreach as specced — REQ-01..34 is a genuine core loop — but the *implicit* live-mode expectation (whole prototype UI working against the backend) does overreach, and is explicitly reduced to the core research loop (G-002, escalated for owner ratification at the P5 gate).
+
+---
+
+### Axis 1 — Business Case
+- **Q1**: What problem does this actually solve, and is that problem still the top priority?
+  - Evidence: PROJECT.md Core Value + Key Decisions ("deep-research agents hallucinate URLs at the highest measured rates; verification cuts failures to <1% [E1]"); owner approved v0.1.8 and immediately unblocked v0.2 (commits 3fd0e10, 42435bc).
+  - Answer: Real, named problem — citation-untrustworthy deep-research agents — converted into a differentiated product thesis (methodology-first + trust loop). The owner's same-day unblocking of v0.2 shows it remains the top priority. Not a project that outlived its justification: the value is entirely unrealized until the MVP ships, which argues for proceeding, not stopping.
+  - Confidence: 0.80
+- **Q2**: Who is the named executive sponsor, and when did they last make a decision under pressure?
+  - Evidence: Owner decisions under pressure recorded twice in v0.1: P4 gate returned *feedback instead of approval* → binding P5/P6 extension (ROADMAP P4 note, commit 7db53d62); P6 gate returned *2nd feedback* → P7/P8 extension (commit 57c5231, ROADMAP P6 note); final approval 3fd0e10. D-018/D-019 record owner directives for this run.
+  - Answer: The sponsor is pressure-tested, not a rubber stamp — two rejections/extensions before approval. This is the strongest possible sponsor signal available in the record.
+  - Confidence: 0.85
+- **Q3**: What happens to the business if the project is cancelled?
+  - Evidence: v0.1 is mock-only by design (REQ-53: "no backend, no API keys"); zero research value has shipped; all value lands in v0.2 (REQ-01..34).
+  - Answer: Cancelling now strands 100% of sunk effort — the prototype is a shell without the MVP. The project is not a zombie; it is the opposite: a project whose entire value is still ahead of it, which raises the stakes of P2/P3 execution quality, not the case for stopping.
+  - Confidence: 0.75
+- **Q4**: Is the ROI calculated against a counterfactual?
+  - Evidence: MISSING — no ROI/counterfactual calculation exists anywhere in .ciagent/.
+  - Answer: No formal ROI. The implicit counterfactual is "ad-hoc LLM prompting with unverified citations," which is plausible but never quantified. For an owner-directed, single-user, local-first tool this is a tolerable omission — the sponsor is the beneficiary — but it means priority calls rest entirely on owner judgment, with no objective measure if enthusiasm fades.
+  - Confidence: 0.55
+  - Decision: G-007 — make the counterfactual *measurable in-product*: per-run request/token/cost counters in the run trace, surfaced via `GET /api/config` (advisory, no hard spend cap in MVP). This is the cheapest honest ROI instrumentation available.
+
+### Axis 2 — Scope and Requirements
+- **Q1**: Is the scope expanding, contracting, or genuinely stable?
+  - Evidence: REQ-01..34 locked with traceability (REQUIREMENTS.md table); D-007..D-020 clarify commit recorded (e79102b); v0.1 scope *grew twice* via owner gate feedback (P5/P7 extensions) — proof the gate can grow scope.
+  - Answer: The formal scope is stable and frozen. But the grill found the *informal* scope is ambiguous: the prototype's approved UI implies backend endpoints that REQ-25 does not promise (see Q4). That ambiguity will resolve itself at P3 — either as scope growth or as a visible degraded mode. It must be resolved now, in writing.
+  - Confidence: 0.60
+- **Q2**: Who owns the requirements, and have they been frozen?
+  - Evidence: Owner-approved milestone structure (PROJECT.md Constraints); REQUIREMENTS.md traceability with per-phase status; clarify decisions D-007..D-020 at confidence 0.75–1.0.
+  - Answer: Owner owns; the pipeline freezes and traces them. Requirements management is this project's strongest discipline.
+  - Confidence: 0.85
+- **Q3**: What is explicitly out of scope?
+  - Evidence: REQUIREMENTS.md "Out of Scope" table (paywalled sources, chatbot/hosting, auth/multi-tenancy, native Ollama adapter, rename, autonomous v1.0.0); PROJECT.md Out of Scope.
+  - Answer: Explicit, reasoned, and enforced (e.g., OpenAI-compatible-only is restated in constraints and architecture).
+  - Confidence: 0.90
+- **Q4**: Are there hidden requirements only disclosed late in delivery?
+  - Evidence: **FOUND — two.** (a) `frontend/src/lib/api/client.ts` lines 123–179 document v0.2 mappings to `GET /api/graph`, `GET /api/tasks`, `GET /api/library`, `GET /api/library/connections`, `GET /api/suggestions`, `POST /api/refine/questions`, `POST /api/refine/compose`, `PUT /api/config` — none of which appear in REQ-25 (runs, methodologies, lifecycle, SSE, config-read only) or any v0.2 phase mapping. (b) The same file exposes no `pauseRun`/`resumeRun` while REQ-25 mandates pause/resume in the API and REQ-15 mandates server-side pause/resume across restarts; line 69's comment claims "pause/resume stay client-side concerns," which contradicts the engine requirement.
+  - Answer: The P3 swap ("behind the unchanged ApiClient interface," REQ-26/REQ-54) is wired to detonate: either the backend grows 7+ undocumented endpoints (scope expansion inside the MVP milestone), or live mode silently breaks six approved UI surfaces, or the interface changes anyway (breaking REQ-54's zero-rewrite promise without a plan). This is the single largest finding of this grill.
+  - Confidence: 0.50
+  - Decision: G-002 — declare the v0.2 live-mode surface = **core research loop only** (Ask, Choose, Plan & Run, Reading Room + read-only `GET /api/config`); Library, Settings persistence, Suggestions, Refine, project graph, task inbox, and user profile stay mock-bound behind ApiClient in live mode, honestly marked in-UI, with their backends explicitly deferred to v0.3+. G-003 — add `pauseRun`/`resumeRun` to ApiClient in P3 as the single planned, documented interface extension (mock gains matching implementations), superseding the v0.1 client-side-pause comment; REQ-54's zero-rewrite promise is amended to "no *unplanned* rewrites."
+  - Escalation: [G-009] — owner must ratify the live-mode boundary at the P5 gate (see Escalations).
+
+### Axis 3 — Architecture and Technical Feasibility
+- **Q1**: Has the architecture been validated by the people who will build and operate it?
+  - Evidence: RESEARCH-v02.md — 8 topics with concrete API payload shapes, pitfalls, and 14 conclusions written for the builders (pydantic event unions, shielded state writes, `os.replace` atomicity, pytest-asyncio modes, hatchling `packages` key). But `backend/` does not exist yet — zero lines of the architecture have run.
+  - Answer: Design-side validation is strong (this is what a builder-facing research doc should look like); runtime validation is zero, by definition of P0. The risk concentrates at first contact: ollama.com/v1 shapes, Tavily payload, SSE backpressure. P1 Wave 3 is the first live proof.
+  - Confidence: 0.65
+- **Q2**: What is the integration surface, and where does it quietly double in cost?
+  - Evidence: Five adapter slots (ARCHITECTURE §2); SSE transport (D-014); OpenAPI client generation (D-013, RESEARCH §7 — flags operation-id stability and regen-from-snapshot discipline as pitfalls); the ApiClient surface gap (Axis 2 Q4).
+  - Answer: 5 adapters + SSE + codegen swap = 7 integration seams. The cost-doubling candidate is the P3 swap (seam #7) — precisely where the undocumented-endpoint problem sits. Second candidate: the openapi.json snapshot discipline exists only as a research *pitfall note*, not a P3 must-have.
+  - Confidence: 0.60
+  - Decision: G-005 — P3 must-have: commit the backend `openapi.json` snapshot; regenerate `frontend/src/lib/api/generated/` only from the snapshot (never a live server); add a schema-drift check to the gates; fix FastAPI operation-ids at route creation.
+- **Q3**: Is there an existing system being replaced — actual data volume, transaction rate, edge-case behavior?
+  - Evidence: Greenfield backend; the "replaced system" is `MockApiClient` (fixtures + scripted replay, frontend/src/lib/api/mock/). REQ-54 defines the swap contract; PERSONAS.md binds the frontend-engineer to it.
+  - Answer: No data migration risk. The migration is one interface binding line (client.ts:187) — provided G-002/G-003 are absorbed; otherwise the "small migration" is the biggest one in the project.
+  - Confidence: 0.70
+- **Q4**: What technical debt is inherited, and is it budgeted for?
+  - Evidence: (a) the v0.1 "client-side pause" comment (client.ts:69) contradicting REQ-15 — budgeted via G-003. (b) DDG `html.duckduckgo.com/html` scrape as the keyless fallback (D-012, confidence 0.75) — RESEARCH §3 itself warns "rate-limits aggressively... best-effort." (c) Scripted-replay SSE shape must match D-014's event union — verified aligned (D-014 rationale cites the MockApiClient replay contract).
+  - Answer: The DDG fallback is the fragility hotspot: a legacy HTML surface, conservatively scraped, that the research file already expects to fail. The zero-config promise of the product rests partly on it. Mitigation exists in design (surfaced warning, never hang) but is not yet test-enforced.
+  - Confidence: 0.55
+  - Decision: G-008 — DDG fallback is tested against recorded HTML fixtures only (never live-scraped in CI); the degradation contract (partial/empty results + typed warning, never hang, never block the engine) is asserted by test. DDG is documented as degraded-mode, not a reliable second source.
+
+### Axis 4 — People, Skills, and Organization
+- **Q1**: Which 2–3 people, if they left, would the project fail?
+  - Evidence: The entire delivery capability is one agent pipeline (coreci) + one owner (decision commit 3fd0e10; all directives owner-recorded). PERSONAS.md is a persona roster, not a human team.
+  - Answer: Key-person dependency is total and structural: owner disengagement stalls every gate by design (that is the governance model); pipeline failure stops all delivery. For a single-user, owner-directed tool this is acceptable — but it means timeline estimates are really "pipeline availability" estimates, and there is no bench.
+  - Confidence: 0.60
+- **Q2**: Are resources actually allocated at the percentages claimed?
+  - Evidence: Autonomy level "full" (config.json); v0.1 shipped 9 phases, PRs #1–#8, tags v0.1.0–v0.1.8 within ~10 hours of wall clock (commits dd2538f 00:44 → d6ddcfe 10:03, 2026-09-27).
+  - Answer: The pipeline is demonstrably 100% allocated and not fighting BAU fires — velocity is exceptional and verified by artifact trail, not status reports.
+  - Confidence: 0.85
+- **Q3**: Is there a product owner with actual authority to prioritize?
+  - Evidence: Owner directives recorded as binding decisions (D-018, D-019 at confidence 1.0); two gate rejections prove authority in practice.
+  - Answer: Unambiguous single owner; no committee. Model is working.
+  - Confidence: 0.90
+- **Q4**: Is the team building capability it doesn't have, hoping to learn as they go?
+  - Evidence: The stack is being built in-milestone: FastAPI, asyncio durability (shielded writes, CancelledError discipline — RESEARCH §5), sse-starlette, httpx adapters, openapi codegen. No backend code exists yet (repo is frontend-only today). RESEARCH-v02.md documents the failure modes in advance (pytest-asyncio event_loop removal, hatchling src-layout wheel pitfall, uvicorn single-worker constraint).
+  - Answer: Yes, capability is being built on the fly — acceptable here because (a) this is a prototype-to-MVP transition with research-backed patterns, and (b) zero-key fakes (REQ-31) mean the engine can be proven without live services. But P2 is where "learning asyncio under load" meets "13 requirements" — see Axis 5.
+  - Confidence: 0.60
+
+### Axis 5 — Timeline and Estimates
+- **Q1**: Was the deadline set before or after scope and approach were understood?
+  - Evidence: No wall-clock deadlines exist anywhere in ROADMAP v0.2 — sequencing is dependency-driven (P0→P5), cadence is owner gates (D-018: halt at the owner approval gate).
+  - Answer: No reverse-engineered deadline — the healthiest possible pattern. The only "date" is the owner's attention, which v0.1 proved is present.
+  - Confidence: 0.85
+- **Q2**: What is the critical path, and what single thing would push it by 3+ months?
+  - Evidence: Critical path P1 → P2 → P3 → P4 (sequential phases, ROADMAP). P2 is the milestone's heaviest phase: 13 requirements (REQ-07, 12, 13–24) including the durable asyncio state machine, trust loop, and live probing. The 3-month pusher is a P3 integration-drift discovery: the ApiClient surface gap (Axis 2 Q4) hitting mid-swap, after P2's engine is built against the wrong boundary assumptions.
+  - Answer: Critical path is P2-heavy and P3-fragile. G-002/G-003 defuse the P3 risk; P2's size needs a pressure valve.
+  - Confidence: 0.70
+  - Decision: G-006 — permit P2 to ship as two patches (P2a: engine + durable state + SSE; P2b: trust loop + live probe/REQ-07/12) or run mid-phase wave gates, without changing milestone scope; the P3 swap plan (endpoint list per G-002) must be drafted at P2 *start*, not P3 start, so drift surfaces before the engine is frozen.
+- **Q3**: Are the estimates evidence-based?
+  - Evidence: The only velocity base is v0.1: ~1 phase/hour sustained across 9 phases including review+audit each. v0.2 phases are materially heavier (greenfield backend, adversarial tests). MISSING: any per-phase sizing in ROADMAP/PLAN.
+  - Answer: No estimates exist to be wrong — but also none to be right. v0.1 velocity does not transfer 1:1 (frontend screens vs. a durable async engine); treating it as a base rate would understate P2. The mitigation is the phase-patch mechanism (G-006) rather than fake numbers, which this grill endorses over invented estimates.
+  - Confidence: 0.60
+- **Q4**: Is there a working definition of done?
+  - Evidence: Per-phase success criteria (ROADMAP); PLAN.md gates + "REQ coverage assert: each REQ mapped to ≥1 test or contract proof"; verify stage precedent (PASS-WITH-FIXES with in-phase P0 fixes, PRs #4/#6/#8); final owner gate.
+  - Answer: Yes, and it is enforced — v0.1 reviews fixed 5 P0s and multiple P1s *in-phase*, which is proof the DoD has teeth.
+  - Confidence: 0.85
+  - Decision: G-001 — resolve a DoD contradiction inside P1's own plan: PLAN.md must_haves and tasks T-1.10/T-1.11 claim REQ-07/REQ-12 delivery ("GET /models + structured-output smoke test" = live probing) while PLAN's frontmatter (`requirements: [REQ-01..06, 08..11, 31]`), ROADMAP P1 ("REQ-07, REQ-12 ship in P2... live probing against real endpoints in P2"), and REQUIREMENTS traceability all map them to P2. Binding: P1 ships the typed ProbeResult + structured-output warning *contracts* proven with fake adapters; live endpoint probing executes in P2 with the engine. Secondary bookkeeping fix in the same decision: the "REQ-13..24" range notation includes REQ-17 in both P2 and P4 rows — REQ-17 (3-click on real stack) stays in P4; ranges are corrected to exclude it.
+
+### Axis 6 — Budget and Financial Realism
+- **Q1**: What percentage of budget is spent vs. remaining?
+  - Evidence: MISSING — no cost ledger exists. Known spends: pipeline tokens (v0.1: 9 phases of agent execution; v0.2 P0 stages), Ollama cloud key (config.json secrets scope `model`), Tavily key (scope `search`), self-hosted LXC infra (DEPLOY-RECORD.md).
+  - Answer: Untracked. For a single-user local-first tool the absolute numbers are small, but "untracked" is still a finding: no one can currently answer what a Deep Report run costs.
+  - Confidence: 0.60
+- **Q2**: Are there predictable cost drivers not in the original budget?
+  - Evidence: Deep Report = depth 3/breadth 2 → per run: ~dozens of model calls (planner + depth-loop reflections + writer + verification passes) plus search calls; Ollama cloud is pay-per-use; Tavily free tier is quota-capped; DDG fallback is free-but-fragile (D-012). Localhost:11434 fallback is the zero-cost escape hatch (REQ-08).
+  - Answer: Cost drivers are real and unbounded per run (no request caps on loops beyond dial defaults). The local-fallback design keeps the project from *hard* dependency on spend, but there is no visibility.
+  - Confidence: 0.60
+  - Decision: G-007 — per-run counters (model requests, tokens, search calls) recorded in the run trace and surfaced via `GET /api/config`; advisory only in MVP.
+- **Q3**: Burn rate and runway?
+  - Evidence: MISSING formal tracking; mitigated by local-first defaults (keyless localhost fallback, DDG keyless fallback) meaning the runway floor is "zero marginal cost, degraded mode."
+  - Answer: The architecture is honest about this: the product's default posture degrades to free. Runway is effectively unbounded if the owner accepts degraded mode; the grill accepts this as sound for the MVP.
+  - Confidence: 0.70
+- **Q4**: Is the budget contingent on something that hasn't happened yet?
+  - Evidence: No — no sale/board/hiring dependency. Keys exist (config.json scopes), infra exists (LXC), pipeline is running.
+  - Answer: Not contingent. Proceed.
+  - Confidence: 0.80
+
+### Axis 7 — Risks, Assumptions, and Dependencies
+- **Q1**: Top 3 assumptions, and evidence for each?
+  - Evidence: (a) *Adapter endpoint compatibility* — ollama.com/v1 OpenAI-shape and Tavily POST payload researched with concrete shapes (RESEARCH §2/§3), but unvalidated live in-repo; P1 Wave 3 is the test. (b) *DDG fallback stability* — RESEARCH §3 itself rates it "best-effort, aggressively rate-limited" (weakest assumption in the plan; D-012 confidence 0.75). (c) *Zero-rewrite client swap* — typed boundary exists (client.ts), RESEARCHX_API_MODE designed (D-020), but the interface gaps (Axis 2 Q4) undercut it until G-002/G-003 land.
+  - Answer: Two of three are well-evidenced; the DDG assumption is the one the project's own research argues against relying on. All three have named first-contact phases (P1 Wave 3, P2, P3).
+  - Confidence: 0.60
+  - Decision: G-008 (fixture-tested DDG degradation contract) — see Axis 3 Q4.
+- **Q2**: External dependencies outside the team?
+  - Evidence: Tavily quota; Ollama cloud key validity; DDG uncontrolled HTML surface; none of these are under the project's control; all have fallbacks *except* Tavily→DDG quality.
+  - Answer: Dependencies are acknowledged with degradation paths — the correct posture. The unmitigated residual is *degraded search quality* when Tavily is exhausted, which directly attacks the ≥99% liveness bar.
+  - Confidence: 0.65
+- **Q3**: The single risk that kills the project, and is there a mitigation?
+  - Evidence: P3 swap discovering the ApiClient/surface drift after the engine is frozen (evidence chain: client.ts:123–179 vs REQ-25; ROADMAP P3 "the ApiClient interface absorbs any prototype-era API drift" — an assertion, not a plan).
+  - Answer: Kill risk = integration drift at P3 → rework spiral through a hand-rolled engine → owner patience (already tested twice by extensions) exhausts. Mitigation now exists in writing: G-002 (boundary declared), G-003 (interface change planned), G-005 (snapshot discipline), G-006 (P3 plan drafted at P2 start). This grill's core job is done if those four hold.
+  - Confidence: 0.65
+- **Q4**: Has a pre-mortem been done?
+  - Evidence: MISSING — no pre-mortem artifact. This grill is the closest proxy.
+  - Answer: "It's 12 months out and v0.2 failed" — the derivable causes, in order: (1) P3 surface gap hit late (mitigated: G-002/003/005/006); (2) P2 asyncio durability bugs (pause/resume across restarts is genuinely hard — mitigated by RESEARCH §5 patterns + REQ-32 pause-mid-depth-loop adversarial tests); (3) quote anchoring thrash on real noisy pages (difflib 0.85 is fixture-proven only — live-page behavior unknown until P4/live runs); (4) DDG dead + Tavily exhausted → un-demoable zero-config mode (mitigated: G-008 + owner-held Tavily key).
+  - Confidence: 0.60
+
+### Axis 8 — Governance, Decision-Making, and Communication
+- **Q1**: Who is the decision-maker when two parties disagree?
+  - Evidence: Single owner; all decisions recorded as decision commits (3fd0e10; D-007..D-020 in e79102b); escalation hooks codified in config.json (deploy, delete_data, merge_to_main, prototype_approval).
+  - Answer: Unambiguous. No dual-executive stall is possible in this structure.
+  - Confidence: 0.90
+- **Q2**: Governance cadence and escalation pattern — useful in a crisis?
+  - Evidence: Per-phase ship + verify + audit with `---ci---` blocks; v0.1 precedent: pipeline *halted itself* at gates twice (7db53d62, 57c5231) rather than self-approving — the escalation pattern is proven under the exact stress it exists for.
+  - Answer: Cadence is per-phase and gates have been exercised under pressure. Crisis-tested by construction.
+  - Confidence: 0.85
+- **Q3**: What is being omitted from status reports?
+  - Evidence: Honest reporting verified in history: "PASS-WITH-FIXES," "PASS-WITH-NOTES," "approval_pending," P0s disclosed and fixed in-phase; DEPLOY-RECORD.md as a separate ledger. The one systemic omission this grill found lives in *spec comments, not status blocks*: the client.ts v0.2 endpoint mappings that were never promoted into REQUIREMENTS — a silent scope assumption, now surfaced (G-002).
+  - Answer: Status reporting is honest. Spec-side implication drift is the channel where optimism leaked — and it's now on the record.
+  - Confidence: 0.80
+- **Q4**: Is there a stop-the-project trigger?
+  - Evidence: Owner rejection at gate → binding fix cycle (v0.1 exercised twice); v1.0.0 owner-only (config.json major_locked); D-018 halts at the v0.2 gate; D-019 forbids deploys without directive.
+  - Answer: Yes — and rejection has demonstrably not become politically impossible; the owner said "not yet, extend" twice without ceremony.
+  - Confidence: 0.85
+
+### Axis 9 — Change, Adoption, and Operational Readiness
+- **Q1**: Who will use this, how does their work change, and what's in it for them?
+  - Evidence: Single-user owner-researcher (PROJECT.md constraint: "Single-user, local-first"); work change = ad-hoc prompting → structured, reproducible methodology runs with auditable citations (REQ-04 dial snapshots, REQ-21 ledger, REQ-22 checklist).
+  - Answer: The user is the sponsor — adoption politics are minimal, and the value proposition (trustable citations) is the same thesis the sponsor approved twice. The real adoption test is whether live-mode runs *feel* better than the mock — which lands at P4/REQ-17.
+  - Confidence: 0.80
+- **Q2**: Is ops involved now, or handed a finished product at go-live?
+  - Evidence: The pipeline *is* ops: deploy.sh with rolling swap + `researchx-prev` rollback container (commit 2ffc71c), gates re-run at deploy time (DEPLOY-RECORD.md rows), VERSIONING.md rules. Gap: the deploy system is frontend-only; the MVP's live mode requires a local backend process (uvicorn, single worker — RESEARCH §4) whose serving story at the owner gate is undefined (D-019 forbids deploys without directive, so live-mode *presentation* mode is an open question).
+  - Answer: Ops is built-in and rollback-capable for the frontend. The backend has no deploy story — coherent with local-first, but it means the P5 owner-gate demo of the *live* MVP needs a plan (local backend + keys at demo time, or gate runs on mock mode). This rides with G-009.
+  - Confidence: 0.60
+- **Q3**: What is the rollback plan?
+  - Evidence: Tags v0.1.0–v0.1.8 preserve history; deploy.sh swaps containers with a `researchx-prev` rollback; durable run state is per-run JSON on local disk (D-017) — engine changes cannot corrupt other runs' state; frontend mock mode (RESEARCHX_API_MODE=mock default, D-020) is itself a rollback for the entire live integration.
+  - Answer: Multi-layer rollback exists and is codified. The mock-default flag is an unusually good one — the MVP can ship with live mode opt-in, making go-live risk nearly zero.
+  - Confidence: 0.80
+- **Q4**: Have success criteria been validated with the people who will judge success?
+  - Evidence: REQ-17 (≤3 clicks on real stack) is P4-tested, validated on mock in v0.1 (REQ-61 pinned by test). REQ-23 (≥99% citation liveness) — **measurement gap**: the entire adversarial suite is zero-key on a 5–8 page fixture corpus (RESEARCH §5b); 99% liveness on fixture URLs is vacuous, and no keyed/live validation run is scheduled anywhere in P1–P5.
+  - Answer: The 99% bar — the project's headline promise — is currently scheduled to be "verified" in a harness that cannot verify it. If the owner gate treats REQ-23 as CI-green, the status report will be honest-looking but hollow.
+  - Confidence: 0.55
+  - Decision: G-004 — REQ-23 is defined as a **runtime per-run gate** enforced at export (failures listed in the verification checklist, REQ-22) plus an opt-in, keyed, live-URL test tier (skipped by default, run before ships at owner discretion); P4 proves the *gate mechanics* with fixtures and explicitly does not claim live 99% attainment. The MVP definition of done for REQ-23 = the gate exists and enforces, not "CI showed 99%."
+
+### Meta — Closing Review
+- **Q1**: If you were the auditor, what would you flag?
+  - Evidence: The two internal contradictions (PLAN vs ROADMAP/REQUIREMENTS on REQ-07/12, PLAN must_haves vs PLAN frontmatter; REQ-17 double-mapped in range notation) and the spec-comment endpoint mappings outside REQ-25 (client.ts:123–179).
+  - Answer: Flag #1: phase-mapping integrity — the traceability table is the single source of truth and PLAN must conform to it (G-001). Flag #2: an approved artifact (client.ts) documents v0.2 API surface that the v0.2 spec does not contain — the grill treats this as the most consequential process lapse found, because it would have surfaced as a P3 "surprise" after the engine was frozen.
+  - Confidence: 0.75
+- **Q2**: What is the project not doing that it should?
+  - Evidence: Missing items found across axes: openapi snapshot drift check as a gate (G-005), per-run cost counters (G-007), live-URL test tier for REQ-23 (G-004), P3 swap plan at P2 start (G-006), fixture-based DDG tests (G-008), live-mode boundary declaration (G-002).
+  - Answer: All six are now bound. Nothing found suggests the project is doing something it should not.
+  - Confidence: 0.75
+- **Q3**: What is the simplest version that delivers 80% of the value?
+  - Evidence: The MVP already trimmed to 2 of 8 methodologies (REQ-03) and a core-loop-only API (REQ-25). The remaining 20% of complexity carrying outsized risk: Deep Report's depth-3 breadth-2 loop (multiplies engine, trust, and cost surface) vs. Rapid Answer's depth-1 single-pass core.
+  - Answer: Rapid Answer alone + trust loop = 80% of the thesis proof. Deep Report is the pre-agreed deferral lever if P2 overruns — decided *now*, while it is cheap, rather than mid-crisis.
+  - Confidence: 0.65
+  - Decision: G-010 — contingency lever, pre-agreed: if P2/P4 slip beyond one extension cycle, Deep Report (REQ-03 partial) defers to v0.3 and the MVP ships Rapid Answer end-to-end; the lever requires owner sign-off when pulled, per gate rules.
+- **Q4**: What must be true for this to succeed in the next 90 days, and is it true today?
+  - Evidence: Required: (a) researched adapter shapes hold live (untested — first proof P1 Wave 3); (b) owner engagement continues (proven: 3 gate decisions in one day); (c) Tavily key active/quota available (held in secrets scope; unverified live); (d) the P3 boundary is as declared in G-002 (currently *not* true in writing — client.ts says otherwise).
+  - Answer: Three of four are true or evidenced; (d) becomes true when the orchestrator promotes G-002/G-003. That promotion is the gating action of this entire grill.
+  - Confidence: 0.70
+
+---
+
+### Binding Decisions
+| ID | Axis | Decision | Confidence |
+|----|------|----------|-----------|
+| G-001 | 2/5 | Resolve the REQ-07/REQ-12 phase contradiction in PLAN.md's favor of the ROADMAP/traceability mapping: P1 ships typed probe/warning contracts proven with fakes; live endpoint probing (GET /models, structured-output smoke test) executes in P2. Reword PLAN must_haves T-1.10/T-1.11 to contract level; fix the REQ-13..24 range notation so REQ-17 appears only in P4. | 0.85 |
+| G-002 | 2/3 | Declare v0.2 live-mode surface = core research loop only (Ask, Choose, Plan & Run, Reading Room, read-only GET /api/config). Library, Settings persistence, Suggestions, Refine, project graph, task inbox, user profile stay mock-bound in live mode, honestly marked; their backends are v0.3+ scope. Update client.ts v0.2-mapping comments accordingly. | 0.80 |
+| G-003 | 3 | Add `pauseRun`/`resumeRun` to the ApiClient interface in P3 as the single planned, documented interface extension (mock gains matching implementations); run-level pause is server-side per REQ-15/REQ-25, superseding the v0.1 "client-side concerns" comment. REQ-54 amended: no *unplanned* rewrites. | 0.80 |
+| G-004 | 7/9 | REQ-23 (≥99% liveness) is a runtime per-run gate enforced at export and surfaced in the verification checklist — not a zero-key CI assertion. Add an opt-in keyed live-URL test tier (skipped by default). P4 proves gate mechanics with fixtures; MVP DoD for REQ-23 = the gate exists and enforces. | 0.75 |
+| G-005 | 3/5 | P3 must-have: commit the backend openapi.json snapshot; regenerate frontend/src/lib/api/generated/ only from the snapshot; add a schema-drift check to gates; fix FastAPI operation-ids at route creation. | 0.85 |
+| G-006 | 5 | Permit P2 (13 REQs — heaviest phase) to ship as two patches (P2a engine+durable state+SSE, P2b trust loop+live probe) or run mid-phase wave gates without milestone scope change; draft the P3 swap endpoint plan (per G-002) at P2 start, not P3 start. | 0.70 |
+| G-007 | 1/6 | Per-run advisory counters (model requests, tokens, search calls) recorded in the run trace and surfaced via GET /api/config — the cheapest honest ROI/burn instrumentation; no hard spend cap in MVP. | 0.70 |
+| G-008 | 3/7 | DDG fallback tested against recorded HTML fixtures only (never live-scraped in CI); degradation contract (partial/empty + typed warning, never hang the engine) asserted by test; DDG documented as degraded-mode, not a reliable second source. | 0.70 |
+| G-010 | Meta | Pre-agreed contingency lever: if P2/P4 slip beyond one extension cycle, Deep Report (depth 3) defers to v0.3 and the MVP ships Rapid Answer end-to-end; pulling the lever requires owner sign-off at a gate. | 0.65 |
+
+### Escalations
+- [G-009] Axis 2 — Owner ratification required at the P5 gate (D-018 halt): the v0.2 MVP demonstrates the **live core research loop only**; the remaining approved-prototype surfaces (Library, Settings persistence, Suggestions, Refine, graph/inbox previews, profile) remain mock-bound until v0.3+, and the live-mode gate demo requires a local backend + keys (or runs in mock mode) since D-019 forbids deploys. This redefines what "MVP done" looks like at the demo and must not be discovered by the owner at the gate — it must be ratified in advance. Engineering-side handling is bound in G-002/G-003; the ratification itself is unresolved until the owner records it.
+  - **RESOLVED 2026-09-27: RATIFIED.** Owner approval recorded via /ci-run 'APPROVED' at the v0.2.5 gate (decision commit 4721c2a), following the owner-directed UAT staging at https://research.coreci.dev. Live-mode scope = core research loop only is the accepted MVP boundary; mock-bound surfaces move to v0.3+.

.ciagent/PERSONAS.md

@@ -1,46 +1,56 @@
-# Personas — Milestone v0.1 (Prototype)
+# Personas — Milestone v0.2 (MVP)
 
 ---
 active:
+  - name: backend-engineer
+  - name: data-engineer
   - name: frontend-engineer
   - name: ci-lead-developer
-phase_specific: []
-reason: "v0.1 is a pure frontend prototype (Next.js, mock data). Only the frontend domain has work; backend/data personas activate in v0.2. Lead-developer coordinates decomposition and enforces the ApiClient boundary."
+phase_specific:
+  - name: security-engineer
+    phases: [2]
+reason: "v0.2 is the MVP: FastAPI backend + engine + adapters + trust loop (backend/data domains activate), the frontend consumes the OpenAPI-generated client in P3 (frontend stays active for the binding swap + P4 E2E), and the trust loop in P2 needs a phase-specific security-engineer for secrets handling and liveness verification. Lead-developer coordinates."
 ---
 
 ## Roster
 
+### backend-engineer
+- **Domain**: backend
+- **Active**: true
+- **Phase-specific**: false
+- **Frameworks**: fastapi, pydantic v2, uv, uvicorn, sse-starlette, httpx, pytest, pytest-asyncio
+- **Constraints**: src-layout package `researchx` in backend/; all external I/O lives in adapters — engine imports no vendor SDKs (httpx only inside adapters); no blocking calls in async paths; durable state via atomic tmp+os.replace; never swallow CancelledError; API layer is transport only (no business logic); single uvicorn worker (single-user)
+- **Territory**: `backend/**`
+
+### data-engineer
+- **Domain**: data
+- **Active**: true
+- **Phase-specific**: false
+- **Frameworks**: pydantic v2 (schemas), pytest
+- **Constraints**: owns the pydantic schema contracts: dial schema (REQ-01), run state, evidence store models (stable passage IDs), citation ledger JSON schema (REQ-21); pure data + validation — no I/O in schema modules; every run persists resolved dial values (REQ-04)
+- **Territory**: `backend/src/researchx/config/**`, `backend/src/researchx/evidence/**`
+
 ### frontend-engineer
 - **Domain**: frontend
 - **Active**: true
 - **Phase-specific**: false
-- **Frameworks**: next.js (App Router), react 19, typescript (strict), tailwind, vitest
-- **Constraints**: component-first; server components by default, client components only where interactivity demands; all data access through the ApiClient interface — components never import MockApiClient directly; no secrets or env keys in the frontend; typography care per vision §4
+- **Frameworks**: next.js (App Router), react 19, typescript (strict), tailwind, vitest, openapi-fetch, openapi-typescript
+- **Constraints**: components never import the mock client or the generated client directly — only the ApiClient boundary does; RESEARCHX_API_MODE=mock|live selects the binding, mock default; no secrets or env keys in the frontend (NEXT_PUBLIC_API_BASE_URL only); zero component rewrites in the P3 swap (REQ-54/REQ-26)
 - **Territory**: `frontend/**`
 
+### security-engineer (phase-specific: P2)
+- **Domain**: security
+- **Active**: false (P2 shipped — removed per phase-specific policy)
+- **Phase-specific**: true
+- **Frameworks**: httpx, pytest, STRIDE analysis
+- **Constraints**: secrets resolve from env-file scopes only (OLLAMA_API_KEY, TAVILY_API_KEY, GITEA_TOKEN via .ciagent/.env.secrets) — never shell env, never logged, never in git; liveness verification and trust-loop code must not leak keys in errors or traces; SSRF guard for fetched URLs (private-address refusal); authority tiering must not phone home
+- **Territory**: `backend/src/researchx/trust/**`, `backend/src/researchx/adapters/secrets*/**`
+- **Removal**: deactivate after P2 ships
+
 ### ci-lead-developer
 - **Domain**: coordination
 - **Active**: true
 - **Phase-specific**: false
 - **Frameworks**: ciagent workflows, git discipline
-- **Constraints**: enforce persona territories; ApiClient boundary review; commit discipline with ---ci--- blocks; phase-boundary file updates only (no .ciagent/ writes during task execution)
-- **Territory**: `.ciagent/**`, repo root config files
-
-### Deactivated (v0.1)
-
-#### backend-engineer
-- **Domain**: backend
-- **Active**: false
-- **Reason**: No backend in the prototype milestone; the FastAPI backend is milestone v0.2 (blocked until prototype approval)
-- **Frameworks**: fastapi, pydantic, uv (activates in v0.2)
-- **Territory**: `backend/**` (does not exist yet)
-
-#### data-engineer
-- **Domain**: data
-- **Active**: false
-- **Reason**: No database/schema work in v0.1; evidence store and citation ledger models arrive in v0.2; prototype uses typed fixtures
-- **Frameworks**: pydantic schemas (activates in v0.2)
-- **Territory**: `backend/src/researchx/evidence/**` (does not exist yet)
-
-### Custom personas
-None required for v0.1. The security-auditor persona activates in v0.2 phase 2 (trust loop: secrets handling, liveness verification). No CLI surface exists in this milestone, so no cli-engineer.
+- **Constraints**: enforce persona territories; adapter/engine boundary review (I/O only in adapters); commit discipline with ---ci--- blocks; phase-boundary file updates only (no .ciagent/ writes during task execution); gates green before every ship
+- **Territory**: `.ciagent/**`, repo root config files (README, VERSIONING, .gitignore)

.ciagent/PLAN.md

@@ -1,48 +1,44 @@
-# PLAN — Milestone v0.1 Phase 7: Ask Screen Intelligence — Suggestions + Refine
+# PLAN — Milestone v0.2 Phase 5 (FINAL): Review + Audit + Ship
 
 ---
-phase: 7
-milestone: v0.1
-status: planned
+phase: 5
+milestone: v0.2
+status: executed
 must_haves:
-  - "Follow-up query suggestions on the New Research view, derived from unanswered questions (open task-inbox items joined with source reports); click fills the question box — editable, never auto-starts (REQ-67)"
-  - "Refine option: opt-in back-and-forth dialogue in an inline drawer (scripted clarifying questions → answers → composed refined question + suggested context); accept fills the form, or keep original (REQ-68)"
-  - "Both features opt-in — zero required clicks added to the ≤3-click happy path (pinned by test)"
-  - "All new data access extends the ApiClient boundary + MockApiClient fixtures (REQ-53/54 discipline)"
+  - "Multi-persona full-milestone review: 4 P0 + 15 P1 + 15 P2 found; all 4 P0s fixed in-phase with attack-proofs (A1 tautological anchoring → real writer-quote extraction; C2 gate denominator → cited-URL scoped; C1 zombie runs → shape-validated plans + catch-all FAILED persist; S1 fetch SSRF → per-hop re-guarding); 6 cheap P1s fixed (approve-with-plan, FAILED status, length caps, probe wiring, README env-var + adapter honesty)"
+  - "Audit: PASS-WITH-NOTES — reconstruction PASS (all REQ-01..34 covered across v0.2.0–v0.2.4), secrets clean (zero key values in history), branch hygiene exact; critical notes fixed in-phase (REQUIREMENTS traceability un-staled, P5 PLAN written, ROADMAP P5 status, security-engineer persona deactivated per its removal note)"
+  - "Milestone ship: v0.2.5 tagged as the MVP release candidate — the pipeline then HALTS at the merge_to_main owner approval gate (D-018)"
+  - "G-009 escalation presented at the gate: the owner ratifies that live mode covers the core research loop only (G-002); remaining prototype surfaces stay mock-backed to v0.3+"
 personas:
-  - frontend-engineer
   - ci-lead-developer
-requirements: [REQ-67, REQ-68]
+requirements: [REQ-01, REQ-02, REQ-03, REQ-04, REQ-05, REQ-06, REQ-07, REQ-08, REQ-09, REQ-10, REQ-11, REQ-12, REQ-13, REQ-14, REQ-15, REQ-16, REQ-17, REQ-18, REQ-19, REQ-20, REQ-21, REQ-22, REQ-23, REQ-24, REQ-25, REQ-26, REQ-31, REQ-32, REQ-33, REQ-34]
 ---
 
 ## User-Facing Surface
 
-1. **Ask suggestions** (`/ask`, below the primary form): "Pick up an open question" — cards for each open task-inbox item (question text + source report title + "from your research" attribution). Click fills the question textarea (editable, no auto-submit, focus moves to the box). Honest empty state: "No open questions yet — they collect here as you run research."
-2. **Refine drawer** (`/ask`, inline): "Refine question" button (disabled until a draft exists) opens the established dials-drawer pattern — one clarifying question at a time with answer input, progress indicator (1/2/3), then the composed refined question + suggested context preview. **Use this** fills question + context and closes; **Keep original** dismisses; **Restart** re-runs the exchange. Escape closes. Honest caption: "Scripted refinement in the prototype — model-driven refine lands in v0.2."
+The MVP release candidate: the approved v0.1 prototype frontend (Ask → Choose → Plan & Run → Reading Room, all 8 cards, shell, library, settings) now backed by a real FastAPI research engine in live mode — methodology registry (Rapid Answer + Deep Report), 12-dial framework, asyncio state machine with durable pause/cancel/resume, visited-only evidence store, attack-proven trust loop (quote anchoring, SSRF-guarded liveness, citation ledger, ≥99% export gate with zero-unanchored requirement), SSE live trace, adversarial suite (14 attacks), E2E happy path on the real stack. Releases v0.2.0–v0.2.5.
 
-## Happy Path
+## Happy Path (owner review script)
 
-1. `cd frontend && pnpm install && pnpm dev` → http://localhost:3000/ask (shell present)
-2. Default path unchanged: question → Research this (click 1) → Choose → Start research (click 2) → Approve plan (click 3)
-3. Suggestions: scroll to "Pick up an open question" → click a card → question box fills with the open question → edit if desired → Research this as usual
-4. Refine: type a draft → "Refine question" → answer the 3 clarifying questions → review the composed question + suggested context → "Use this" → both boxes filled → Research this
-5. Keep-original: open the drawer, answer partway, Escape → the original draft is untouched
+1. `cd backend && uv sync && uv run pytest` — 129 tests green, zero API keys (live tier: `uv run pytest -m live`, skips cleanly)
+2. `cd frontend && corepack pnpm install && corepack pnpm test` — 97 tests green (90 component + 5 live-binding + 2 real-stack E2E)
+3. `uv run uvicorn researchx.api.app:app --port 8000` + `NEXT_PUBLIC_RESEARCHX_API_MODE=live corepack pnpm dev` → http://localhost:3000 → Ask a question → Research this → pick Deep Report → Start research → approve the plan (3 clicks) → live SSE trace → report with anchored citations → ledger → export Markdown (citation links) / JSON (backend-schema round-trip)
+4. `uv run python -m researchx.engine.demo` — full pipeline on fakes, artifacts in a temp runs dir
+5. Owner decision: approve → milestone merge to main + v0.2.5 published as the MVP release; or direct changes → binding fix cycle
 
 ## UX Acceptance Criteria
 
-- ≤3-click default happy path still green (both features opt-in; zero required interactions)
-- Suggestions never compete with the primary action (below the form, not modal, no auto-start)
-- Refine drawer: draft visible behind, Escape-safe, honest scripted-prototype caption
-- Keyboard accessible; focus ring in accent (global standard)
-- All data via `api.*` — components never import MockApiClient; v0.2 OpenAPI swap unaffected
+- ≤3 clicks from cold start to initiated research, validated on the real stack (REQ-17)
+- Every trust claim attack-proven: hallucinated citations fail the export gate; fabricated quotes on real passage IDs flag unanchored; SSRF redirects die; pause/resume/cancel survive the loop
+- Honest scope: live mode = core research loop (G-002); library/settings/suggestions/refine stay mock-backed until v0.3+ — ratified at this gate (G-009)
+- No secret value in any artifact, trace, or log; zero-key test discipline throughout
 
-## Waves
+## What this phase did
 
-1. **T-7.1 Boundary**: types (`SuggestedQuery`, `RefinementQuestion`, `RefinedQuestion`) → ApiClient gains `getSuggestedQueries` (mock: open `taskInboxFixture` items joined with `reportLibraryFixture`; v0.2: GET /api/suggestions), `getRefinementQuestions(draft)` (mock: scripted 3-question set; v0.2: POST /api/refine step 1), `composeRefinedQuestion(draft, answers)` (mock: deterministic composer; v0.2: model-driven) → co-located boundary tests
-2. **T-7.2 Suggestions UI**: `AskSuggestions` component on /ask; click-fills-box contract; empty state; tests
-3. **T-7.3 Refine drawer**: `RefineQuestionButton` + drawer component; exchange state machine; use/keep/restart; tests
-4. **T-7.4 Regression + polish**: 3-click re-pin, README, typography pass, gates green
+1. **Review** (multi-persona, probe-verified): 4 P0 + 15 P1 + 15 P2. The 4 P0s broke the milestone's flagship guarantees and were all fixed with attack-proofs: quote anchoring extracted the stored passage's own quote (always 1.0) instead of the writer's text; the export-gate denominator counted unprobed visited pages as dead; malformed planner JSON left zombie runs; fetch adapters followed redirects without re-guarding. Six cheap P1s also fixed.
+2. **Audit**: PASS-WITH-NOTES — reconstruction, secrets sweep (clean), branch/tag hygiene exact; both critical notes (stale traceability rows, missing P5 plan) fixed in-phase.
+3. **Ship (this commit sequence)**: PR #14 (phase/05 → milestone), squash-merge, tag v0.2.5 — the MVP release candidate, release with the full milestone summary. Per D-018 and the merge_to_main escalation hook, the milestone merge to main does NOT proceed autonomously — the pipeline halts for the recorded owner decision, with G-009 (live-mode scope) presented at the same gate.
 
 ## Scope Guard
 
-P8 (final review + approval re-presentation) follows P7 ship + UAT deploy. Milestone merge to main remains gated on the owner's recorded approval (REQ-62, prototype_approval escalation hook). No backend work, no v0.2 scope, no model calls (scripted refine only — the model-driven version is v0.2).
+Milestone merge to main, v0.2.5 publication, and any deploy wait on the owner approval gate (D-018/G-009). The pipeline does not proceed autonomously past this commit.

.ciagent/PROJECT.md

@@ -51,5 +51,13 @@ Vision finalized and locked 2026-09-26: v1 methodology composition LOCKED (8 cor
 - Model adapter default: Ollama cloud-first (ollama.com/v1) with keyless localhost:11434/v1 fallback on auth/connection failure
 - Prototype-first gate (owner): UI/UX prototype with mock data, approved before MVP work; prototype is its own milestone (v0.1)
 - Versioning (owner): starts at v0.1; MAJOR locked at 0 until owner-approved v1 release; MVP may span multiple 0.x minor milestones
-- Prototype = production Next.js frontend with typed ApiClient/MockApiClient split — zero throwaway work; phase 4 of v0.2 swaps the mock for the OpenAPI client
-- Tag-line mapping: 0.x milestones run patches on their own minor line (v0.1.x); supersedes the greenfield deviation noted at init
+- Prototype = production Next.js frontend with typed ApiClient/MockApiClient split — zero throwaway work; phase 3 of v0.2 swaps the mock for the OpenAPI client
+- Tag-line mapping: 0.x milestones run patches on their own minor line (v0.1.x); supersedes the greenfield deviation noted at init
+
+## Key Decisions (v0.2 clarify — D-007..D-020, 2026-09-27)
+- Backend layout: `backend/` repo-root package, src-layout `researchx` (config, methodologies, adapters, engine, evidence, trust, api per ARCHITECTURE §Components); uv + uv-managed Python 3.12 (D-007/D-008)
+- Ports/binding: backend 127.0.0.1:8000, frontend :3000 via NEXT_PUBLIC_API_BASE_URL; CORS localhost:3000 (D-009); run IDs = 8-char slugs; storage = <dir>/runs/<id>/ (D-010)
+- Adapters: Ollama base URLs + key via env-file secrets scopes (OLLAMA_BASE_URL, OLLAMA_API_KEY); DDG keyless fallback = html.duckduckgo.com/html conservative scrape (D-011/D-012)
+- Integration: openapi-typescript + openapi-fetch → frontend/src/lib/api/generated, bound behind ApiClient; RESEARCHX_API_MODE=mock|live, mock default (D-013/D-020)
+- Transport/trust: sse-starlette SSE + pydantic typed event bus (D-014); difflib quote anchoring ≥ 0.85 (D-015); HTTP liveness live/stale/dead (D-016); JSON durable state, atomic rewrite per transition (D-017)
+- Run termination: pipeline ships P1..P4 + P5 final patch, then HALTS at the owner approval gate before milestone → main (merge_to_main hook, v0.1 precedent); no deploys without owner directive (D-018/D-019)

.ciagent/REQUIREMENTS.md

@@ -17,7 +17,7 @@
 ### Vision Validation & Gate
 - **REQ-60**: v2 surface mockups: project graph and task inbox panels rendered from mock data
 - **REQ-61**: ≤3-click happy path on defaults (Ask → Choose → Run); typography care pass per vision §4
-- **REQ-62**: Owner approval gate: prototype ships only after recorded owner approval (prototype_approval escalation hook); MVP milestone v0.2 begins only after v0.1.4 is tagged
+- **REQ-62**: Owner approval gate: prototype ships only after recorded owner approval (prototype_approval escalation hook); MVP milestone v0.2 begins only after v0.1.4 is tagged — **APPROVED 2026-09-27: owner approval recorded on v0.1.8 (extended prototype); v0.2 unblocked**
 
 ### App Shell Extension (P5 — owner gate feedback, directed 2026-09-27)
 - **REQ-63**: Persistent app shell on all screens: sidebar (primary nav + future-option slots) and top bar (search/command-palette slot + avatar button); shell adds zero required clicks to the ≤3-click happy path
@@ -73,6 +73,13 @@
 - **REQ-33**: Monorepo: uv-managed backend (ruff, mypy, pytest) + Next.js frontend (ESLint, strict TS, Vitest); one-command install/dev
 - **REQ-34**: Full export round-trip: report + ledger + citations survive as real links
 
+### Clarified constraints (v0.2 P0 clarify — D-007..D-020)
+- **D-007/D-008**: backend/ src-layout package `researchx` (config, methodologies, adapters, engine, evidence, trust, api); uv + managed Python 3.12
+- **D-009/D-010**: backend 127.0.0.1:8000, CORS localhost:3000; run IDs 8-char slugs; runs/<id>/ storage layout
+- **D-011/D-012**: model/search endpoints + keys resolve from env-file secrets scopes; DDG keyless fallback via html.duckduckgo.com/html scrape
+- **D-013/D-020**: openapi-typescript + openapi-fetch generated client bound behind ApiClient; RESEARCHX_API_MODE=mock|live, mock default until P3
+- **D-014..D-017**: sse-starlette SSE + pydantic event bus; difflib quote anchoring ≥ 0.85; HTTP liveness live/stale/dead; JSON durable state atomically rewritten per transition
+
 ## V2 (Post-MVP backlog)
 
 ### Methodology Catalog Extension
@@ -119,12 +126,12 @@
 | REQ-57 (Plan & Run) | v0.1 | P2 | complete |
 | REQ-58, REQ-59 (Reading Room, exports) | v0.1 | P2 | complete |
 | REQ-60, REQ-61 (v2 mockups, 3-click) | v0.1 | P3 | complete |
-| REQ-62 (approval gate) | v0.1 | P8 | in_progress (awaiting owner decision on extended prototype) |
+| REQ-62 (approval gate) | v0.1 | P8 | complete (owner approval recorded 2026-09-27) |
 | REQ-63, REQ-64, REQ-65, REQ-66 (app shell, library, settings, avatar) | v0.1 | P5 | complete |
-| REQ-67, REQ-68 (ask suggestions, refine dialogue) | v0.1 | P7 | in_progress |
-| REQ-01..06, REQ-08..11, REQ-31 (framework, adapters) | v0.2 | P1 | blocked |
-| REQ-07, REQ-12, REQ-13..24 (probing, engine, trust) | v0.2 | P2 | blocked |
-| REQ-25, REQ-26, REQ-33 (API, client, tooling) | v0.2 | P3 | blocked |
-| REQ-17, REQ-32, REQ-34 (adversarial, E2E, round-trip) | v0.2 | P4 | blocked |
-| All REQ-01..34 (milestone gate) | v0.2 | P5 | blocked |
+| REQ-67, REQ-68 (ask suggestions, refine dialogue) | v0.1 | P7 | complete |
+| REQ-01..06, REQ-08..11, REQ-31 (framework, adapters) | v0.2 | P1 | complete (v0.2.1; REQ-07/12 contracts proven, live probing in P2) |
+| REQ-07, REQ-12, REQ-13..24 (probing, engine, trust) | v0.2 | P2 | complete (v0.2.2) |
+| REQ-25, REQ-26, REQ-33 (API, client, tooling) | v0.2 | P3 | complete (v0.2.3) |
+| REQ-17, REQ-32, REQ-34 (adversarial, E2E, round-trip) | v0.2 | P4 | complete (v0.2.4) |
+| All REQ-01..34 (milestone gate) | v0.2 | P5 | complete (v0.2.5 — **owner approval recorded 2026-09-27**, G-009 ratified; milestone merged to main) |
 | REQ-35..51 | v2 backlog (post-MVP milestones) | — | pending |

.ciagent/RESEARCH-v02.md

@@ -0,0 +1,140 @@
+# Research — v0.2 MVP (Phase 0)
+
+## Run: 2026-09-27 (stage: research)
+
+Phase-0 research findings for milestone v0.2 (MVP): FastAPI backend, custom asyncio engine, adapter layer, trust loop, OpenAPI client integration. Each topic records concrete recommendations and pitfalls that PLAN consumes.
+
+## 1. Backend foundation (uv + FastAPI)
+
+**Recommendation:**
+- uv (>= 0.4) with `backend/pyproject.toml`, src-layout: `backend/src/researchx/__init__.py`, `backend/src/researchx/{config,methodologies,adapters,engine,evidence,trust,api}/__init__.py`
+- `[project] name = "researchx"`, `requires-python = ">=3.12"`; deps: `fastapi>=0.115,<0.116`, `pydantic>=2.8,<3`, `uvicorn>=0.30,<1`, `sse-starlette>=2.1,<3`, `httpx>=0.27,<1`
+- Dev group (`uv sync --group dev` or `[dependency-groups]`): `ruff>=0.6`, `mypy>=1.11`, `pytest>=8`, `pytest-asyncio>=0.23`
+- `[build-system] hatchling`; `[tool.hatch.build.targets.wheel] packages = ["src/researchx"]` — src-layout pitfall: without the explicit packages key, uv/hatch builds fail or ship an empty wheel
+- Dev run: `cd backend && uv run uvicorn researchx.api.app:app --reload --port 8000`; one-command from root documented in README
+- mypy strict on `src/`: `[tool.mypy] strict = true, mypy_path = "src"`; ruff: line-length 100, target py312
+
+**Pitfalls:**
+- `uv run` resolves the project venv automatically — never `pip install` into it
+- pytest needs `pythonpath = ["src"]` in `[tool.pytest.ini_options]` or an editable install (`uv sync` does this) — tests import `researchx.*` directly
+- pytest-asyncio: use `asyncio_mode = "auto"` and `loop_scope = "function"` (the old `event_loop` fixture is removed in recent versions)
+
+## 2. Ollama OpenAI-compatible endpoints
+
+**Recommendation:**
+- Cloud: `https://ollama.com/v1` with `Authorization: Bearer <OLLAMA_API_KEY>`; local fallback `http://localhost:11434/v1` keyless
+- Chat: POST `/chat/completions` (OpenAI shape: messages, model, temperature; response choices[0].message.content)
+- Probe: GET `/models` → data[].id; capability check via a tiny structured-completion smoke test at connect time
+- Context cap: `min(model_claim, 8192)` tokens; model claim unknown → 8192 flat; embedding batch 8
+- Planner/writer roles = two model names from settings (default: same model both roles)
+
+**Pitfalls:**
+- ollama.com/v1 is cloud-keyed — 401 on missing/invalid key → automatic local-fallback attempt, then surfaced error
+- Some served models don't support function calling/structured outputs → REQ-12 warning path: detect via smoke-test failure, warn in UI, degrade to plain chat + prompt-embedded JSON contract
+- Model names are server-specific (`q4` suffixes etc.) — settings must store the exact served name; probe lists what's actually available
+
+## 3. Search adapters
+
+**Recommendation:**
+- Tavily: POST `https://api.tavily.com/search`, JSON `{"api_key": key, "query": q, "search_depth": "basic"|"advanced", "max_results": n, "include_answer": false}` → `results[]: {title, url, content, score}`; timeouts 10s
+- DuckDuckGo keyless fallback: POST `https://html.duckduckgo.com/html/?q=<urlencoded>` with a plain httpx client; parse anchors `a.result__a` (href → URL, text → title) and `a.result__snippet` from the result list; conservative: max 8 results, no retries beyond one backoff, user-agent string honest
+- Adapter interface: `async search(query, max_results) -> list[SearchResult]`; registry selects Tavily when TAVILY_API_KEY present, else DDG
+
+**Pitfalls:**
+- DDG html rate-limits aggressively — the fallback is best-effort; on 403/timeout return partial/empty with a surfaced warning, never hang the engine
+- Tavily's `content` is already a snippet — evidence extraction still fetches the live page (visited-only constraint requires the visit)
+- Never put the API key in a query string or log line
+
+## 4. FastAPI SSE + asyncio durability
+
+**Recommendation:**
+- `sse-starlette` EventSourceResponse fed by a per-run `asyncio.Queue`; pydantic event models with a discriminated union on `type` (run_started, query_fired, source_visited, passage_extracted, state_changed, run_done, run_error)
+- EventSourceResponse generator: `async for event in queue` → `{"event": <type>, "data": <model_dump_json>}`; send on connect a `state_changed` replay of current persisted state
+- Client disconnect: wrap the generator in try/finally that cancels only the SSE subscription (never the run); runs keep going when browsers disconnect
+- Backpressure: unbounded queue per run is acceptable single-user; cap at 1000 with drop-oldest `state_changed` coalescing if needed
+
+**Pitfalls:**
+- No blocking I/O in the response generator — all fetches via httpx.AsyncClient
+- uvicorn single worker; multiple workers would break in-memory run registry — document single-user explicitly
+- On reconnect (Last-Event-ID unused in MVP) → replay current state + live events onward; full event log persisted in the run dir anyway
+
+## 5. Durable state machine patterns
+
+**Recommendation:**
+- `runs/<id>/state.json`: `{run_id, state, dial_values, plan, question, created_at, updated_at, cursor}` — rewritten atomically after every transition: write `.tmp`, `os.replace`
+- Transitions only at method boundaries of the state machine; the cursor records depth-loop position for resume
+- Pause = asyncio.Event cleared; cancel = task.cancel() + terminal CANCELLED state persisted; resume on restart = state file read, EventBus rebuilt, loop re-entered at cursor
+- pytest-asyncio: `asyncio_mode = "auto"`; tests construct the engine with fake adapters and `await engine.run()` directly
+
+**Pitfalls:**
+- Never swallow CancelledError — re-raise after persisting the cancel state
+- Shield the state write: `with contextlib.suppress(asyncio.CancelledError): await asyncio.shield(save())` then re-raise
+- Torn reads: only ever `os.replace` (atomic on same filesystem); never append — state is a snapshot, trace is a separate append-only file
+
+## 5b. Testing fakes (REQ-31)
+
+**Recommendation:**
+- FakeModelAdapter: canned planner (sub-questions from a fixture), canned writer (deterministic report citing fixture passage IDs) — zero API keys
+- FakeSearchAdapter: fixture corpus of 5-8 pages with overlapping passages; deterministic ordering
+- Engine tests drive every transition, depth loop, pause/resume mid-depth-loop, cancel, and adversarial writer outputs
+
+**Pitfalls:**
+- Fakes must implement the full adapter interface (no stub methods) — verify layer asserts interface conformance
+- Keep fixtures small and unicode-diverse (quote anchoring edge cases)
+
+## 6. §6. Quote anchoring + liveness
+
+**Recommendation:**
+- Normalize (unicode NFC → casefold → whitespace collapse) both quote and passage; exact-substring short-circuit; else difflib SequenceMatcher ratio ≥ 0.85
+- Ledger entry: `{url, visited_at, passages: [{id, quote}], claims: [claim_ids], health, authority_tier}`
+- Liveness: single GET with redirect-follow (httpx, 10s timeout): 2xx live; 3xx loop/parked-domain or content-gone markers → stale; 4xx/5xx/timeout/unresolvable → dead
+- ≥99% liveness gate: shipped report citations must pass liveness at export time; failures listed in the verification checklist
+
+**Pitlingfalls:**
+- SequenceMatcher on long passages is O(n²)-ish — anchor per-passage (passages are ≤ ~500 chars), not per-document
+- Fuzzy matches near threshold (0.80-0.90) flagged in the ledger as `weak_match` for transparency
+
+**Pitfalls:** (corrected)
+- SequenceMatcher cost is quadratic-ish — always match quote vs its claimed passage only
+- Near-threshold (0.80–0.90) matches flagged `weak_match` in the ledger — surfaced, not silently accepted
+
+## 7. OpenAPI client generation
+
+**Recommendation:**
+- `openapi-typescript@^7` (types) + `openapi-fetch@^0.13` (typed fetch client), generated into `frontend/src/lib/api/generated/`
+- Regen: `pnpm dlx openapi-typescript http://127.0.0.1:8000/openapi.json -o frontend/src/lib/api/generated/schema.d.ts` — needs the backend running, or read a committed `openapi.json` snapshot in CI
+- Binding: a thin `GeneratedApiClient` implements the existing ApiClient interface by delegating to openapi-fetch with baseURL from NEXT_PUBLIC_API_BASE_URL; components never import it directly — only the boundary file does
+- RESEARCHX_API_MODE=mock|live env flag selects the binding at boundary initialization; mock stays default
+
+**Pitfalls:**
+- FastAPI operation-id stability: route order and function names determine ids — fix function names early; regen discipline = regenerate only from a committed snapshot
+- FastAPI's default unions (None | X) — openapi-typescript emits optional/nullable types that must be handled at the boundary, not in components
+
+## 8. Monorepo ergonomics
+
+**Recommendation:**
+- Root README one-command story: `uv sync` (backend) + `corepack pnpm install` (frontend); dev: `uv run uvicorn ...` + `corepack pnpm dev`
+- Backend gates: `uv run ruff check src tests`, `uv run mypy src`, `uv run pytest` (all via `uv run` from backend/)
+- Frontend gates carry over from v0.1 unchanged: `pnpm typecheck`, `pnpm lint`, `pnpm test`, `pnpm build`
+- Repo-root package.json is NOT created (frontend is the only JS package); document commands in README instead
+
+**Pitfalls:**
+- pnpm via corepack (packageManager field pins pnpm@12.6.0) — direct pnpm may be absent; always `corepack pnpm`
+- openapi.json snapshot committed for reproducible client regen; regenerate the TS client when the snapshot changes
+
+## Research Conclusions
+
+1. Backend = uv + src-layout `researchx` in backend/, pyproject with hatchling `packages=["src/researchx"]`, deps fastapi/pydantic/uvicorn/sse-starlette/httpx, dev ruff/mypy/pytest/pytest-asyncio — one-command via `uv sync && uv run uvicorn researchx.api.app:app`.
+2. All I/O lives in adapters; engine imports no vendor SDKs (httpx only inside adapters).
+3. Ollama cloud `https://ollama.com/v1` (Bearer) → local `http://localhost:11434/v1` keyless fallback on 401/connection failure; probe via GET /models + structured-output smoke test; context cap min(claim, 8192), embed batch 8.
+4. REQ-12 structured-output warning: detect via smoke test; degrade to prompt-embedded JSON contract + UI warning — never fail cryptically.
+5. Tavily POST api.tavily.com/search with api_key in JSON body; DDG fallback scrapes html.duckduckgo.com/html anchors conservatively (max 8, one backoff, surfaced warnings on rate-limit).
+6. SSE = sse-starlette EventSourceResponse + per-run asyncio.Queue + pydantic discriminated-union event types; state replay on connect; single uvicorn worker (single-user).
+7. Durable state = runs/<id>/state.json, atomic tmp+os.replace per transition, cursor for depth-loop resume; trace is a separate append-only file; shielded state writes; never swallow CancelledError.
+8. Quote anchoring = normalize + exact-substring short-circuit + SequenceMatcher ≥ 0.85 per-passage; near-threshold flagged weak_match.
+9. Liveness = redirect-following GET, 10s: 2xx live / redirect-loop or content-gone stale / 4xx-5xx-timeout dead; ≥99% citation liveness gate at export.
+10. Fake adapters (REQ-31) implement the full adapter interface with canned planner/writer + fixture corpus — enables the entire engine + trust test suite with zero keys.
+11. Client gen = openapi-typescript@^7 + openapi-fetch@^0.13 from a committed openapi.json snapshot; GeneratedApiClient binds behind the ApiClient interface; RESEARCHX_API_MODE=mock|live selects binding; mock default.
+12. Monorepo gates: backend `uv run ruff check`, `uv run mypy`, `uv run pytest`; frontend v0.1 gates unchanged; no root package.json — commands documented in README.
+13. Config/status endpoints surface probe results + adapter status (REQ-25 GET /api/config) — plan the schema early so the settings surface stays honest.
+14. All decisions D-007..D-020 confirmed workable; refinements: hatchling packages key (new), openapi.json snapshot discipline (new), single-worker uvicorn note (new), structured-output smoke-test detection pattern (new) — folded into PLAN as constraints.

.ciagent/ROADMAP.md

@@ -54,51 +54,80 @@ Two milestones, owner-directed 2026-09-27. **Milestone v0.1 — Prototype**: the
 - **Depends on**: 5
 - **Status**: shipped (PR #6 squash-merged, tag v0.1.6 + release created; review PASS-WITH-FIXES — deep-link P0 + 5 P1s fixed; audit PASS; owner directed UAT deploy then returned 2nd gate feedback → binding extension cycle P7/P8; milestone merge to main stays halted)
 
-### Phase 7 — Ask Screen Intelligence: Suggestions + Refine (2nd owner gate feedback)
+### Phase 7 — Ask Screen Intelligence: Suggestions + Refine (complete — shipped v0.1.7)
 - **Description**: New Research view gains follow-up query suggestions derived from unanswered questions (open task-inbox items joined with their source reports); one click fills the question box — editable, never auto-starts. An opt-in Refine dialogue (inline drawer, one clarifying question at a time, scripted in the prototype) composes a refined question + suggested context; accept fills the form, or keep the original. Both are opt-in affordances — zero required clicks added to the ≤3-click happy path. All data through the ApiClient boundary.
 - **Requirements covered**: REQ-67, REQ-68
 - **Success criteria**: suggestions render from open inbox items with source attribution; click fills the box (no auto-submit); refine drawer completes a scripted exchange and composes a refined question; both flows keyboard-accessible; 3-click path pinned green; gates green
 - **Depends on**: 6
-- **Status**: in_progress
+- **Status**: complete (PR #7 squash-merged to milestone/v0.1-prototype, tag v0.1.7, release created; verify PASS — 2 P1 fixes with regression tests: Enter-guard defense in depth, focus return to trigger)
 
-### Phase 8 — Final Review + Approval Re-presentation + Ship (FINAL)
+### Phase 8 — Final Review + Approval Re-presentation + Ship (FINAL — complete)
 - **Description**: Multi-persona review of the full milestone diff (now including P7), audit, then re-present the extended prototype at the REQ-62 owner approval gate. On recorded approval: milestone merge to main, tag v0.1.8 — the milestone release. (v0.2 P1 branches only after this tag.)
 - **Requirements covered**: REQ-62 (gate) + milestone approval of REQ-52..68
 - **Success criteria**: review PASS (P0s fixed in-phase); audit PASS; v0.1.8 tagged + release; UAT staged per owner directive; pipeline halts at the approval gate
 - **Depends on**: 7
-- **Status**: planned
+- **Status**: complete (PR #8 squash-merged, tag v0.1.8 + release; review PASS-WITH-FIXES, audit PASS-WITH-NOTES; **owner approval RECORDED 2026-09-27** — decision commit 3fd0e10; milestone merged to main; v0.2 unblocked)
 
-## Milestone v0.2 — MVP (feature) — BLOCKED until prototype approval
+## Milestone v0.1 — COMPLETE (approved 2026-09-27)
 
-Phases renumbered from the original v1.0 plan (1-based within the milestone):
+All requirements complete: REQ-52..62, REQ-63..68. The approved
+prototype release is **v0.1.8** (final phase patch). Milestone branch
+merged to main and deleted — tags v0.1.0–v0.1.8 preserve the full
+history. Next milestone: v0.2 MVP (unblocked).
+
+## Milestone v0.2 — MVP (feature) — COMPLETE (approved 2026-09-27)
+
+Phases renumbered from the original v1.0 plan (1-based within the milestone). Tags run on the v0.2.x line; MAJOR stays 0.
 
 ### Phase 0 — Pre-Execution (v0.2)
-- **Description**: Milestone pre-execution re-run: PLAN.md refresh against approved prototype decisions (layout learnings, API shape implied by the ApiClient interface), research on any gaps surfaced by approval feedback.
-- **Status**: blocked (gate: v0.1.4)
+- **Description**: Milestone pre-execution: SPECIFY (spec validated for v0.2), CLARIFY (D-007..D-020: backend layout, uv+Python 3.12, ports/run-IDs, DDG fallback, openapi-typescript client, SSE+pydantic events, difflib anchoring, liveness rules, durable JSON state, owner-gate halt, no-deploy policy, RESEARCHX_API_MODE), RESEARCH (RESEARCH-v02.md — 8 topics, 14 conclusions, 4 D-refinements), PLAN (P1 vertical-slice plan), GRILL (mechanical nine-axis review), MVP/UX check.
+- **Requirements covered**: none (planning artifacts)
+- **Success criteria**: .ciagent/ files refreshed for v0.2; PLAN.md carries User-Facing Surface + Happy Path + UX Acceptance Criteria; PERSONAS.md v0.2 roster active; grill verdict recorded with binding decisions
+- **Depends on**: v0.1 approval (recorded)
+- **Status**: complete (PR #9 squash-merged to milestone/v0.2-mvp bbf80ce, tag v0.2.0, release created HTTP 201, phase branch deleted; grill Proceed 0.72 with G-001..G-010 promoted; MVP/UX PASS)
 
 ### Phase 1 — Methodology Framework + Adapter Layer
-- **Description**: Dial schema (12 dials, typed, safe defaults), methodology registry with Rapid Answer + Deep Report, adapter contracts (model/search/storage/memory/secrets) with local implementations, capability probing with conservative caps (8192 context, embedding batch 8, Ollama cloud-first + local fallback), fake model/search adapters.
-- **Requirements covered**: REQ-01..06, REQ-08..11, REQ-31
-- **Status**: blocked
+- **Description**: Dial schema (12 dials, typed, safe defaults), methodology registry with Rapid Answer + Deep Report, adapter contracts (model/search/storage/memory/secrets) with local implementations, capability probing with conservative caps (8192 context, embedding batch 8, Ollama cloud-first + local fallback), fake model/search adapters. Full task waves in PLAN.md.
+- **Requirements covered**: REQ-01..06, REQ-08..11, REQ-31 (REQ-07, REQ-12 ship in P2 per ROADMAP phase mapping — dial-level + warning contracts are proven here, live probing against real endpoints in P2)
+- **Success criteria**: uv one-command backend; gates green zero-API-key; registry resolves slugs; dial snapshot round-trips; fakes drive full interface; degradation typed + honest
+- **Depends on**: 0
+- **Status**: complete (PR #10 squash-merged to milestone/v0.2-mvp dfb738d, tag v0.2.1, release HTTP 201, phase branch deleted; verify PASS 0 P0 / 2 P1 fixed in-phase / 9 P2 flagged; REQ-07/12 contracts proven with fakes per G-001, live probing in P2)
 
-### Phase 2 — Research Engine + Trust Loop
+### Phase 2 — Research Engine + Trust Loop (complete — shipped v0.2.2)
 - **Description**: Asyncio state machine with durable JSON state and pause/cancel/resume; plan approval gate; typed event bus → SSE; evidence store with stable passage IDs; trust loop (visited-only constraint, URL liveness pass, quote anchoring, citation ledger, verification checklist, confidence labels).
 - **Requirements covered**: REQ-07, REQ-12, REQ-13..24
-- **Status**: blocked
+- **Status**: complete (PR #11 squash-merged 558f21a, tag v0.2.2, release HTTP 201, phase branch deleted; verify found 2 P0 + 9 P1, all fixed in-phase with regression pins; SSE transport itself lands in P3 — the bus + trace artifacts shipped here)
 
-### Phase 3 — API Layer + Integration
+### Phase 3 — API Layer + Integration (complete — shipped v0.2.3)
 - **Description**: FastAPI routes (runs, methodologies, lifecycle, SSE events, config status); OpenAPI-generated typed client; **swap MockApiClient → generated client** (the ApiClient interface absorbs any prototype-era API drift); ETA/cost heuristics for methodology cards.
 - **Requirements covered**: REQ-25, REQ-26
-- **Status**: blocked
+- **Status**: complete (PR #12 squash-merged 75479a9, tag v0.2.3, release HTTP 201, phase branch deleted; verify found 1 P0 mode-flag + 4 P1, all fixed in-phase; REQ-33 one-command story completed here per plan)
 
-### Phase 4 — Hardening + Adversarial Suite + E2E
-- **Description**: Adversarial test suite (hallucinated-URL writer, quote-anchor mismatch, pause/resume mid-depth-loop), E2E happy-path (Playwright), monorepo tooling polish (one-command install/dev, lint/typecheck/test green).
+### Phase 4 — Hardening + Adversarial Suite + E2E (complete — shipped v0.2.4)
+- **Description**: Adversarial test suite (hallucinated-URL writer, quote-anchor mismatch, pause/resume mid-depth-loop), E2E happy-path (real stack via live binding + dev bridge), monorepo tooling polish (one-command install/dev, lint/typecheck/test green).
 - **Requirements covered**: REQ-17, REQ-32, REQ-33, REQ-34
-- **Status**: blocked
+- **Status**: complete (PR #13 squash-merged dcf2475, tag v0.2.4, release HTTP 201, phase branch deleted; verify found 5 P1 honesty gaps in the suite itself — export gate anchored, weak band pinned, fabricated reports fail export; E2E validated on the real stack, defaults only)
 
 ### Phase 5 — Final Review + Ship (FINAL)
 - **Description**: Review + audit + milestone ship; final patch tag IS the MVP release. MAJOR stays 0 — the MVP ships as a 0.x release. v1.0.0 comes only after an owner-approved release decision.
-- **Status**: blocked
+- **Status**: complete (PR #14 squash-merged 023667e, tag v0.2.5, release HTTP 201, phase branch deleted; review 4 P0 + 15 P1 — P0s attack-proven fixed; audit PASS-WITH-NOTES — criticals fixed; **owner approval RECORDED 2026-09-27** — decision commit 4721c2a, G-009 scope ratified; milestone merged to main, v0.2.5 = the MVP release)
+
+## Milestone v0.2 — COMPLETE (approved 2026-09-27)
+
+All requirements complete: REQ-01..26, REQ-31..34 (the MVP set). The
+approved MVP release is **v0.2.5** (final phase patch). Delivered: the
+FastAPI research engine (asyncio state machine, durable
+pause/cancel/resume), methodology framework (12 dials, Rapid Answer +
+Deep Report), five-adapter layer (Ollama cloud-first fallback,
+Tavily/DDG, storage, memory, secrets), the attack-proven trust loop
+(real quote anchoring, cited-scoped ≥99% liveness export gate, SSRF-
+guarded fetching, citation ledger, verification checklist), SSE live
+trace, OpenAPI-generated typed client behind the unchanged ApiClient
+boundary, a 14-attack adversarial suite, and the 3-click E2E on the
+real stack. G-009 ratified: live mode = core research loop only;
+library/settings/suggestions/refine/graph stay mock-backed until
+v0.3+. Milestone branch merged to main and deleted — tags
+v0.2.0–v0.2.5 preserve the full history. Next: v0.3 planning.
 
 ## Milestone Releases
 - **v0.1.4 = extended-prototype candidate** (superseded by the P5/P6 extension cycle)
@@ -106,7 +135,7 @@ Phases renumbered from the original v1.0 plan (1-based within the milestone):
 - **v0.1.6 = extended-prototype candidate** (superseded by the P7/P8 extension cycle)
 - **v0.1.7 = ask suggestions + refine dialogue** (P7 patch)
 - **v0.1.8 = milestone release** (P8 final phase patch — the approved extended prototype release, pending owner decision)
-- **v0.2.x = MVP release** (MAJOR still 0; ship only if all v0.2 phases complete)
+- **v0.2.5 = milestone release** (P5 final phase patch — the approved MVP; owner approval recorded 2026-09-27, G-009 ratified)
 - If MVP scope extends: additional 0.x minor milestones (v0.3, …), each a full milestone cycle
 - **v1.0.0**: owner-approved release only — not created by the pipeline autonomously
 

.ciagent/config.json

@@ -2,18 +2,23 @@
   "ci_version": "0.7.0",
   "projects": [],
   "active_project": "researchx",
-  "milestone": "v0.1",
-  "milestone_name": "prototype",
+  "milestone": "v0.3",
+  "milestone_name": "next-milestone-planning",
   "milestone_type": "feature",
   "versioning": {
     "major_locked": true,
-    "major_lock_note": "MAJOR remains 0 until an owner-approved v1 release; the MVP may span multiple 0.x minor milestones; all pre-v1 ships are MINOR/PATCH only",
-    "tag_line": "v0.1.x",
-    "next_milestone": "v0.2-mvp (blocked until prototype approval)"
+    "major_lock_note": "MAJOR remains 0 until an owner-approved v1 release; all pre-v1 ships are MINOR/PATCH only",
+    "tag_line": "v0.3.x",
+    "next_milestone": "v0.3 scope definition pending owner direction (post-MVP backlog: live-bound library/settings/suggestions/refine, backend hosting, remaining 6 methodologies)"
   },
   "autonomy": {
     "level": "full",
-    "escalation_hooks": ["deploy", "delete_data", "merge_to_main", "prototype_approval"],
+    "escalation_hooks": [
+      "deploy",
+      "delete_data",
+      "merge_to_main",
+      "prototype_approval"
+    ],
     "decision_confidence_threshold": 0.6,
     "max_revision_iterations": 3,
     "clarify_budget": 10
@@ -37,9 +42,16 @@
   "secrets": {
     "env_file": ".ciagent/.env.secrets",
     "scopes": {
-      "release": ["GITEA_TOKEN"],
-      "model": ["OLLAMA_API_KEY", "OLLAMA_BASE_URL"],
-      "search": ["TAVILY_API_KEY"]
+      "release": [
+        "GITEA_TOKEN"
+      ],
+      "model": [
+        "OLLAMA_API_KEY",
+        "OLLAMA_BASE_URL"
+      ],
+      "search": [
+        "TAVILY_API_KEY"
+      ]
     }
   }
-}
+}

.ciagent/release/DEPLOY-RECORD.md

@@ -1,13 +1,18 @@
-# Deploy Record — UAT stagings of the v0.1 prototype
+# Deploy Record — UAT stagings and releases
 
-Owner-directed UAT deployments, recorded per commit discipline. The
-approval gate (REQ-62) stays closed; UAT variants stage review builds
-without minting release tags.
+Owner-directed deployments, recorded per commit discipline. Release
+deploys carry the owner approval (v0.1.8); UAT variants stage review
+builds without minting release tags.
 
 | Date | Version | Commit | Directive | Result |
 |---|---|---|---|---|
 | 2026-09-27 | v0.1.4-uat | d15568f (P3 ship) | owner review staging (P4) | healthy — http://10.0.0.114:3000 |
 | 2026-09-27 | v0.1.6-uat | 600b49c (P6 ship) | owner: "push updates to lxc container" | healthy — http://10.0.0.114:3000 |
+| 2026-09-27 | v0.1.7-uat | 432d2c0 (P7 ship + boundary docs) | owner cadence: deploy after P7 and P8 | healthy — http://10.0.0.114:3000 |
+| 2026-09-27 | v0.1.8-uat | 93a7b57 (P8 ship — release candidate) | owner cadence: deploy after P7 and P8 | healthy — http://10.0.0.114:3000 |
+| 2026-09-27 | **v0.1.8 (release)** | 93a7b57 (tagged) | **owner approval recorded — milestone release published** | healthy — http://10.0.0.114:3000 |
+| 2026-09-27 | v0.2.5-uat | c28a97e (v0.2 milestone HEAD + v0.2.5 version strings) | owner: "deploy and validate against https://research.coreci.dev" | healthy — https://research.coreci.dev (HAProxy/SSL) |
+| 2026-09-27 | **v0.2.5 (release)** | b11b202 (main merge; tag v0.2.5) | **owner approval recorded (/ci-run APPROVED) — milestone release published; G-009 ratified** | serving — same container (v0.2.5-uat build = release content); no redeploy needed |
 
 ## v0.1.6-uat (extended prototype for owner review)
 
@@ -21,4 +26,25 @@ without minting release tags.
 - Rollback: `ssh root@10.0.0.114 'docker stop researchx; docker rename
   researchx-prev researchx; docker start researchx'`
 - The approval gate remains closed: milestone merge to main still halts
-  for the recorded owner decision (REQ-62)
+  for the recorded owner decision (REQ-62)
+
+## v0.2.5-uat (MVP release candidate, owner-directed)
+
+- Deployed via `bash .ciagent/release/deploy.sh v0.2.5-uat` — the v0.2
+  milestone HEAD (c28a97e: tag v0.2.5 + v0.2.5 About/package.json
+  version strings), per the owner's direct request to deploy and
+  validate against the public URL
+- Gates re-run at deploy time from the milestone HEAD: typecheck,
+  lint, test (97/97), build — green before sync
+- Image `researchx:v0.2.5-uat` + `latest` on the host; container
+  swapped, `researchx-prev` (v0.1.8) kept for rollback
+- Health: 2 checks; validated through the HAProxy SSL front:
+  https://research.coreci.dev — /ask /library /settings /choose all
+  200, root 307→/ask, TLS verified; served settings chunk carries
+  "v0.2.5 · MVP release candidate"; the RESEARCHX_API_MODE switch is
+  present in the served bundle (mock default — correct for a
+  frontend-only container; live mode additionally needs the backend
+  API on the host, which is v0.3+ deployment work)
+- The merge gate (D-018) remains closed: milestone → main still halts
+  for the recorded owner decision, with G-009 (live-mode scope)
+  presented at the same gate

.ciagent/release/UAT-v0.2.5.md

@@ -0,0 +1,87 @@
+# UAT Script — v0.2.5 (MVP release candidate)
+
+Deployment: https://research.coreci.dev (HAProxy → LXC container
+`researchx:v0.2.5-uat`, commit c28a97e, mock-backed frontend).
+
+Scope note (G-009): this container serves the v0.2.5 frontend with
+scripted mock data. The v0.2 engine (FastAPI, adapters, trust loop)
+is validated by the automated suites (129 backend + 97 frontend
+tests, 14 adversarial attacks, real-stack E2E) and runs via the
+README live-mode locally; hosting the backend is v0.3+ work. This
+UAT validates the release-candidate build of the product surface.
+
+## 1. Shell & navigation (REQ-63, REQ-66)
+
+1. Open https://research.coreci.dev → lands on **/ask** inside the app shell
+2. Sidebar: **New research / Library / Settings** nav present on every screen
+3. Top bar: press **⌘K** → navigation palette (screens + stored reports)
+4. Click the **avatar** (top right) → user menu: local profile, Settings, About
+5. Pass: shell persistent everywhere, honest preview-marked future slots
+
+## 2. Version check (this deploy)
+
+1. Sidebar → **Settings** → scroll to *About & version*
+2. Pass: reads **"v0.2.5 · MVP release candidate"** (confirms the deployed build)
+
+## 3. The ≤3-click happy path (REQ-61 / REQ-17 — core criterion)
+
+1. **/ask**: type a question → click **Research this** (click 1)
+2. **/choose**: pick a card (Deep Report is the recommended default) → **Start research** (click 2)
+3. **Plan & Run**: review the plan → **Approve plan** (click 3)
+4. Pass: exactly 3 clicks, defaults only, research running with a live trace
+
+## 4. Plan & Run (REQ-57)
+
+1. Plan approval UI shows sub-questions, source universe, outline
+2. Watch the live trace stream (scripted replay)
+3. Press **pause** → trace halts; **resume** → continues; **cancel** → terminal state
+4. Pass: all three controls behave; no lost events
+
+## 5. Reading Room + exports (REQ-58, REQ-59, REQ-34)
+
+1. Open the finished report from the run screen
+2. Hover/focus any **[n]** citation marker → the exact quoted passage appears
+3. Open the **citation ledger** panel: URL, quote, health, authority tier
+4. **Export Markdown** and **Export JSON** → real files download; citations survive as links
+5. Pass: quotes match exactly; files open; links intact
+
+## 6. Ask intelligence (REQ-67, REQ-68)
+
+1. **New research** → below the form: open-question suggestions appear
+2. Click one → the question box fills; **never auto-starts**
+3. Type a draft → **Refine question** → answer the 3 clarifying questions → **Use this** → refined question + context fill the form
+4. Try **Keep original** on a second draft → untouched; keyboard (Enter) works through both flows
+5. Pass: both helpers are opt-in, keyboard-accessible, drafts preserved on dismiss
+
+## 7. Library (REQ-64)
+
+1. Sidebar → **Library**: folder tree, auto-categorized (topic + methodology), sortable (recency/title)
+2. Open a stored report → its own Reading Room view
+3. **Connections** panel: shared-source ⇄ and topical → edges
+4. v2 previews: project graph + task inbox panels render
+5. Pass: folders, sorting, connections, previews all render from the fixture data
+
+## 8. Settings (REQ-65)
+
+1. API keys: masked (never raw); storage directory field
+2. Methodology defaults: resolved 12-dial display
+3. Appearance preview; About & version (step 2)
+4. Pass: everything honest and functional on mock data
+
+## Optional: hands-on the live engine (not on this URL)
+
+```bash
+# locally, two terminals:
+cd backend && uv sync && uv run uvicorn researchx.api.app:app --port 8000
+cd frontend && NEXT_PUBLIC_RESEARCHX_API_MODE=live corepack pnpm dev
+# then repeat steps 3-5 against the real engine (fake adapters, zero keys)
+```
+
+## Decision rubric (the gate this UAT feeds)
+
+- **Approve**: recorded via /ci-run → milestone merges to main,
+  v0.2.5 publishes as the MVP release, v0.3 planning unblocks
+  (with G-009 scope ratified: library/settings/suggestions/refine/
+  graph stay mock-backed until v0.3+)
+- **Request changes**: feedback becomes binding decisions for a
+  fix cycle (v0.1 precedent: two feedback cycles before approval)

.ciagent/release/VERSIONING.md

@@ -8,8 +8,8 @@ as established by the CIAgent branch strategy and `config.json`.
 
 | Milestone | Tags | Deployed by |
 |---|---|---|
-| v0.1 prototype | v0.1.0 … v0.1.5 | `bash .ciagent/release/deploy.sh v0.1.5` |
-| v0.2 MVP | v0.2.0 … | `bash .ciagent/release/deploy.sh v0.2.x` |
+| v0.1 prototype | v0.1.0 … v0.1.8 | `bash .ciagent/release/deploy.sh v0.1.8` |
+| v0.2 MVP | v0.2.0 … v0.2.5 | `bash .ciagent/release/deploy.sh v0.2.5-uat` (staged) — see DEPLOY-RECORD.md |
 
 ## Rules
 
@@ -33,7 +33,7 @@ as established by the CIAgent branch strategy and `config.json`.
 6. **Milestone gating applies to deployment too.** The v0.1 prototype
    deploys for owner review. v0.2 releases deploy only after the
    REQ-62 owner-approval gate is cleared (recorded on the extended
-   prototype, v0.1.6).
+   prototype, v0.1.7 → released as v0.1.8).
 
 ## Container conventions
 

.gitea/workflows/ci.yml

@@ -0,0 +1,157 @@
+# .gitea/workflows/ci.yml - ResearchX phase-4 CI gate (researchx#24).
+#
+# This file IS the gate. The pre-code clause (coreci/company#105, c14057):
+# a code phase opens only when the product repo's gating workflow file has
+# dispatched at least one run on `main` and every job in that file is green
+# in that run. Until this file exists, coreci/researchx has no workflow and
+# no run at all - that is the case the clause was amended for (researchx#24,
+# c14093). A half-green pipeline does not open the phase either.
+#
+# Two jobs:
+#   backend  - uv + Python 3.12: ruff, mypy, pytest
+#   frontend - Node 22 + pnpm 12.6.0: typecheck, lint, test, build
+#
+# Runner label: `ubuntu-latest` - the org CI fleet's published label whose
+# image is docker.gitea.com/runner-images:ubuntu-latest (label map read at
+# source: coreci/nextcraft deploy/ci/docker-compose.yaml + deploy/ci/README.md,
+# R-3). The previous string `employee-runner` was a fleet NAME, not a label:
+# the employee fleet's labels are `employee-py` and `employee-coder` (read
+# from a live job log of this seat's own home), and the CI fleet's are node /
+# ubuntu-latest / python / release - no runner carried the old label, so a
+# merged file asking for it could still buy no run.
+#
+# Toolchain: measured, not assumed. From the runner's own logs (job 56393,
+# coreci/nova-platform, 2026-10-26T23:17Z, and job 57005, coreci/inboxos-v1,
+# 2026-10-27T03:01Z): the image carries python 3.12.3, pip, git, node (the
+# actions run in it), pypi REACHABLE and github REACHABLE; actions/checkout@v4,
+# actions/setup-python@v5 and actions/setup-go@v5 all run inside it. It does
+# NOT carry uv or pnpm, so this file installs them: uv from pypi (pip), pnpm
+# 12.6.0 through corepack - the repo's own documented way (README command map).
+# The gates are the repo's documented commands: backend `uv run ruff check src
+# tests`, `uv run mypy src`, `uv run pytest`; frontend `pnpm typecheck`,
+# `pnpm lint`, `pnpm test`, `pnpm build`. The frontend lane mirrors the
+# release image's own recipe (frontend/Dockerfile: node:22-alpine, corepack,
+# pnpm install --frozen-lockfile, pnpm build), so the gate tests what the
+# product ships.
+#
+# Owner of a red leg (the clause asks for the owner of the fix next to the
+# owner of the product line): toolchain / image / dispatch problems ->
+# coreci-sre (employee-runner-fleet + gitea-instance); product-line problems
+# -> coreci-researchx-po. Approval for this file rides the merge request
+# (merge = approval, constitution v1.3).
+
+name: ci
+
+on:
+  push:
+  pull_request:
+    branches: ["main"]
+  workflow_dispatch:
+
+jobs:
+  backend:
+    name: "backend (uv, Python 3.12: ruff/mypy/pytest)"
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      # uv is not in the CI image; pypi is reachable from it (measured). The
+      # install is a toolchain leg, not a product gate: the gates still run
+      # from the repo's own committed lockfile (backend/uv.lock).
+      - name: Install uv (from pypi)
+        run: |
+          set -eu
+          python -m pip install --upgrade uv
+          uv --version
+
+      - name: Install dependencies (uv, from the committed lockfile)
+        working-directory: backend
+        run: uv sync --frozen
+
+      - name: Lint (ruff)
+        working-directory: backend
+        run: uv run ruff check src tests
+
+      - name: Typecheck (mypy)
+        working-directory: backend
+        run: uv run mypy src
+
+      - name: Test (pytest)
+        working-directory: backend
+        run: uv run pytest
+
+  frontend:
+    name: "frontend (Next.js on pnpm: typecheck/lint/test/build)"
+    runs-on: ubuntu-latest
+    timeout-minutes: 25
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      # Node 22 to mirror the release image (frontend/Dockerfile: node:22).
+      - name: Setup Node 22
+        uses: actions/setup-node@v4
+        with:
+          node-version: "22"
+
+      - name: Setup Python 3.12 (for the real-stack e2e bridge)
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install uv (from pypi)
+        run: |
+          set -eu
+          python -m pip install --upgrade uv
+
+      # pnpm 12.6.0 is pinned by frontend/package.json `packageManager`;
+      # corepack reads it from there. If the image carries no corepack, npm
+      # installs the same pinned version.
+      - name: pnpm 12.6.0 (corepack, pinned by frontend/package.json)
+        working-directory: frontend
+        run: |
+          set -eu
+          node --version
+          corepack enable pnpm 2>/dev/null || true
+          if ! pnpm --version >/dev/null 2>&1; then
+            npm i -g pnpm@12.6.0
+          fi
+          test "$(pnpm --version)" = "12.6.0"
+
+      - name: Install dependencies (from the committed lockfile)
+        working-directory: frontend
+        run: pnpm install --frozen-lockfile
+
+      # frontend/src/lib/api/e2e-real-stack.test.ts drives the real FastAPI
+      # stack: it spawns `uv run python -m researchx.api.dev_bridge` from
+      # ../backend (loopback :8000, fakes only, zero API keys). Without a
+      # synced backend venv that test cannot come up, so the lane provisions
+      # it. Provisioning only - the backend gates stay in the backend job.
+      - name: Backend venv for the real-stack e2e bridge
+        working-directory: backend
+        run: uv sync --frozen
+
+      - name: Typecheck
+        working-directory: frontend
+        run: pnpm typecheck
+
+      - name: Lint
+        working-directory: frontend
+        run: pnpm lint
+
+      - name: Test
+        working-directory: frontend
+        run: pnpm test
+
+      - name: Build
+        working-directory: frontend
+        env:
+          NEXT_TELEMETRY_DISABLED: "1"
+        run: pnpm build

README.md

@@ -1,26 +1,112 @@
 # ResearchX
 
+**TL;DR** — ResearchX turns one question into a cited research report: pick a method, approve the plan, and the engine visits real web sources, with every claim anchored to a quoted passage from a page it actually read. The engine milestone (v0.2.5) is shipped and owner-approved; hosting goes live next (v0.3, in progress).
+
+- **What** — FastAPI backend (planning, search, extraction, verification, export gates) plus a Next.js frontend; the full test suite runs with zero API keys.
+- **Why** — Readers can check every citation back to its source passage; runs are resumable from durable state.
+- **Action** — no action — FYI. Developers: see the Quickstart below.
+- **Details** — `frontend/README.md` (web app); `.ciagent/` (pipeline state and roadmap).
+
 A deep-research studio where you bring your own model, storage, and memory; choose a research methodology before a single query fires; and every claim in the final report is anchored to a visited, verified, quotable source.
 
-**Status: prototype (milestone v0.1)** — UI/UX with mock data. No backend, no API keys, no network calls.
+**Status: MVP shipped (v0.2.5, owner-approved 2026-09-27)** — the full research engine (FastAPI + asyncio state machine + adapter layer + attack-proven trust loop) behind the v0.1 frontend. Live mode covers the core research loop (G-002/G-009): the engine runs locally per the quickstart; library/settings/suggestions/refine stay mock-backed until v0.3+.
 
 ## Quickstart
 
 ```bash
+# frontend (prototype, mock-backed — works today)
 cd frontend
-pnpm install
-pnpm dev
+corepack pnpm install
+corepack pnpm dev          # http://localhost:3000
+
+# backend (MVP — uv manages Python 3.12 and the venv)
+cd backend
+uv sync                    # installs deps + editable researchx package
+uv run uvicorn researchx.api.app:app --reload --port 8000
+uv run pytest              # full suite, zero API keys
 ```
 
-Open http://localhost:3000 — you land on **Ask**, inside the app shell (left sidebar, top bar with ⌘K search and your avatar). Type a question, click **Research this**, pick a methodology on **Choose** (Deep Report is the recommended default), and press **Start research**.
-
 Three clicks from cold start to initiated research.
 
+## Monorepo command map
+
+| Layer | Install | Dev | Gates |
+|---|---|---|---|
+| backend (uv, Python 3.12) | `uv sync` | `uv run uvicorn researchx.api.app:app --reload --port 8000` | `uv run ruff check src tests` · `uv run mypy src` · `uv run pytest` |
+| frontend (pnpm 12.6) | `corepack pnpm install` | `corepack pnpm dev` | `corepack pnpm typecheck` · `corepack pnpm lint` · `corepack pnpm test` · `corepack pnpm build` |
+
+## Engine architecture (v0.2 P2)
+
+The research engine is a hand-rolled asyncio state machine:
+
+```
+PLANNING → AWAITING_APPROVAL → SEARCHING → EXTRACTING → REFLECTING ─┐
+                (halt until             ↑ depth loop (dials.depth)  │
+                 approved)              └────────────────────────────┘
+→ SYNTHESIZING → VERIFYING → DONE  (+ CANCELLED / FAILED terminals)
+```
+
+- Durable state: `runs/<id>/state.json` rewritten atomically after every transition; resume re-enters at the recorded cursor with the persisted plan
+- Event bus: typed events (`run_started`, `query_fired`, `source_visited`, `passage_extracted`, `state_changed`, `run_done`, `run_error`) — trace per run
+- Visited-only constraint: the writer's context is the evidence store and nothing else
+- Trust loop: SSRF-guarded liveness (live/stale/dead), quote anchoring (normalize + fuzzy ≥ 0.85, weak matches flagged), citation ledger JSON, exportable verification checklist, single-source vs corroborated confidence labels
+
+Run artifacts per run: `state.json`, `report.md`, `ledger.json`, `checklist.md`.
+
+Try it on fakes (no keys): `uv run python -m researchx.engine.demo`
+
+## Adversarial guarantees (v0.2 P4)
+
+Every trust-loop claim is attacked by the adversarial suite (`backend/tests/test_adversarial.py`) — these are tests that try to fool the verifier, and their passing proves the defenses:
+
+| Attack | Defense (proven) |
+|---|---|
+| Writer hallucinates a citation to a passage that was never stored | Unknown passage IDs count as **unanchored claims** in the ledger; the export gate fails the report |
+| Fabricated quote (matches nothing) | Anchoring verdict: no match, flagged — never silently accepted |
+| Near-miss quote (0.80–0.85 similarity) | Flagged `weak_match` in the ledger — surfaced, not accepted |
+| Liveness probe redirected to a private/metadata IP | Per-hop redirect re-guarding classifies it **dead** (SSRF refusal) |
+| Redirect chain ending at a gone page (410) | Classified **dead** |
+| Oversized page (5MB) response | 2MB read cap — classifies without unbounded memory |
+| Pause during the depth loop | Durable state persists; resume completes the run over the HTTP API |
+| Cancel mid-loop | Terminal CANCELLED state persisted, never swallowed |
+
+REQ-23 (≥99% citation liveness) is a per-run **export gate** enforced by the verification checklist, plus an opt-in keyed live tier (`cd backend && uv run pytest -m live`) — the zero-key CI suite never asserts it vacuously.
+
+The E2E happy path (≤3 clicks: ask, choose, approve) is validated against the real FastAPI + engine stack, defaults only — not the mock (`frontend/src/lib/api/e2e-real-stack.test.ts`).
+
+## Adapter configuration (v0.2)
+
+All keys resolve from env files only (`.env`, `.env.secrets`, `.env.*` — never the shell environment, never git):
+
+| Variable | Scope | Used by |
+|---|---|---|
+| `OLLAMA_API_KEY` | model (cloud) | Ollama cloud endpoint `https://ollama.com/v1`; absent/keyless falls back to `http://localhost:11434/v1` automatically |
+| `OLLAMA_BASE_URL` | model | Overrides the default cloud base URL |
+| `TAVILY_API_KEY` | search | Tavily default search; absent falls back to the keyless DuckDuckGo adapter (degraded mode — surfaced in the run trace) |
+
+The test suite needs **no** keys: fake model/search adapters (REQ-31) drive every engine test.
+
+## Live mode (v0.2 P3)
+
+The frontend runs mock-backed by default (works standalone, zero keys). To run the core research loop against the real backend:
+
+```bash
+# terminal 1 — backend (fake adapters by default; real Ollama/Tavily adapters
+# are used by the engine in v0.2.5+ wiring — the served API currently ships
+# fake-adapter runs for demos and tests; see Adapter configuration below)
+cd backend && uv run uvicorn researchx.api.app:app --reload --port 8000
+
+# terminal 2 — frontend in live mode
+cd frontend && NEXT_PUBLIC_RESEARCHX_API_MODE=live corepack pnpm dev
+```
+
+Live mode covers the core loop (Ask → Choose → approve plan → live trace → report + ledger); the library, settings persistence, suggestions, refine, and graph surfaces stay mock-backed until v0.3. The API surface: `POST /api/runs`, `GET /api/methodologies`, run lifecycle (`approve/pause/cancel/resume`), `GET /api/runs/{id}/events` (SSE), `GET /api/config`, report + ledger artifacts.
+
 ## What's in the prototype
 
 | Screen | What it does |
 |---|---|
-| `/ask` | One question box + one optional context box. Nothing else competing for attention. |
+| `/ask` | One question box + one optional context box — plus two opt-in helpers below and beside them: open-question suggestions (follow-ups from your past runs, one click fills the box) and the Refine question dialogue (a few clarifying answers → a composed, sharper question). Neither ever auto-starts. |
 | `/choose` | All 8 locked methodology cards — mock ETA, cost estimate, why-recommended, and the 12 methodology dials behind each card's Advanced drawer. |
 | `/run/[id]` | Plan & Run: approve the research plan (sub-questions, source universe, outline), watch the live trace stream, pause/resume or cancel. |
 | `/run/[id]/report` | Reading Room: the report with page-anchored citations — hover or focus any `[n]` marker for the exact quoted passage — plus the citation ledger and Markdown/JSON exports. |

backend/.gitignore

@@ -0,0 +1,5 @@
+.venv/
+__pycache__/
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/

backend/.python-version

@@ -0,0 +1 @@
+3.12

backend/pyproject.toml

@@ -0,0 +1,48 @@
+[project]
+name = "researchx"
+version = "0.2.0"
+description = "ResearchX — methodology-first deep research studio"
+requires-python = ">=3.12"
+dependencies = [
+    "fastapi>=0.115,<0.116",
+    "pydantic>=2.8,<3",
+    "uvicorn>=0.30,<1",
+    "sse-starlette>=2.1,<3",
+    "httpx>=0.27,<1",
+]
+
+[dependency-groups]
+dev = [
+    "ruff>=0.6",
+    "mypy>=1.11",
+    "pytest>=8",
+    "pytest-asyncio>=0.23",
+    "httpx>=0.28.1",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/researchx"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py312"
+
+[tool.ruff.lint]
+extend-select = ["I", "UP"]
+
+[tool.mypy]
+strict = true
+mypy_path = "src"
+python_version = "3.12"
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+markers = [
+    "live: opt-in keyed tests against real adapters (skipped without keys)",
+]
+asyncio_mode = "auto"
+testpaths = ["tests"]

backend/src/researchx/adapters/capability_probe.py

@@ -0,0 +1,52 @@
+import json
+
+import httpx
+
+from researchx.adapters.model import ModelAdapter
+from researchx.adapters.probe import (
+    DEFAULT_EMBEDDING_BATCH,
+    CapabilityProbe,
+    cap_context_window,
+    structured_output_warning,
+)
+from researchx.adapters.types import ModelMessage
+
+
+def supports_probe(adapter: ModelAdapter) -> bool:
+    return getattr(adapter, "probing_supported", False)
+
+
+async def probe_model_adapter(adapter: ModelAdapter) -> CapabilityProbe:
+    models = await adapter.list_models()
+    smoke_ok = await _structured_output_smoke_test(adapter)
+    writer = adapter.roles().writer
+    warning = structured_output_warning(smoke_ok, writer)
+    endpoint = getattr(adapter, "active_base_url", "unknown")
+    fallback_reason = getattr(adapter, "last_fallback_reason", None)
+    return CapabilityProbe(
+        endpoint=str(endpoint),
+        models=models,
+        context_window=cap_context_window(None),
+        embedding_batch=DEFAULT_EMBEDDING_BATCH,
+        structured_outputs_supported=smoke_ok,
+        structured_output_warning=warning,
+        fallback_reason=fallback_reason,
+    )
+
+
+async def _structured_output_smoke_test(adapter: ModelAdapter) -> bool:
+    probe_messages = [
+        ModelMessage(
+            role="user",
+            content='Return a JSON object with exactly one key "ok" set to true. No other text.',
+        )
+    ]
+    try:
+        result = await adapter.chat(probe_messages, model=adapter.roles().writer, json_mode=True)
+    except (httpx.HTTPError, httpx.HTTPStatusError, ValueError, KeyError):
+        return False
+    try:
+        parsed = json.loads(result.content.strip())
+    except json.JSONDecodeError:
+        return False
+    return isinstance(parsed, dict) and parsed.get("ok") is True

backend/src/researchx/adapters/duckduckgo.py

@@ -0,0 +1,136 @@
+import re
+from datetime import UTC, datetime
+from html import unescape
+from urllib.parse import parse_qs, unquote, urlparse
+
+import httpx
+
+from researchx.adapters.secrets import SecretsProvider
+from researchx.adapters.tavily import TavilySearchAdapter, extract_text, extract_title
+from researchx.adapters.types import AdapterError, PageContent, SearchResult
+from researchx.adapters.url_guard import url_allowed
+
+_DDG_URL = "https://html.duckduckgo.com/html"
+_SEARCH_TIMEOUT = 10.0
+_FETCH_TIMEOUT = 10.0
+_MAX_FETCH_REDIRECTS = 5
+_BACKOFF_SECONDS = 1.0
+_USER_AGENT = "researchx/0.2 (local research studio)"
+_RESULT_RE = re.compile(
+    r'<a[^>]+class="[^"]*result__a[^"]*"[^>]+href="([^"]+)"[^>]*>(.*?)</a>',
+    re.DOTALL,
+)
+_SNIPPET_RE = re.compile(r'<a[^>]+class="[^"]*result__snippet[^"]*"[^>]*>(.*?)</a>', re.DOTALL)
+_TAG_RE = re.compile(r"<[^>]+>")
+
+
+class DuckDuckGoSearchAdapter:
+    def __init__(self) -> None:
+        self._last_degradation: str | None = None
+
+    async def search(self, query: str, *, max_results: int = 5) -> list[SearchResult]:
+        results = await self._attempt_search(query, max_results)
+        if results is None:
+            self._last_degradation = "duckduckgo rate-limited or unreachable; returning partial results"
+            return []
+        self._last_degradation = None
+        return results
+
+    async def _attempt_search(self, query: str, max_results: int) -> list[SearchResult] | None:
+        import asyncio
+
+        params = {"q": query}
+        headers = {"User-Agent": _USER_AGENT}
+        for attempt in range(2):
+            try:
+                async with httpx.AsyncClient(timeout=_SEARCH_TIMEOUT) as client:
+                    response = await client.post(_DDG_URL, params=params, headers=headers)
+                    if response.status_code in (403, 429):
+                        if attempt == 0:
+                            await asyncio.sleep(_BACKOFF_SECONDS)
+                            continue
+                        return None
+                    response.raise_for_status()
+                    return self._parse_results(response.text, max_results)
+            except httpx.HTTPError:
+                if attempt == 0:
+                    await asyncio.sleep(_BACKOFF_SECONDS)
+                    continue
+                return None
+        return None
+
+    def _parse_results(self, html: str, max_results: int) -> list[SearchResult]:
+        anchors = _RESULT_RE.findall(html)
+        snippets = [self._strip(s) for s in _SNIPPET_RE.findall(html)]
+        results: list[SearchResult] = []
+        for index, (href, title_html) in enumerate(anchors):
+            url = self._normalize_href(href)
+            if not url:
+                continue
+            snippet = snippets[index] if index < len(snippets) else ""
+            results.append(
+                SearchResult(
+                    title=self._strip(title_html),
+                    url=url,
+                    snippet=snippet,
+                )
+            )
+            if len(results) >= max_results:
+                break
+        return results
+
+    def _normalize_href(self, href: str) -> str:
+        decoded = unescape(href)
+        parsed = urlparse(decoded)
+        if parsed.path.startswith("//duckduckgo.com/l/") or parsed.netloc == "duckduckgo.com":
+            target = parse_qs(parsed.query).get("uddg", [""])[0]
+            return unquote(target)
+        if decoded.startswith("http"):
+            return decoded
+        return ""
+
+    def _strip(self, html: str) -> str:
+        text = _TAG_RE.sub("", html)
+        return re.sub(r"\s+", " ", text).strip()
+
+    async def fetch(self, url: str) -> PageContent:
+        from urllib.parse import urljoin
+
+        current = url
+        async with httpx.AsyncClient(
+            timeout=_FETCH_TIMEOUT,
+            follow_redirects=False,
+            headers={"User-Agent": _USER_AGENT},
+        ) as client:
+            for _ in range(_MAX_FETCH_REDIRECTS + 1):
+                if not url_allowed(current):
+                    raise AdapterError(
+                        "fetch refused: url not allowed (private or non-http scheme)"
+                    )
+                response = await client.get(current)
+                if 300 <= response.status_code < 400:
+                    location = response.headers.get("location")
+                    if not location:
+                        raise AdapterError("fetch failed: redirect without location")
+                    current = urljoin(current, location)
+                    continue
+                response.raise_for_status()
+                return PageContent(
+                    url=url,
+                    title=extract_title(response.text),
+                    text=extract_text(response.text),
+                    fetched_at=datetime.now(UTC),
+                )
+        raise AdapterError("fetch failed: too many redirects")
+
+    @property
+    def last_degradation(self) -> str | None:
+        return self._last_degradation
+
+
+def resolve_search_adapter(
+    secrets: SecretsProvider,
+) -> tuple[TavilySearchAdapter | DuckDuckGoSearchAdapter, str]:
+    if secrets.resolve("TAVILY_API_KEY"):
+        return TavilySearchAdapter(secrets), "tavily"
+    return DuckDuckGoSearchAdapter(), "duckduckgo-keyless"

backend/src/researchx/adapters/fakes.py

@@ -0,0 +1,165 @@
+from datetime import UTC, datetime
+
+from researchx.adapters.model import ModelRoles
+from researchx.adapters.types import (
+    AdapterError,
+    ChatResult,
+    ModelMessage,
+    PageContent,
+    SearchResult,
+)
+
+
+def _now() -> datetime:
+    return datetime.now(UTC)
+
+
+class FakeModelAdapter:
+    def __init__(self, canned: list[ChatResult]) -> None:
+        self._canned = list(canned)
+        self._json_mode_calls: list[bool] = []
+        self.roles_value = ModelRoles(planner="fake-planner", writer="fake-writer")
+
+    async def chat(
+        self,
+        messages: list[ModelMessage],
+        *,
+        model: str,
+        temperature: float = 0.2,
+        json_mode: bool = False,
+    ) -> ChatResult:
+        del messages, temperature
+        self._json_mode_calls.append(json_mode)
+        if not self._canned:
+            raise AdapterError(f"no canned response for model {model}")
+        return self._canned.pop(0)
+
+    async def list_models(self) -> list[str]:
+        return ["fake-model"]
+
+    def roles(self) -> ModelRoles:
+        return self.roles_value
+
+    @property
+    def last_json_mode(self) -> bool | None:
+        return self._json_mode_calls[-1] if self._json_mode_calls else None
+
+
+class FakeSearchAdapter:
+    def __init__(self, corpus: list[PageContent]) -> None:
+        self._corpus = list(corpus)
+        self._by_url = {page.url: page for page in corpus}
+
+    async def search(self, query: str, *, max_results: int = 5) -> list[SearchResult]:
+        terms = [t.lower() for t in query.split() if t]
+        results: list[SearchResult] = []
+        for page in self._corpus:
+            haystack = f"{page.title}\n{page.text}".lower()
+            if all(t in haystack for t in terms):
+                snippet = page.text[:200]
+                results.append(SearchResult(title=page.title, url=page.url, snippet=snippet))
+            if len(results) >= max_results:
+                break
+        return results
+
+    async def fetch(self, url: str) -> PageContent:
+        page = self._by_url.get(url)
+        if page is None:
+            raise AdapterError(f"unknown url: {url}")
+        return page.model_copy(update={"fetched_at": _now()})
+
+
+SHARED_SENTENCE = (
+    "The verification pass re-anchored every quoted claim to its stored passage "
+    "before the report was allowed to ship."
+)
+
+
+def corpus() -> list[PageContent]:
+    stamp = _now()
+    pages = [
+        PageContent(
+            url="https://example.org/verification",
+            title="Verification passes in research pipelines",
+            text=(
+                "Deep research pipelines fail when citations are decorative. "
+                f"{SHARED_SENTENCE} The pipeline treats every quote as a claim "
+                "about evidence, not a claim about the world.\n\n"
+                "Verification therefore runs twice: once at generation time and "
+                "once at export time — liveness is rechecked, anchors are "
+                "re-matched, and the ledger records the outcome."
+            ),
+            fetched_at=stamp,
+        ),
+        PageContent(
+            url="https://example.org/anchoring",
+            title="Quote anchoring and auditability",
+            text=(
+                f"{SHARED_SENTENCE} Anchoring is the mechanism that makes this "
+                "auditability real: each claim carries a fuzzy-matched pointer "
+                "back to the exact stored passage — d’abord normalisé, puis "
+                "comparé. 近似匹配的阈值设定为 0.85.\n\n"
+                "A claim without an anchor is not a finding; it is a hypothesis "
+                "with better typography."
+            ),
+            fetched_at=stamp,
+        ),
+        PageContent(
+            url="https://example.org/ollama",
+            title="OpenAI-compatible endpoints on Ollama",
+            text=(
+                "Ollama exposes an OpenAI-compatible surface at /v1: chat "
+                "completions accept the standard message array, and model "
+                "listing works via GET /v1/models. Cloud deployments require "
+                "a bearer key; localhost deployments are keyless by default.\n\n"
+                "Capability probing stays conservative: cap context at the "
+                "minimum of the model claim and 8192 tokens, and batch "
+                "embeddings at 8."
+            ),
+            fetched_at=stamp,
+        ),
+        PageContent(
+            url="https://example.org/search-routing",
+            title="Search routing across keyless and keyed providers",
+            text=(
+                "A keyed provider (Tavily) is the default route; a keyless "
+                "fallback (DuckDuckGo HTML) degrades gracefully under rate "
+                "limiting. The fallback is a degraded mode, not a second "
+                "source — its warnings surface in the run trace.\n\n"
+                "Routing decisions belong to the methodology dials, never to "
+                "the writer."
+            ),
+            fetched_at=stamp,
+        ),
+        PageContent(
+            url="https://example.org/state-machines",
+            title="Durable state machines for research engines",
+            text=(
+                "A research engine survives restarts by persisting state after "
+                "every transition: an atomic tmp-plus-replace write leaves no "
+                "torn files, and a cursor records the depth-loop position.\n\n"
+                "Pause clears an asyncio event; cancel persists a terminal "
+                "state; resume re-enters the loop at the recorded cursor. "
+                "CancelledError is re-raised after the write — never swallowed."
+            ),
+            fetched_at=stamp,
+        ),
+        PageContent(
+            url="https://example.org/methodology",
+            title="Methodology-first research selection",
+            text=(
+                "Choosing a methodology before a single query fires converts "
+                "ad-hoc prompt crafting into a structured, reproducible "
+                "decision. Dials — breadth, depth, citation rigor, "
+                "verification passes — resolve into a snapshot that persists "
+                "with every run.\n\n"
+                "The methodology registry ships Rapid Answer for memo-shaped "
+                "answers and Deep Report for executive reports with full "
+                "verification."
+            ),
+            fetched_at=stamp,
+        ),
+    ]
+    return pages
+
+CORPUS = corpus()

backend/src/researchx/adapters/local_storage.py

@@ -0,0 +1,73 @@
+import asyncio
+import os
+import re
+import secrets as secrets_module
+from pathlib import Path
+
+from researchx.adapters.types import AdapterError
+
+_RUN_ID_ALPHABET = "abcdefghjkmnpqrstuvwxyz23456789"
+_RUN_ID_RE = re.compile(r"^[a-z0-9]{8}$")
+_ARTIFACT_NAME_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._-]*$")
+
+
+def generate_run_id() -> str:
+    return "".join(secrets_module.choice(_RUN_ID_ALPHABET) for _ in range(8))
+
+
+def _validate_run_id(run_id: str) -> None:
+    if not _RUN_ID_RE.match(run_id):
+        raise AdapterError("invalid run id")
+
+
+def _validate_artifact_name(name: str) -> None:
+    if not _ARTIFACT_NAME_RE.match(name) or Path(name).name != name:
+        raise AdapterError("invalid artifact name")
+
+
+class LocalStorageAdapter:
+    def __init__(self, base_dir: Path) -> None:
+        self._base_dir = base_dir
+
+    def run_dir(self, run_id: str) -> Path:
+        _validate_run_id(run_id)
+        return self._base_dir / "runs" / run_id
+
+    async def write_run_artifact(self, run_id: str, name: str, content: str) -> Path:
+        _validate_artifact_name(name)
+        target = self.run_dir(run_id) / name
+        target.parent.mkdir(parents=True, exist_ok=True)
+        tmp_path = target.with_name(f"{target.name}.{secrets_module.token_hex(4)}.tmp")
+
+        def _write_atomic() -> None:
+            with open(tmp_path, "w", encoding="utf-8") as handle:
+                handle.write(content)
+                handle.flush()
+                os.fsync(handle.fileno())
+            tmp_path.replace(target)
+
+        try:
+            await asyncio.to_thread(_write_atomic)
+        finally:
+            tmp_path.unlink(missing_ok=True)
+        return target
+
+    async def read_run_artifact(self, run_id: str, name: str) -> str:
+        _validate_artifact_name(name)
+        target = self.run_dir(run_id) / name
+        try:
+            return target.read_text(encoding="utf-8")
+        except FileNotFoundError as exc:
+            raise AdapterError(f"artifact not found: runs/{run_id}/{name}") from exc
+
+    async def append_run_artifact(self, run_id: str, name: str, content: str) -> Path:
+        _validate_artifact_name(name)
+        target = self.run_dir(run_id) / name
+        target.parent.mkdir(parents=True, exist_ok=True)
+
+        def _append() -> None:
+            with open(target, "a", encoding="utf-8") as handle:
+                handle.write(content)
+
+        await asyncio.to_thread(_append)
+        return target

backend/src/researchx/adapters/memory.py

@@ -0,0 +1,8 @@
+from typing import Protocol, runtime_checkable
+
+
+@runtime_checkable
+class MemoryAdapter(Protocol):
+    async def remember(self, scope: str, key: str, value: str) -> None: ...
+
+    async def recall(self, scope: str, key: str) -> str | None: ...

backend/src/researchx/adapters/model.py

@@ -0,0 +1,26 @@
+from typing import Protocol, runtime_checkable
+
+from pydantic import BaseModel
+
+from researchx.adapters.types import ChatResult, ModelMessage
+
+
+class ModelRoles(BaseModel):
+    planner: str
+    writer: str
+
+
+@runtime_checkable
+class ModelAdapter(Protocol):
+    async def chat(
+        self,
+        messages: list[ModelMessage],
+        *,
+        model: str,
+        temperature: float = 0.2,
+        json_mode: bool = False,
+    ) -> ChatResult: ...
+
+    async def list_models(self) -> list[str]: ...
+
+    def roles(self) -> ModelRoles: ...

backend/src/researchx/adapters/ollama.py

@@ -0,0 +1,118 @@
+from typing import Any
+
+import httpx
+
+from researchx.adapters.model import ModelRoles
+from researchx.adapters.secrets import EnvFileSecretsProvider
+from researchx.adapters.types import AdapterError, ChatResult, ModelMessage, Usage
+
+_DEFAULT_CLOUD_BASE = "https://ollama.com/v1"
+_DEFAULT_LOCAL_BASE = "http://localhost:11434/v1"
+_REQUEST_TIMEOUT = 60.0
+
+
+class OllamaModelAdapter:
+    probing_supported = True
+
+    def __init__(
+        self,
+        secrets: EnvFileSecretsProvider,
+        planner_model: str,
+        writer_model: str,
+        cloud_base_url: str | None = None,
+        local_base_url: str | None = None,
+    ) -> None:
+        self._secrets = secrets
+        self._roles = ModelRoles(planner=planner_model, writer=writer_model)
+        self._cloud_base = (cloud_base_url or secrets.resolve("OLLAMA_BASE_URL") or _DEFAULT_CLOUD_BASE).rstrip("/")
+        self._local_base = (local_base_url or _DEFAULT_LOCAL_BASE).rstrip("/")
+        self._active_base = self._cloud_base
+        self._api_key = secrets.resolve("OLLAMA_API_KEY")
+        self._last_fallback_reason: str | None = None
+
+    def _headers(self, base_url: str) -> dict[str, str]:
+        headers = {"Content-Type": "application/json"}
+        if base_url == self._cloud_base and self._api_key:
+            headers["Authorization"] = f"Bearer {self._api_key}"
+        return headers
+
+    async def _post_chat(
+        self,
+        base_url: str,
+        payload: dict[str, object],
+    ) -> dict[str, Any]:
+        async with httpx.AsyncClient(timeout=_REQUEST_TIMEOUT) as client:
+            response = await client.post(
+                f"{base_url}/chat/completions",
+                json=payload,
+                headers=self._headers(base_url),
+            )
+            try:
+                response.raise_for_status()
+            except httpx.HTTPError as exc:
+                raise AdapterError(f"chat request failed ({type(exc).__name__})") from exc
+            data: dict[str, Any] = response.json()
+            return data
+
+    async def chat(
+        self,
+        messages: list[ModelMessage],
+        *,
+        model: str,
+        temperature: float = 0.2,
+        json_mode: bool = False,
+    ) -> ChatResult:
+        payload: dict[str, object] = {
+            "model": model,
+            "messages": [m.model_dump() for m in messages],
+            "temperature": temperature,
+        }
+        if json_mode:
+            payload["response_format"] = {"type": "json_object"}
+        try:
+            data = await self._post_chat(self._active_base, payload)
+        except AdapterError as first_error:
+            if self._active_base == self._cloud_base:
+                self._last_fallback_reason = f"cloud endpoint failed: {type(first_error.__cause__).__name__ if first_error.__cause__ else 'Error'}"
+                self._active_base = self._local_base
+                data = await self._post_chat(self._local_base, payload)
+            else:
+                raise
+        choice = data["choices"][0]["message"]
+        raw_usage = data.get("usage") or {}
+        usage = Usage(
+            prompt_tokens=raw_usage.get("prompt_tokens"),
+            completion_tokens=raw_usage.get("completion_tokens"),
+        )
+        return ChatResult(content=choice["content"], model=model, usage=usage)
+
+    async def list_models(self) -> list[str]:
+        try:
+            async with httpx.AsyncClient(timeout=_REQUEST_TIMEOUT) as client:
+                response = await client.get(
+                    f"{self._active_base}/models",
+                    headers=self._headers(self._active_base),
+                )
+                try:
+                    response.raise_for_status()
+                except httpx.HTTPError as exc:
+                    raise AdapterError(f"models listing failed ({type(exc).__name__})") from exc
+                data: dict[str, Any] = response.json()
+            return [str(entry["id"]) for entry in data.get("data", [])]
+        except (AdapterError, httpx.HTTPError):
+            if self._active_base == self._cloud_base:
+                self._last_fallback_reason = "cloud models listing failed; using local"
+                self._active_base = self._local_base
+                return await self.list_models()
+            raise
+
+    def roles(self) -> ModelRoles:
+        return self._roles
+
+    @property
+    def active_base_url(self) -> str:
+        return self._active_base
+
+    @property
+    def last_fallback_reason(self) -> str | None:
+        return self._last_fallback_reason

backend/src/researchx/adapters/probe.py

@@ -0,0 +1,34 @@
+from pydantic import BaseModel
+
+DEFAULT_CONTEXT_CAP = 8192
+DEFAULT_EMBEDDING_BATCH = 8
+
+
+class CapabilityProbe(BaseModel):
+    endpoint: str
+    models: list[str]
+    context_window: int
+    embedding_batch: int
+    structured_outputs_supported: bool
+    structured_output_warning: str | None = None
+    fallback_reason: str | None = None
+
+    @property
+    def degraded(self) -> bool:
+        return self.structured_output_warning is not None or self.fallback_reason is not None
+
+
+def cap_context_window(model_claim: int | None) -> int:
+    if model_claim is None or model_claim <= 0:
+        return DEFAULT_CONTEXT_CAP
+    return min(model_claim, DEFAULT_CONTEXT_CAP)
+
+
+def structured_output_warning(supported: bool, model_name: str) -> str | None:
+    if supported:
+        return None
+    return (
+        f"Model '{model_name}' did not confirm structured-output (function-calling) support. "
+        "Methodologies needing structured outputs will degrade to a prompt-embedded JSON "
+        "contract — expect looser parsing, not a hard failure."
+    )

backend/src/researchx/adapters/search.py

@@ -0,0 +1,10 @@
+from typing import Protocol, runtime_checkable
+
+from researchx.adapters.types import PageContent, SearchResult
+
+
+@runtime_checkable
+class SearchAdapter(Protocol):
+    async def search(self, query: str, *, max_results: int = 5) -> list[SearchResult]: ...
+
+    async def fetch(self, url: str) -> PageContent: ...

backend/src/researchx/adapters/secrets.py

@@ -0,0 +1,32 @@
+from pathlib import Path
+from typing import Protocol, runtime_checkable
+
+
+@runtime_checkable
+class SecretsProvider(Protocol):
+    def resolve(self, name: str) -> str | None: ...
+
+
+def _parse_env_file(path: Path) -> dict[str, str]:
+    values: dict[str, str] = {}
+    for raw_line in path.read_text(encoding="utf-8").splitlines():
+        line = raw_line.strip()
+        if not line or line.startswith("#") or "=" not in line:
+            continue
+        key, _, value = line.partition("=")
+        values[key.strip()] = value.strip().strip("'\"")
+    return values
+
+
+class EnvFileSecretsProvider:
+    def __init__(self, paths: list[Path]) -> None:
+        self._paths = [p for p in paths if p.is_file()]
+        self._values: dict[str, str] = {}
+        for path in self._paths:
+            self._values.update(_parse_env_file(path))
+
+    def resolve(self, name: str) -> str | None:
+        return self._values.get(name)
+
+    def __repr__(self) -> str:
+        return f"EnvFileSecretsProvider(paths={[p.name for p in self._paths]})"

backend/src/researchx/adapters/storage.py

@@ -0,0 +1,11 @@
+from pathlib import Path
+from typing import Protocol, runtime_checkable
+
+
+@runtime_checkable
+class StorageAdapter(Protocol):
+    async def write_run_artifact(self, run_id: str, name: str, content: str) -> Path: ...
+
+    async def read_run_artifact(self, run_id: str, name: str) -> str: ...
+
+    def run_dir(self, run_id: str) -> Path: ...

backend/src/researchx/adapters/tavily.py

@@ -0,0 +1,87 @@
+import re
+from datetime import UTC, datetime
+
+import httpx
+
+from researchx.adapters.secrets import SecretsProvider
+from researchx.adapters.types import AdapterError, PageContent, SearchResult
+from researchx.adapters.url_guard import url_allowed
+
+_TAVILY_URL = "https://api.tavily.com/search"
+_SEARCH_TIMEOUT = 10.0
+_FETCH_TIMEOUT = 10.0
+_MAX_FETCH_REDIRECTS = 5
+_USER_AGENT = "researchx/0.2 (local research studio)"
+_TITLE_RE = re.compile(r"<title[^>]*>(.*?)</title>", re.IGNORECASE | re.DOTALL)
+_BLOCK_RE = re.compile(r"<(script|style)[^>]*>.*?</\1>", re.IGNORECASE | re.DOTALL)
+_TAG_RE = re.compile(r"<[^>]+>")
+
+
+def extract_text(html: str) -> str:
+    text = _BLOCK_RE.sub(" ", html)
+    text = _TAG_RE.sub(" ", text)
+    text = re.sub(r"\s+", " ", text)
+    return text.strip()
+
+
+def extract_title(html: str) -> str:
+    match = _TITLE_RE.search(html)
+    return match.group(1).strip() if match else ""
+
+
+class TavilySearchAdapter:
+    def __init__(self, secrets: SecretsProvider) -> None:
+        self._api_key = secrets.resolve("TAVILY_API_KEY")
+        if not self._api_key:
+            raise AdapterError("TAVILY_API_KEY not present in secrets scope")
+
+    async def search(self, query: str, *, max_results: int = 5) -> list[SearchResult]:
+        payload = {
+            "api_key": self._api_key,
+            "query": query,
+            "search_depth": "basic",
+            "max_results": max_results,
+            "include_answer": False,
+        }
+        async with httpx.AsyncClient(timeout=_SEARCH_TIMEOUT) as client:
+            response = await client.post(_TAVILY_URL, json=payload)
+            response.raise_for_status()
+            data = response.json()
+        return [
+            SearchResult(
+                title=str(entry.get("title", "")),
+                url=str(entry.get("url", "")),
+                snippet=str(entry.get("content", "")),
+            )
+            for entry in data.get("results", [])
+        ][:max_results]
+
+    async def fetch(self, url: str) -> PageContent:
+        from urllib.parse import urljoin
+
+        current = url
+        async with httpx.AsyncClient(
+            timeout=_FETCH_TIMEOUT,
+            follow_redirects=False,
+            headers={"User-Agent": _USER_AGENT},
+        ) as client:
+            for _ in range(_MAX_FETCH_REDIRECTS + 1):
+                if not url_allowed(current):
+                    raise AdapterError(
+                        "fetch refused: url not allowed (private or non-http scheme)"
+                    )
+                response = await client.get(current)
+                if 300 <= response.status_code < 400:
+                    location = response.headers.get("location")
+                    if not location:
+                        raise AdapterError("fetch failed: redirect without location")
+                    current = urljoin(current, location)
+                    continue
+                response.raise_for_status()
+                return PageContent(
+                    url=url,
+                    title=extract_title(response.text),
+                    text=extract_text(response.text),
+                    fetched_at=datetime.now(UTC),
+                )
+        raise AdapterError("fetch failed: too many redirects")

backend/src/researchx/adapters/types.py

@@ -0,0 +1,36 @@
+from datetime import datetime
+
+from pydantic import BaseModel
+
+
+class ModelMessage(BaseModel):
+    role: str
+    content: str
+
+
+class Usage(BaseModel):
+    prompt_tokens: int | None = None
+    completion_tokens: int | None = None
+
+
+class ChatResult(BaseModel):
+    content: str
+    model: str
+    usage: Usage | None = None
+
+
+class SearchResult(BaseModel):
+    title: str
+    url: str
+    snippet: str
+
+
+class PageContent(BaseModel):
+    url: str
+    title: str
+    text: str
+    fetched_at: datetime
+
+
+class AdapterError(Exception):
+    pass

backend/src/researchx/adapters/url_guard.py

@@ -0,0 +1,44 @@
+import socket
+from ipaddress import IPv4Address, IPv6Address
+from urllib.parse import urlparse
+
+
+def _host_is_private(hostname: str) -> bool:
+    try:
+        addr_info = socket.getaddrinfo(hostname, None)
+    except (socket.gaierror, UnicodeError):
+        return True
+    for family, _, _, _, sockaddr in addr_info:
+        try:
+            if family == socket.AF_INET6:
+                ip: IPv4Address | IPv6Address = IPv6Address(sockaddr[0])
+            else:
+                ip = IPv4Address(sockaddr[0])
+        except ValueError:
+            return True
+        if (
+            ip.is_private
+            or ip.is_loopback
+            or ip.is_link_local
+            or ip.is_reserved
+            or ip.is_multicast
+            or ip.is_unspecified
+        ):
+            return True
+    return False
+
+
+def url_allowed(url: str) -> bool:
+    parsed = urlparse(url)
+    if parsed.scheme not in ("http", "https"):
+        return False
+    if not parsed.hostname:
+        return False
+    return not _host_is_private(parsed.hostname)
+
+
+class FetchRefusedError(Exception):
+    pass
+
+
+__all__ = ["FetchRefusedError", "url_allowed"]

backend/src/researchx/api/app.py

@@ -0,0 +1,358 @@
+import asyncio
+from collections.abc import AsyncIterator
+from pathlib import Path
+from typing import Any
+
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel, Field, ValidationError
+from sse_starlette.sse import EventSourceResponse
+
+from researchx.adapters.capability_probe import probe_model_adapter, supports_probe
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter
+from researchx.adapters.local_storage import LocalStorageAdapter
+from researchx.adapters.types import AdapterError, ChatResult
+from researchx.engine.actor import RunActor, make_run_config
+from researchx.engine.events import EventBus, RunEvent
+from researchx.engine.run_state import Plan, RunState
+from researchx.engine.states import RunStateName
+from researchx.methodologies import registry
+
+_CANNED_PLAN = (
+    '{"sub_questions": ["What is the research question?"], '
+    '"source_universe": ["web"], "outline": ["approach", "findings", "conclusion"]}'
+)
+_CANNED_WRITER = (
+    "# Research Memo\n\n"
+    "The verified core finding [p-1]. A second corroborated observation [p-2].\n"
+)
+
+
+class CreateRunBody(BaseModel):
+    question: str = Field(min_length=1, max_length=2000)
+    context: str = Field(default="", max_length=8000)
+    methodology: str
+    dial_overrides: dict[str, Any] = Field(default_factory=dict)
+
+
+class ApproveBody(BaseModel):
+    plan: dict[str, Any] | None = None
+
+
+class RunSummary(BaseModel):
+    id: str
+    status: str
+    question: str
+    methodology: str
+    plan: dict[str, Any] | None = None
+    started_at: str
+
+
+class MethodologyCard(BaseModel):
+    slug: str
+    name: str
+    description: str
+    eta_minutes: int
+    cost_estimate: str
+    why_recommended: str
+    output_shape: str
+    dials: dict[str, Any]
+
+
+class ConfigStatus(BaseModel):
+    model_adapter: str
+    search_adapter: str
+    storage_dir: str
+    probe: dict[str, Any] | None = None
+    cost_counters: dict[str, int]
+
+
+_STATUS_MAP = {
+    RunStateName.PLANNING: "planning",
+    RunStateName.AWAITING_APPROVAL: "awaiting_approval",
+    RunStateName.SEARCHING: "searching",
+    RunStateName.EXTRACTING: "extracting",
+    RunStateName.REFLECTING: "reflecting",
+    RunStateName.SYNTHESIZING: "synthesizing",
+    RunStateName.VERIFYING: "verifying",
+    RunStateName.DONE: "done",
+    RunStateName.CANCELLED: "cancelled",
+    RunStateName.FAILED: "failed",
+}
+
+_ETA_TABLE = {"rapid-answer": (2, "low"), "deep-report": (12, "medium")}
+
+
+def _cost_estimate(slug: str) -> str:
+    depth, breadth = 1, 1
+    methodology = registry.get(slug)
+    depth = methodology.dials.depth
+    breadth = methodology.dials.breadth
+    units = depth * breadth
+    if units <= 1:
+        return "~5k tokens (estimate)"
+    if units <= 4:
+        return "~25k tokens (estimate)"
+    return "~60k tokens (estimate)"
+
+
+def _why_recommended(slug: str) -> str:
+    return {
+        "rapid-answer": "One pass, one memo — fastest path to a confident, cited answer.",
+        "deep-report": "Iterative depth with full verification — when the answer must stand up to scrutiny.",
+    }.get(slug, "Methodology-first research.")
+
+
+class RunRegistry:
+    def __init__(self) -> None:
+        self._actors: dict[str, tuple[RunActor, asyncio.Task[RunState]]] = {}
+        self._buses: dict[str, EventBus] = {}
+        self.cost_counters: dict[str, int] = {"runs_created": 0, "runs_completed": 0}
+
+    def add(self, run_id: str, actor: RunActor, task: asyncio.Task[RunState], bus: EventBus) -> None:
+        self._actors[run_id] = (actor, task)
+        self._buses[run_id] = bus
+        self.cost_counters["runs_created"] += 1
+
+    def actor(self, run_id: str) -> RunActor:
+        entry = self._actors.get(run_id)
+        if entry is None:
+            raise KeyError(run_id)
+        return entry[0]
+
+    def bus(self, run_id: str) -> EventBus:
+        bus = self._buses.get(run_id)
+        if bus is None:
+            raise KeyError(run_id)
+        return bus
+
+    def has(self, run_id: str) -> bool:
+        return run_id in self._actors
+
+    def note_completed(self) -> None:
+        self.cost_counters["runs_completed"] += 1
+
+
+def create_app(
+    *,
+    storage_dir: Path | None = None,
+    model_adapter: Any = None,
+    search_adapter: Any = None,
+) -> FastAPI:
+    app = FastAPI(title="ResearchX API", version="0.2.0")
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=["http://localhost:3000", "http://127.0.0.1:3000"],
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )
+
+    storage = LocalStorageAdapter(base_dir=storage_dir or Path.cwd() / ".researchx")
+    runs = RunRegistry()
+    model = model_adapter or FakeModelAdapter(
+        canned=[
+            ChatResult(content=_CANNED_PLAN, model="fake-planner"),
+            ChatResult(content=_CANNED_WRITER, model="fake-writer"),
+        ]
+    )
+    search = search_adapter or FakeSearchAdapter(CORPUS)
+
+    def _summary(run_id: str) -> RunSummary:
+        actor = runs.actor(run_id)
+        state = actor.state
+        return RunSummary(
+            id=run_id,
+            status=_STATUS_MAP[state.state],
+            question=state.question,
+            methodology=state.methodology_slug,
+            plan=state.plan.model_dump(mode="json") if state.plan else None,
+            started_at=state.created_at.isoformat(),
+        )
+
+    @app.get("/api/config")
+    async def config_status() -> ConfigStatus:
+        latest_probe = None
+        for run_id in list(runs._actors)[-1:]:
+            actor_probe = runs.actor(run_id).state.probe
+            latest_probe = actor_probe
+        return ConfigStatus(
+            model_adapter=type(model).__name__,
+            search_adapter=type(search).__name__,
+            storage_dir=str(storage.run_dir("00000000").parent),
+            probe=latest_probe,
+            cost_counters=runs.cost_counters,
+        )
+
+    @app.get("/api/methodologies")
+    async def methodologies() -> list[MethodologyCard]:
+        cards: list[MethodologyCard] = []
+        for methodology in registry.list():
+            eta_minutes, _ = _ETA_TABLE.get(methodology.slug, (5, "low"))
+            cards.append(
+                MethodologyCard(
+                    slug=methodology.slug,
+                    name=methodology.name,
+                    description=methodology.description,
+                    eta_minutes=eta_minutes,
+                    cost_estimate=_cost_estimate(methodology.slug),
+                    why_recommended=_why_recommended(methodology.slug),
+                    output_shape=methodology.output_shape,
+                    dials=methodology.dials.model_dump(mode="json"),
+                )
+            )
+        return cards
+
+    @app.post("/api/runs", status_code=201)
+    async def create_run(body: CreateRunBody) -> RunSummary:
+        if body.methodology not in registry:
+            raise HTTPException(status_code=404, detail="unknown methodology")
+        try:
+            run_id, config = make_run_config(
+                question=body.question,
+                context=body.context,
+                methodology_slug=body.methodology,
+                overrides=body.dial_overrides,
+                registry=registry,
+            )
+        except ValueError as exc:
+            raise HTTPException(status_code=422, detail=str(exc)) from exc
+        except ValidationError as exc:
+            raise HTTPException(status_code=422, detail="invalid dial override") from exc
+        bus = EventBus()
+        actor = RunActor(
+            run_config=config,
+            model=model,
+            search=search,
+            storage=storage,
+            registry=registry,
+            event_bus=bus,
+            on_complete=runs.note_completed,
+        )
+        probe_data: dict[str, Any] | None = None
+        if supports_probe(model):
+            try:
+                probe = await probe_model_adapter(model)
+                probe_data = probe.model_dump(mode="json")
+                await actor.attach_probe(probe_data)
+            except AdapterError:
+                probe_data = None
+
+        task = asyncio.create_task(actor.run())
+        runs.add(run_id, actor, task, bus)
+
+        async def _watch() -> None:
+            await task
+
+        asyncio.create_task(_watch())
+        return _summary(run_id)
+
+    @app.get("/api/runs/{run_id}")
+    async def get_run(run_id: str) -> RunSummary:
+        if not runs.has(run_id):
+            raise HTTPException(status_code=404, detail="run not found")
+        return _summary(run_id)
+
+    @app.post("/api/runs/{run_id}/approve")
+    async def approve_run(run_id: str, body: ApproveBody | None = None) -> RunSummary:
+        if not runs.has(run_id):
+            raise HTTPException(status_code=404, detail="run not found")
+        actor = runs.actor(run_id)
+        edited_plan: Plan | None = None
+        if body and body.plan:
+            try:
+                edited_plan = Plan.model_validate(body.plan)
+            except ValidationError:
+                raise HTTPException(status_code=422, detail="invalid plan")
+        await actor.approve(edited_plan)
+        return _summary(run_id)
+
+    @app.post("/api/runs/{run_id}/pause")
+    async def pause_run(run_id: str) -> RunSummary:
+        if not runs.has(run_id):
+            raise HTTPException(status_code=404, detail="run not found")
+        runs.actor(run_id).pause()
+        return _summary(run_id)
+
+    @app.post("/api/runs/{run_id}/resume")
+    async def resume_run(run_id: str) -> RunSummary:
+        if not runs.has(run_id):
+            raise HTTPException(status_code=404, detail="run not found")
+        runs.actor(run_id).resume()
+        return _summary(run_id)
+
+    @app.post("/api/runs/{run_id}/cancel")
+    async def cancel_run(run_id: str) -> RunSummary:
+        if not runs.has(run_id):
+            raise HTTPException(status_code=404, detail="run not found")
+        actor = runs.actor(run_id)
+        actor.cancel()
+        actor.resume()
+        return _summary(run_id)
+
+    @app.get("/api/runs/{run_id}/events")
+    async def run_events(run_id: str) -> EventSourceResponse:
+        if not runs.has(run_id):
+            raise HTTPException(status_code=404, detail="run not found")
+        bus = runs.bus(run_id)
+        actor = runs.actor(run_id)
+        terminal = {RunStateName.DONE, RunStateName.CANCELLED, RunStateName.FAILED}
+
+        async def event_stream() -> AsyncIterator[dict[str, str]]:
+            queue: asyncio.Queue[RunEvent] = asyncio.Queue()
+
+            async def forward(event: RunEvent) -> None:
+                await queue.put(event)
+
+            bus.subscribe(forward)
+            try:
+                replay = bus.replay()
+                watermark = replay[-1].seq if replay else 0
+                for prior in replay:
+                    yield {"event": prior.type, "data": prior.model_dump_json()}
+                while True:
+                    if actor.state.state in terminal:
+                        try:
+                            event = await asyncio.wait_for(queue.get(), timeout=0.5)
+                        except TimeoutError:
+                            return
+                    else:
+                        event = await queue.get()
+                    if event.seq <= watermark:
+                        continue
+                    yield {"event": event.type, "data": event.model_dump_json()}
+                    if event.type in ("run_done", "run_error"):
+                        return
+            finally:
+                bus.unsubscribe(forward)
+
+        return EventSourceResponse(event_stream())
+
+        return EventSourceResponse(event_stream())
+
+    @app.get("/api/runs/{run_id}/report")
+    async def run_report(run_id: str) -> dict[str, Any]:
+        if not runs.has(run_id):
+            raise HTTPException(status_code=404, detail="run not found")
+        try:
+            content = await storage.read_run_artifact(run_id, "report.md")
+        except AdapterError:
+            raise HTTPException(status_code=404, detail="report not ready")
+        return {"run_id": run_id, "markdown": content}
+
+    @app.get("/api/runs/{run_id}/ledger")
+    async def run_ledger(run_id: str) -> dict[str, Any]:
+        if not runs.has(run_id):
+            raise HTTPException(status_code=404, detail="run not found")
+        try:
+            content = await storage.read_run_artifact(run_id, "ledger.json")
+        except AdapterError:
+            raise HTTPException(status_code=404, detail="ledger not ready")
+        import json
+
+        data: dict[str, Any] = json.loads(content)
+        return data
+
+    return app
+
+
+app = create_app()

backend/src/researchx/api/dev_bridge.py

@@ -0,0 +1,85 @@
+"""Dev bridge: serve the FastAPI app on a loopback port for E2E tests.
+
+Prints READY on stdout once the server is listening; SIGTERM shuts
+down cleanly. Single-user, loopback-only, disposable — for tests and
+local dev. Uses an inexhaustible scripted model so many sequential
+runs work without restocking canned responses.
+"""
+
+import contextlib
+import json
+import sys
+import tempfile
+from pathlib import Path
+from typing import Any
+
+import uvicorn
+
+from researchx.adapters.fakes import CORPUS, FakeSearchAdapter
+from researchx.adapters.types import ChatResult, ModelMessage
+from researchx.api.app import create_app
+
+_HOST = "127.0.0.1"
+_PORT = 8000
+
+_PLAN = json.dumps(
+    {
+        "sub_questions": ["verification passes"],
+        "source_universe": ["web"],
+        "outline": ["approach", "findings"],
+    }
+)
+_WRITER = (
+    "# Research Memo\n\n"
+    "The verified core finding [p-1]. A corroborated observation [p-2].\n"
+)
+
+
+class EndlessModelAdapter:
+    def __init__(self) -> None:
+        self.calls = 0
+
+    async def chat(
+        self,
+        messages: list[ModelMessage],
+        *,
+        model: str,
+        temperature: float = 0.2,
+        json_mode: bool = False,
+    ) -> ChatResult:
+        del messages, temperature
+        self.calls += 1
+        if json_mode:
+            return ChatResult(content=_PLAN, model=model)
+        return ChatResult(content=_WRITER, model=model)
+
+    async def list_models(self) -> list[str]:
+        return ["endless-model"]
+
+    def roles(self) -> Any:
+        from researchx.adapters.model import ModelRoles
+
+        return ModelRoles(planner="endless-model", writer="endless-model")
+
+
+def main() -> None:
+    with tempfile.TemporaryDirectory() as tmp:
+        app = create_app(
+            storage_dir=Path(tmp),
+            model_adapter=EndlessModelAdapter(),
+            search_adapter=FakeSearchAdapter(CORPUS),
+        )
+
+        @app.on_event("startup")
+        def _announce() -> None:
+            print(f"READY port={_PORT}", flush=True)
+
+        config = uvicorn.Config(app, host=_HOST, port=_PORT, log_level="warning")
+        server = uvicorn.Server(config)
+        with contextlib.suppress(KeyboardInterrupt):
+            server.run()
+        sys.exit(0)
+
+
+if __name__ == "__main__":
+    main()

backend/src/researchx/config/dials.py

@@ -0,0 +1,111 @@
+from types import MappingProxyType
+from typing import Literal
+
+from pydantic import BaseModel, Field
+
+SourceUniverse = Literal["web", "academic", "local", "web+academic"]
+SearchRouting = Literal["single", "adaptive", "academic-only"]
+QueryStrategy = Literal["fixed", "iterative", "decomposed"]
+QualityGates = Literal["none", "standard", "strict"]
+CitationRigor = Literal["per-claim", "per-section", "per-report"]
+SynthesisStyle = Literal["memo", "executive", "encyclopedic", "adversarial"]
+OutputStructure = Literal["brief", "report", "dossier"]
+MemoryScope = Literal["none", "project", "cross-project"]
+
+
+class DialDescriptor(BaseModel, frozen=True):
+    """UI display metadata for a single dial."""
+
+    name: str
+    label: str
+    description: str
+
+
+class Dials(BaseModel, frozen=True):
+    """The 12 methodology dials with safe defaults (REQ-01)."""
+
+    source_universe: SourceUniverse = "web"
+    search_routing: SearchRouting = "single"
+    query_strategy: QueryStrategy = "decomposed"
+    breadth: int = Field(default=2, ge=1, le=5)
+    depth: int = Field(default=1, ge=1, le=3)
+    quality_gates: QualityGates = "standard"
+    citation_rigor: CitationRigor = "per-claim"
+    verification_passes: int = Field(default=1, ge=0, le=3)
+    synthesis_style: SynthesisStyle = "memo"
+    output_structure: OutputStructure = "brief"
+    memory_scope: MemoryScope = "none"
+    checkpoints: bool = False
+
+
+DIAL_REGISTRY: MappingProxyType[str, DialDescriptor] = MappingProxyType(
+    {
+        "source_universe": DialDescriptor(
+            name="source_universe",
+            label="Source universe",
+            description="Which sources may be searched: web, academic, local, or both.",
+        ),
+        "search_routing": DialDescriptor(
+            name="search_routing",
+            label="Search routing",
+            description="How queries are routed: single endpoint, adaptive, or academic-only.",
+        ),
+        "query_strategy": DialDescriptor(
+            name="query_strategy",
+            label="Query strategy",
+            description="How the question becomes queries: fixed, iterative, or decomposed.",
+        ),
+        "breadth": DialDescriptor(
+            name="breadth",
+            label="Breadth",
+            description="Number of parallel sub-question searches (1-5).",
+        ),
+        "depth": DialDescriptor(
+            name="depth",
+            label="Depth",
+            description="Number of reflection and refinement loops (1-3).",
+        ),
+        "quality_gates": DialDescriptor(
+            name="quality_gates",
+            label="Quality gates",
+            description="How strictly sources are filtered before synthesis.",
+        ),
+        "citation_rigor": DialDescriptor(
+            name="citation_rigor",
+            label="Citation rigor",
+            description="Granularity of citations: per claim, per section, or per report.",
+        ),
+        "verification_passes": DialDescriptor(
+            name="verification_passes",
+            label="Verification passes",
+            description="Post-synthesis verification passes over claims (0-3).",
+        ),
+        "synthesis_style": DialDescriptor(
+            name="synthesis_style",
+            label="Synthesis style",
+            description="Voice of the synthesized report.",
+        ),
+        "output_structure": DialDescriptor(
+            name="output_structure",
+            label="Output structure",
+            description="Shape of the final artifact: brief, report, or dossier.",
+        ),
+        "memory_scope": DialDescriptor(
+            name="memory_scope",
+            label="Memory scope",
+            description="What prior context a run may draw on.",
+        ),
+        "checkpoints": DialDescriptor(
+            name="checkpoints",
+            label="Checkpoints",
+            description="Persist intermediate state so a run can pause and resume.",
+        ),
+    }
+)
+
+
+__all__ = [
+    "DIAL_REGISTRY",
+    "DialDescriptor",
+    "Dials",
+]

backend/src/researchx/config/run_config.py

@@ -0,0 +1,49 @@
+import secrets
+from collections.abc import Mapping
+from datetime import datetime
+from typing import Any
+
+from pydantic import BaseModel, ConfigDict, Field
+
+from researchx.config.dials import Dials
+from researchx.methodologies.registry import MethodologyRegistry
+
+
+class UnknownOverrideError(ValueError):
+    """Raised when an override key is not a dial name."""
+
+
+class RunConfig(BaseModel, frozen=True):
+    """Persisted per-run snapshot of resolved dials (REQ-04)."""
+
+    run_id: str = Field(pattern=r"^[a-z0-9]{8}$")
+    methodology_slug: str
+    question: str = Field(min_length=1)
+    context: str = ""
+    resolved_dials: Dials
+    created_at: datetime
+    overrides: dict[str, Any] = Field(default_factory=dict)
+
+    model_config = ConfigDict(frozen=True)
+
+
+def resolve_dials(
+    methodology_slug: str,
+    overrides: Mapping[str, Any],
+    registry: MethodologyRegistry,
+) -> Dials:
+    """Resolve a methodology's dial bundle with validated overrides applied."""
+    bundle = registry.get(methodology_slug).dials
+    for key in overrides:
+        if key not in Dials.model_fields:
+            raise UnknownOverrideError(f"unknown dial override: {key}")
+    merged = bundle.model_dump()
+    merged.update(overrides)
+    return Dials.model_validate(merged)
+
+
+def new_run_id() -> str:
+    return secrets.token_hex(4)
+
+
+__all__ = ["RunConfig", "UnknownOverrideError", "new_run_id", "resolve_dials"]

backend/src/researchx/engine/actor.py

@@ -0,0 +1,373 @@
+import asyncio
+from collections.abc import Callable
+from datetime import UTC, datetime
+from typing import Any
+
+import httpx
+
+from researchx.adapters.local_storage import LocalStorageAdapter
+from researchx.adapters.model import ModelAdapter
+from researchx.adapters.search import SearchAdapter
+from researchx.adapters.types import AdapterError, ModelMessage
+from researchx.adapters.url_guard import url_allowed
+from researchx.config.dials import Dials
+from researchx.config.run_config import RunConfig, resolve_dials
+from researchx.engine.events import EventBus, RunEvent
+from researchx.engine.run_state import Plan, RunState
+from researchx.engine.states import RunStateName
+from researchx.evidence.store import EvidenceStore
+from researchx.methodologies import MethodologyRegistry
+from researchx.trust.ledger import build_ledger, export_checklist
+from researchx.trust.liveness import liveness_report
+
+
+class EngineError(Exception):
+    pass
+
+
+class RunActor:
+    def __init__(
+        self,
+        *,
+        run_config: RunConfig,
+        model: ModelAdapter,
+        search: SearchAdapter,
+        storage: LocalStorageAdapter,
+        registry: MethodologyRegistry,
+        event_bus: EventBus,
+        on_complete: Callable[[], None] | None = None,
+    ) -> None:
+        self._config = run_config
+        self._model = model
+        self._search = search
+        self._storage = storage
+        self._registry = registry
+        self._bus = event_bus
+        self._on_complete = on_complete
+        self._store = EvidenceStore()
+        self.state = RunState(
+            run_id=run_config.run_id,
+            question=run_config.question,
+            context=run_config.context,
+            methodology_slug=run_config.methodology_slug,
+        )
+        methodology = registry.get(run_config.methodology_slug)
+        self._dials: Dials = run_config.resolved_dials
+        self.state.depth_target = self._dials.depth
+        self._methodology = methodology
+        self._pause = asyncio.Event()
+        self._pause.set()
+        self._cancelled = False
+        self._approved = asyncio.Event()
+
+    async def _publish(self, event_type: str, data: dict[str, str] | None = None) -> None:
+        event = RunEvent(
+            type=event_type,
+            run_id=self._config.run_id,
+            data=data or {},
+        )
+        await self._bus.publish(event)
+        try:
+            await self._storage.append_run_artifact(
+                self._config.run_id,
+                "trace.jsonl",
+                event.model_dump_json() + "\n",
+            )
+        except AdapterError:
+            pass
+
+    async def _persist(self) -> None:
+        content = self._snapshot()
+        await self._storage.write_run_artifact(self._config.run_id, "state.json", content)
+
+    def _snapshot(self) -> str:
+        return self.state.model_dump_json()
+
+    async def _checkpoint(self, target: RunStateName) -> None:
+        if self.state.state != target:
+            self.state.transition(target)
+            if target is RunStateName.DONE and self._on_complete is not None:
+                self._on_complete()
+        await self._persist()
+
+    async def _wait_if_paused(self) -> None:
+        await self._pause.wait()
+
+    def pause(self) -> None:
+        self._pause.clear()
+
+    def resume(self) -> None:
+        self._pause.set()
+
+    def cancel(self) -> None:
+        self._cancelled = True
+
+    async def approve(self, plan: Plan | None = None) -> None:
+        if plan is not None:
+            self.state.plan = plan
+        self._approved.set()
+
+    async def run(self) -> RunState:
+        await self._publish("run_started", {"question": self._config.question})
+        try:
+            await self._execute()
+        except asyncio.CancelledError:
+            await asyncio.shield(self._persist_cancelled())
+            raise
+        except AdapterError as exc:
+            await self._fail(str(exc))
+            raise EngineError(str(exc)) from exc
+        except httpx.HTTPError as exc:
+            await self._fail(f"network error ({type(exc).__name__})")
+            raise EngineError(f"network error ({type(exc).__name__})") from exc
+        except EngineError:
+            await self._fail("engine error")
+            raise
+        except Exception as exc:
+            await self._fail(f"unexpected engine failure ({type(exc).__name__})")
+            raise EngineError(f"unexpected engine failure ({type(exc).__name__})") from exc
+        return self.state
+
+    async def attach_probe(self, probe_data: dict[str, Any]) -> None:
+        self.state.probe = probe_data
+        await self._persist()
+        await self._publish("probe_attached", {"endpoint": str(probe_data.get("endpoint", ""))})
+
+    async def _persist_cancelled(self) -> None:
+        self.state.state = RunStateName.CANCELLED
+        await self._persist()
+
+    async def _fail(self, message: str) -> None:
+        await self._publish("run_error", {"message": message})
+        self.state.state = RunStateName.FAILED
+        await asyncio.shield(self._persist())
+
+    async def _execute(self) -> None:
+        current = self.state.state
+        if current == RunStateName.PLANNING:
+            await self._planning_phase()
+        elif current == RunStateName.AWAITING_APPROVAL:
+            pass
+        elif current in (
+            RunStateName.SEARCHING,
+            RunStateName.EXTRACTING,
+            RunStateName.REFLECTING,
+            RunStateName.SYNTHESIZING,
+        ):
+            await self._research_phase()
+            await self._verify_phase()
+            return
+        elif current == RunStateName.VERIFYING:
+            await self._verify_phase()
+            return
+        else:
+            raise EngineError(f"cannot resume from state {current}")
+        await self._approval_phase()
+        await self._research_phase()
+        await self._verify_phase()
+
+    async def _planning_phase(self) -> None:
+        await self._checkpoint(RunStateName.PLANNING)
+        await self._wait_if_paused()
+        if self._cancelled:
+            await self._persist_cancelled()
+            raise asyncio.CancelledError
+        prompt = self._methodology.planner_prompt.format(
+            question=self._config.question, context=self._config.context
+        )
+        result = await self._model.chat(
+            [ModelMessage(role="user", content=prompt)],
+            model=self._model.roles().planner,
+            json_mode=True,
+        )
+        plan = self._parse_plan(result.content)
+        self.state.plan = plan
+        await self._publish("state_changed", {"state": "AWAITING_APPROVAL"})
+
+    def _parse_plan(self, raw: str) -> Plan:
+        import json
+
+        try:
+            data = json.loads(raw)
+        except json.JSONDecodeError as exc:
+            raise AdapterError("planner returned non-JSON plan") from exc
+        if not isinstance(data, dict):
+            raise AdapterError("planner plan is not a JSON object")
+        sub_questions = data.get("sub_questions", [])
+        source_universe = data.get("source_universe", [])
+        outline = data.get("outline", [])
+        if not (
+            isinstance(sub_questions, list)
+            and isinstance(source_universe, list)
+            and isinstance(outline, list)
+        ):
+            raise AdapterError("planner plan has malformed lists")
+        return Plan(
+            sub_questions=[str(q) for q in sub_questions if isinstance(q, str)],
+            source_universe=[str(u) for u in source_universe if isinstance(u, str)],
+            outline=[str(o) for o in outline if isinstance(o, str)],
+        )
+
+    async def _approval_phase(self) -> None:
+        await self._checkpoint(RunStateName.AWAITING_APPROVAL)
+        while not self._approved.is_set():
+            if self._cancelled:
+                await self._persist_cancelled()
+                raise asyncio.CancelledError
+            try:
+                await asyncio.wait_for(self._approved.wait(), timeout=0.1)
+            except TimeoutError:
+                continue
+        await self._checkpoint(RunStateName.SEARCHING)
+
+    async def _research_phase(self) -> None:
+        while True:
+            await self._check_cancelled()
+            await self._searching_step()
+            await self._extracting_step()
+            if self.state.depth_cursor + 1 >= self.state.depth_target:
+                break
+            await self._reflecting_step()
+            self.state.depth_cursor += 1
+            await self._persist()
+        await self._synthesizing_step()
+
+    async def _check_cancelled(self) -> None:
+        if self._cancelled:
+            await self._persist_cancelled()
+            raise asyncio.CancelledError
+
+    async def _searching_step(self) -> None:
+        if not self.state.plan or not self.state.plan.sub_questions:
+            await self._checkpoint(RunStateName.SEARCHING)
+            return
+        await self._checkpoint(RunStateName.SEARCHING)
+        await self._wait_if_paused()
+        for sub_question in self.state.plan.sub_questions[: self._dials.breadth]:
+            await self._publish("query_fired", {"query": sub_question})
+            self.state.bump("queries")
+            results = await self._search.search(sub_question, max_results=3)
+            for result in results:
+                await self._publish(
+                    "source_found",
+                    {"url": result.url, "title": result.title},
+                )
+
+    async def _extracting_step(self) -> None:
+        await self._checkpoint(RunStateName.EXTRACTING)
+        await self._wait_if_paused()
+        if not self.state.plan:
+            return
+        for sub_question in self.state.plan.sub_questions[: self._dials.breadth]:
+            results = await self._search.search(sub_question, max_results=3)
+            for result in results:
+                if not url_allowed(result.url):
+                    await self._publish("source_refused", {"url": result.url})
+                    continue
+                try:
+                    page = await self._search.fetch(result.url)
+                except (AdapterError, httpx.HTTPError):
+                    continue
+                self._store.add_page(page.url, page.title, page.text)
+                await self._publish(
+                    "source_visited",
+                    {"url": page.url, "title": page.title},
+                )
+                self.state.bump("pages")
+                for passage in self._store.passages_for_url(page.url):
+                    await self._publish(
+                        "passage_extracted",
+                        {"passage_id": passage.passage_id, "url": passage.url},
+                    )
+                    self.state.bump("passages")
+
+    async def _reflecting_step(self) -> None:
+        await self._checkpoint(RunStateName.REFLECTING)
+        await self._wait_if_paused()
+        prompt = self._methodology.planner_prompt.format(
+            question=self._config.question, context=self._config.context
+        )
+        result = await self._model.chat(
+            [ModelMessage(role="user", content=prompt)],
+            model=self._model.roles().planner,
+            json_mode=True,
+        )
+        if self.state.plan:
+            refined = self._parse_plan(result.content)
+            self.state.plan = refined
+
+    async def _synthesizing_step(self) -> None:
+        await self._checkpoint(RunStateName.SYNTHESIZING)
+        await self._wait_if_paused()
+        await self._check_cancelled()
+        context_block = "\n\n".join(
+            f"[{p.passage_id}] ({p.url}) {p.text}" for p in self._store.writer_context()
+        )
+        prompt = self._methodology.render_writer_prompt(
+            question=self._config.question,
+            context=self._config.context or "(none)",
+            plan=self.state.plan.model_dump_json() if self.state.plan else "{}",
+            evidence=context_block or "(no evidence collected)",
+        )
+        result = await self._model.chat(
+            [ModelMessage(role="user", content=prompt)],
+            model=self._model.roles().writer,
+        )
+        report = result.content
+        await self._storage.write_run_artifact(self._config.run_id, "report.md", report)
+        self.state.bump("writer_calls")
+
+    async def _verify_phase(self) -> None:
+        await self._checkpoint(RunStateName.VERIFYING)
+        report = await self._storage.read_run_artifact(self._config.run_id, "report.md")
+        liveness = await liveness_report(self._cited_urls(report))
+        ledger = build_ledger(
+            run_id=self._config.run_id,
+            report_text=report,
+            evidence=self._store,
+            liveness=liveness,
+            visited_at=datetime.now(UTC),
+        )
+        await self._storage.write_run_artifact(
+            self._config.run_id, "ledger.json", ledger.model_dump_json(indent=2)
+        )
+        checklist = export_checklist(ledger)
+        await self._storage.write_run_artifact(self._config.run_id, "checklist.md", checklist)
+        await self._checkpoint(RunStateName.DONE)
+        await self._publish("run_done", {"run_id": self._config.run_id})
+
+    def _cited_urls(self, report_text: str) -> list[str]:
+        import re
+
+        pattern = re.compile(r"\[p-(\d+)\]")
+        cited: list[str] = []
+        for match in pattern.finditer(report_text):
+            passage = self._store.get(f"p-{match.group(1)}")
+            if passage and passage.url not in cited:
+                cited.append(passage.url)
+        return cited
+
+
+def make_run_config(
+    *,
+    question: str,
+    context: str,
+    methodology_slug: str,
+    overrides: dict[str, object],
+    registry: MethodologyRegistry,
+    run_id: str | None = None,
+) -> tuple[str, RunConfig]:
+    from researchx.adapters.local_storage import generate_run_id
+
+    rid = run_id or generate_run_id()
+    dials = resolve_dials(methodology_slug, overrides, registry)
+    config = RunConfig(
+        run_id=rid,
+        methodology_slug=methodology_slug,
+        question=question,
+        context=context,
+        resolved_dials=dials,
+        overrides=dict(overrides),
+        created_at=datetime.now(UTC),
+    )
+    return rid, config

backend/src/researchx/engine/demo.py

@@ -0,0 +1,68 @@
+import asyncio
+import tempfile
+from pathlib import Path
+
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter
+from researchx.adapters.local_storage import LocalStorageAdapter
+from researchx.adapters.types import ChatResult
+from researchx.engine.actor import RunActor, make_run_config
+from researchx.engine.events import EventBus
+from researchx.methodologies import registry
+
+
+async def main() -> None:
+    with tempfile.TemporaryDirectory() as tmp:
+        base = Path(tmp)
+        run_id, config = make_run_config(
+            question="How do verification pipelines keep citations honest?",
+            context="",
+            methodology_slug="rapid-answer",
+            overrides={},
+            registry=registry,
+        )
+        plan = (
+            '{"sub_questions": ["verification passes", "quote anchoring"], '
+            '"source_universe": ["web"], "outline": ["intro", "findings"]}'
+        )
+        writer = (
+            "# Research Report\n\n"
+            "The verification pass re-anchored every quoted claim [p-1] "
+            "before the report shipped [p-2].\n"
+        )
+        model = FakeModelAdapter(
+            canned=[
+                ChatResult(content=plan, model="fake-planner"),
+                ChatResult(content=writer, model="fake-writer"),
+            ]
+        )
+        search = FakeSearchAdapter(CORPUS)
+        storage = LocalStorageAdapter(base_dir=base)
+        bus = EventBus()
+        actor = RunActor(
+            run_config=config, model=model, search=search, storage=storage, registry=registry,
+            event_bus=bus,
+        )
+        task = asyncio.create_task(actor.run())
+        while actor.state.state.value == "PLANNING":
+            await asyncio.sleep(0.01)
+        await actor.approve()
+        await task
+
+        state = (storage.run_dir(run_id) / "state.json").read_text()
+        report = (storage.run_dir(run_id) / "report.md").read_text()
+        ledger = (storage.run_dir(run_id) / "ledger.json").read_text()
+        checklist = (storage.run_dir(run_id) / "checklist.md").read_text()
+        print(f"run {run_id} → {actor.state.state.value}")
+        print(f"artifacts under {storage.run_dir(run_id)}:")
+        for name, content in [
+            ("state.json", state),
+            ("report.md", report),
+            ("ledger.json", ledger),
+            ("checklist.md", checklist),
+        ]:
+            print(f"--- {name} ({len(content)} chars) ---")
+        print(f"events: {len(bus.replay())}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

backend/src/researchx/engine/events.py

@@ -0,0 +1,49 @@
+from collections.abc import Awaitable, Callable
+from datetime import UTC, datetime
+from typing import Literal
+
+from pydantic import BaseModel, Field
+
+
+class RunEvent(BaseModel):
+    type: str
+    run_id: str
+    at: datetime = Field(default_factory=lambda: datetime.now(UTC))
+    data: dict[str, str] = {}
+    seq: int = 0
+
+
+class EventBus:
+    def __init__(self) -> None:
+        self._subscribers: list[Callable[[RunEvent], Awaitable[None]]] = []
+        self._log: list[RunEvent] = []
+        self._seq = 0
+
+    def subscribe(self, handler: Callable[[RunEvent], Awaitable[None]]) -> None:
+        self._subscribers.append(handler)
+
+    def unsubscribe(self, handler: Callable[[RunEvent], Awaitable[None]]) -> None:
+        if handler in self._subscribers:
+            self._subscribers.remove(handler)
+
+    async def publish(self, event: RunEvent) -> None:
+        self._seq += 1
+        event.seq = self._seq
+        self._log.append(event)
+        for handler in self._subscribers:
+            await handler(event)
+
+    def replay(self, after_seq: int = 0) -> list[RunEvent]:
+        return [e for e in self._log if e.seq > after_seq]
+
+
+class TraceWriter:
+    def __init__(self, emit: Callable[[str], None]) -> None:
+        self._emit = emit
+
+    async def record(self, event: RunEvent) -> None:
+        self._emit(event.model_dump_json())
+
+
+def event_type_of(event: RunEvent) -> Literal["run_started", "other"]:
+    return "run_started" if event.type == "run_started" else "other"

backend/src/researchx/engine/run_state.py

@@ -0,0 +1,36 @@
+from datetime import UTC, datetime
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+from researchx.engine.states import RunStateName, can_transition
+
+
+class Plan(BaseModel):
+    sub_questions: list[str] = Field(default_factory=list)
+    source_universe: list[str] = Field(default_factory=list)
+    outline: list[str] = Field(default_factory=list)
+
+
+class RunState(BaseModel):
+    run_id: str
+    question: str
+    context: str = ""
+    methodology_slug: str
+    state: RunStateName = RunStateName.PLANNING
+    plan: Plan | None = None
+    depth_cursor: int = 0
+    depth_target: int = 1
+    counters: dict[str, int] = Field(default_factory=dict)
+    probe: dict[str, Any] | None = None
+    created_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
+    updated_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
+
+    def transition(self, target: RunStateName) -> None:
+        if not can_transition(self.state, target):
+            raise ValueError(f"illegal transition: {self.state} -> {target}")
+        self.state = target
+        self.updated_at = datetime.now(UTC)
+
+    def bump(self, key: str) -> None:
+        self.counters[key] = self.counters.get(key, 0) + 1

backend/src/researchx/engine/states.py

@@ -0,0 +1,65 @@
+from enum import StrEnum
+
+
+class RunStateName(StrEnum):
+    PLANNING = "PLANNING"
+    AWAITING_APPROVAL = "AWAITING_APPROVAL"
+    SEARCHING = "SEARCHING"
+    EXTRACTING = "EXTRACTING"
+    REFLECTING = "REFLECTING"
+    SYNTHESIZING = "SYNTHESIZING"
+    VERIFYING = "VERIFYING"
+    DONE = "DONE"
+    CANCELLED = "CANCELLED"
+    FAILED = "FAILED"
+
+
+_LEGAL_TRANSITIONS: dict[RunStateName, set[RunStateName]] = {
+    RunStateName.PLANNING: {RunStateName.AWAITING_APPROVAL, RunStateName.FAILED},
+    RunStateName.AWAITING_APPROVAL: {
+        RunStateName.SEARCHING,
+        RunStateName.CANCELLED,
+        RunStateName.FAILED,
+    },
+    RunStateName.SEARCHING: {
+        RunStateName.EXTRACTING,
+        RunStateName.SYNTHESIZING,
+        RunStateName.CANCELLED,
+        RunStateName.FAILED,
+    },
+    RunStateName.EXTRACTING: {
+        RunStateName.REFLECTING,
+        RunStateName.SYNTHESIZING,
+        RunStateName.CANCELLED,
+        RunStateName.FAILED,
+    },
+    RunStateName.REFLECTING: {
+        RunStateName.SEARCHING,
+        RunStateName.SYNTHESIZING,
+        RunStateName.CANCELLED,
+        RunStateName.FAILED,
+    },
+    RunStateName.SYNTHESIZING: {
+        RunStateName.VERIFYING,
+        RunStateName.CANCELLED,
+        RunStateName.FAILED,
+    },
+    RunStateName.VERIFYING: {
+        RunStateName.DONE,
+        RunStateName.CANCELLED,
+        RunStateName.FAILED,
+    },
+    RunStateName.DONE: set(),
+    RunStateName.CANCELLED: set(),
+    RunStateName.FAILED: set(),
+}
+
+TERMINAL_STATES = {
+    RunStateName.DONE,
+    RunStateName.CANCELLED,
+    RunStateName.FAILED,
+}
+
+
+def can_transition(current: RunStateName, target: RunStateName) -> bool:
+    return target in _LEGAL_TRANSITIONS[current]

backend/src/researchx/evidence/store.py

@@ -0,0 +1,70 @@
+from pydantic import BaseModel, Field
+
+
+class Passage(BaseModel):
+    passage_id: str
+    url: str
+    quote: str
+    text: str
+
+
+class VisitedPage(BaseModel):
+    url: str
+    title: str
+    passage_ids: list[str] = Field(default_factory=list)
+
+
+def extract_passages(text: str, *, min_chars: int = 120) -> list[str]:
+    paragraphs = [p.strip() for p in text.split("\n") if p.strip()]
+    return [p for p in paragraphs if len(p) >= min_chars]
+
+
+class EvidenceStore:
+    def __init__(self) -> None:
+        self._passages: dict[str, Passage] = {}
+        self._pages: dict[str, VisitedPage] = {}
+        self._seen_quotes: set[str] = set()
+        self._counter = 0
+
+    def add_page(self, url: str, title: str, text: str) -> VisitedPage:
+        page = self._pages.setdefault(url, VisitedPage(url=url, title=title))
+        for paragraph in extract_passages(text):
+            self.add_passage(url, paragraph)
+        return page
+
+    def add_passage(self, url: str, text: str) -> Passage:
+        self._counter += 1
+        passage_id = f"p-{self._counter}"
+        passage = Passage(passage_id=passage_id, url=url, quote=text[:200], text=text)
+        self._passages[passage_id] = passage
+        page = self._pages.get(url)
+        if page is None:
+            page = VisitedPage(url=url, title="")
+            self._pages[url] = page
+        page.passage_ids.append(passage_id)
+        self._seen_quotes.add(text[:200])
+        return passage
+
+    def has_seen(self, quote: str) -> bool:
+        return quote[:200] in self._seen_quotes
+
+    def get(self, passage_id: str) -> Passage | None:
+        return self._passages.get(passage_id)
+
+    def passages_for_url(self, url: str) -> list[Passage]:
+        page = self._pages.get(url)
+        if page is None:
+            return []
+        return [self._passages[pid] for pid in page.passage_ids if pid in self._passages]
+
+    def writer_context(self) -> list[Passage]:
+        return [self._passages[pid] for pid in sorted(self._passages, key=self._passage_order)]
+
+    def _passage_order(self, passage_id: str) -> int:
+        return int(passage_id.split("-")[1])
+
+    def pages(self) -> list[VisitedPage]:
+        return list(self._pages.values())
+
+    def __len__(self) -> int:
+        return len(self._passages)

backend/src/researchx/methodologies/__init__.py

@@ -0,0 +1,9 @@
+from researchx.methodologies.builtin import registry
+from researchx.methodologies.models import Methodology
+from researchx.methodologies.registry import MethodologyRegistry
+
+__all__ = [
+    "Methodology",
+    "MethodologyRegistry",
+    "registry",
+]

backend/src/researchx/methodologies/builtin.py

@@ -0,0 +1,97 @@
+from researchx.config.dials import Dials
+from researchx.methodologies.models import Methodology
+from researchx.methodologies.registry import MethodologyRegistry
+
+_RAPID_PLANNER_PROMPT = (
+    "You are a rapid research planner. Decompose the user's question into the fewest "
+    "focused sub-questions that yield a confident answer.\n"
+    "Question: {question}\n"
+    "Context: {context}"
+)
+
+_RAPID_WRITER_PROMPT = (
+    "You are a rapid memo writer. Answer the question directly in a short memo.\n"
+    "Cite a source per claim using the passage markers [p-N]. Every cited quote must "
+    "come verbatim from the evidence passages listed below and from nowhere else.\n"
+    "Question: {question}\n"
+    "Context: {context}\n"
+    "Plan: {plan}\n"
+    "Evidence passages:\n{evidence}"
+)
+
+_DEEP_PLANNER_PROMPT = (
+    "You are a deep research planner. Decompose the user's question into two "
+    "sub-questions, then propose an outline for an executive report with "
+    "sections, each mapped to the sub-questions it answers.\n"
+    "Question: {question}\n"
+    "Context: {context}"
+)
+
+_DEEP_WRITER_PROMPT = (
+    "You are an executive report writer. Synthesize the evidence into a structured "
+    "executive report following the plan: executive summary, findings, risks, and "
+    "recommendations.\n"
+    "Cite a source per claim using the passage markers [p-N]. Every cited quote must "
+    "come verbatim from the evidence passages listed below and from nowhere else.\n"
+    "Question: {question}\n"
+    "Context: {context}\n"
+    "Plan: {plan}\n"
+    "Evidence passages:\n{evidence}"
+)
+
+_BUILTIN: dict[str, Methodology] = {
+    "rapid-answer": Methodology(
+        slug="rapid-answer",
+        name="Rapid Answer",
+        description=(
+            "One search pass, one synthesis pass: a short cited memo for questions "
+            "that need a confident answer fast."
+        ),
+        dials=Dials(
+            source_universe="web",
+            search_routing="single",
+            query_strategy="decomposed",
+            breadth=1,
+            depth=1,
+            quality_gates="standard",
+            citation_rigor="per-claim",
+            verification_passes=1,
+            synthesis_style="memo",
+            output_structure="brief",
+            memory_scope="none",
+            checkpoints=False,
+        ),
+        planner_prompt=_RAPID_PLANNER_PROMPT,
+        writer_prompt=_RAPID_WRITER_PROMPT,
+        output_shape="memo",
+    ),
+    "deep-report": Methodology(
+        slug="deep-report",
+        name="Deep Report",
+        description=(
+            "Full-depth research: iterative sub-questions, reflective refinement, and "
+            "a verified executive report with per-claim citations."
+        ),
+        dials=Dials(
+            source_universe="web+academic",
+            search_routing="adaptive",
+            query_strategy="decomposed",
+            breadth=2,
+            depth=3,
+            quality_gates="strict",
+            citation_rigor="per-claim",
+            verification_passes=2,
+            synthesis_style="executive",
+            output_structure="report",
+            memory_scope="none",
+            checkpoints=True,
+        ),
+        planner_prompt=_DEEP_PLANNER_PROMPT,
+        writer_prompt=_DEEP_WRITER_PROMPT,
+        output_shape="executive-report",
+    ),
+}
+
+registry = MethodologyRegistry(_BUILTIN)
+
+__all__ = ["registry"]

backend/src/researchx/methodologies/models.py

@@ -0,0 +1,32 @@
+from typing import Literal
+
+from pydantic import BaseModel, Field
+
+from researchx.config.dials import Dials
+
+OutputShape = Literal["memo", "executive-report"]
+
+
+class Methodology(BaseModel, frozen=True):
+    """A named research methodology: a dial bundle plus prompt templates (REQ-02)."""
+
+    slug: str = Field(pattern=r"^[a-z0-9]+(-[a-z0-9]+)*$")
+    name: str
+    description: str
+    dials: Dials
+    planner_prompt: str
+    writer_prompt: str
+    output_shape: OutputShape
+
+    def render_planner_prompt(self, question: str, context: str) -> str:
+        return self.planner_prompt.format(question=question, context=context)
+
+    def render_writer_prompt(
+        self, question: str, context: str, plan: str, evidence: str
+    ) -> str:
+        return self.writer_prompt.format(
+            question=question, context=context, plan=plan, evidence=evidence
+        )
+
+
+__all__ = ["Methodology", "OutputShape"]

backend/src/researchx/methodologies/registry.py

@@ -0,0 +1,26 @@
+from collections.abc import Mapping
+
+from researchx.methodologies.models import Methodology
+
+
+class MethodologyRegistry:
+    """Frozen by-slug registry that hands out immutable copies (REQ-02/REQ-03)."""
+
+    def __init__(self, methodologies: Mapping[str, Methodology]) -> None:
+        self._methodologies: dict[str, Methodology] = dict(methodologies)
+
+    def get(self, slug: str) -> Methodology:
+        return self._methodologies[slug].model_copy(deep=True)
+
+    def list(self) -> list[Methodology]:
+        ordered = sorted(self._methodologies.values(), key=lambda m: m.name)
+        return [m.model_copy(deep=True) for m in ordered]
+
+    def __contains__(self, slug: str) -> bool:
+        return slug in self._methodologies
+
+    def __len__(self) -> int:
+        return len(self._methodologies)
+
+
+__all__ = ["MethodologyRegistry"]

backend/src/researchx/trust/anchoring.py

@@ -0,0 +1,89 @@
+import re
+import unicodedata
+from difflib import SequenceMatcher
+
+from pydantic import BaseModel
+
+from researchx.evidence.store import EvidenceStore, Passage
+
+ANCHOR_THRESHOLD = 0.85
+WEAK_MATCH_MIN = 0.80
+
+
+def normalize(text: str) -> str:
+    nfc = unicodedata.normalize("NFC", text)
+    collapsed = re.sub(r"\s+", " ", nfc)
+    return collapsed.casefold().strip()
+
+
+class AnchorVerdict(BaseModel):
+    quote: str
+    passage_id: str | None
+    ratio: float
+    matched: bool
+    weak: bool
+
+
+def anchor_quote(quote: str, passages: list[Passage]) -> AnchorVerdict:
+    normalized_quote = normalize(quote)
+    best_ratio = 0.0
+    best_id: str | None = None
+    for passage in passages:
+        normalized_passage = normalize(passage.text)
+        if normalized_quote and normalized_quote in normalized_passage:
+            return AnchorVerdict(
+                quote=quote, passage_id=passage.passage_id, ratio=1.0, matched=True, weak=False
+            )
+        ratio = SequenceMatcher(None, normalized_quote, normalized_passage).ratio()
+        if ratio > best_ratio:
+            best_ratio = ratio
+            best_id = passage.passage_id
+    matched = best_ratio >= ANCHOR_THRESHOLD
+    weak = WEAK_MATCH_MIN <= best_ratio < ANCHOR_THRESHOLD
+    return AnchorVerdict(
+        quote=quote,
+        passage_id=best_id if (matched or weak) else None,
+        ratio=round(best_ratio, 4),
+        matched=matched,
+        weak=weak,
+    )
+
+
+_MARKER_RE = re.compile(r"\[p-(\d+)\]")
+_HEADER_RE = re.compile(r"^#{1,6}\s.*$", re.MULTILINE)
+
+
+def _claim_fragment(before: str) -> str:
+    cleaned = _HEADER_RE.sub("", before).rstrip()
+    fragment_start = max(
+        cleaned.rfind("."), cleaned.rfind("!"), cleaned.rfind("?"), cleaned.rfind("\n")
+    )
+    quote_text = cleaned[fragment_start + 1 :].strip(" \t>\"'*-")
+    if not quote_text:
+        quote_text = cleaned[-200:].strip(" \t>\"'*-")
+    return quote_text
+
+
+def extract_report_claims(report_text: str) -> list[tuple[str, str]]:
+    """Extract (passage_id, quote_text) claims from the report.
+
+    The quote text is what the WRITER actually wrote adjacent to the
+    citation marker — the last sentence fragment before each [p-N]
+    marker — NOT the stored passage's own text. This is the adversarial
+    core of REQ-20: a fabricated quote riding a real passage ID must
+    be visible to the anchorer.
+    """
+    claims: list[tuple[str, str]] = []
+    for match in _MARKER_RE.finditer(report_text):
+        passage_id = f"p-{match.group(1)}"
+        quote_text = _claim_fragment(report_text[: match.start()])
+        claims.append((passage_id, quote_text))
+    return claims
+
+
+def extract_quotes_from_report(report_text: str, evidence: EvidenceStore) -> list[str]:
+    return [quote for _pid, quote in extract_report_claims(report_text) if evidence.get(_pid)]
+
+
+def extract_cited_passage_ids(report_text: str) -> list[str]:
+    return [f"p-{m.group(1)}" for m in _MARKER_RE.finditer(report_text)]

backend/src/researchx/trust/ledger.py

@@ -0,0 +1,208 @@
+import re
+from datetime import datetime
+
+from pydantic import BaseModel
+
+from researchx.evidence.store import EvidenceStore, Passage
+from researchx.trust.anchoring import (
+    anchor_quote,
+    extract_cited_passage_ids,
+    extract_report_claims,
+    normalize,
+)
+from researchx.trust.liveness import LivenessStatus
+
+_AUTHORITY_TIERS: dict[str, str] = {
+    "example.org": "reference",
+    "gov": "official",
+    "edu": "academic",
+    "org": "reference",
+    "com": "general",
+}
+
+
+def authority_tier(url: str) -> str:
+    host = re.sub(r"^https?://", "", url).split("/")[0].lower().split(":")[0]
+    labels = host.split(".")
+    for suffix, tier in _AUTHORITY_TIERS.items():
+        if labels[-1] == suffix or (len(labels) > 1 and labels[-2] == suffix):
+            return tier
+    return "general"
+
+
+class CitationEntry(BaseModel):
+    url: str
+    visited_at: datetime
+    passages: list[str]
+    claims_supported: int
+    health: str
+    authority_tier: str
+
+
+class VerificationChecklist(BaseModel):
+    run_id: str
+    citations_checked: int
+    live: int
+    stale: int
+    dead: int
+    anchored_claims: int
+    unanchored_claims: int
+    weak_matches: int
+    confidence_labels: dict[str, str]
+    liveness_ratio: float
+
+
+class CitationLedger(BaseModel):
+    run_id: str
+    generated_at: datetime
+    entries: list[CitationEntry]
+    checklist: VerificationChecklist
+
+
+_CLAIM_RE = re.compile(r"\[p-(\d+)\]")
+
+
+def _claims_per_passage(report_text: str) -> dict[str, int]:
+    counts: dict[str, int] = {}
+    for match in _CLAIM_RE.finditer(report_text):
+        pid = f"p-{match.group(1)}"
+        counts[pid] = counts.get(pid, 0) + 1
+    return counts
+
+
+def build_ledger(
+    *,
+    run_id: str,
+    report_text: str,
+    evidence: EvidenceStore,
+    liveness: dict[str, LivenessStatus],
+    visited_at: datetime,
+) -> CitationLedger:
+    claims = _claims_per_passage(report_text)
+    all_passages = evidence.writer_context()
+    report_claims = extract_report_claims(report_text)
+    cited_ids = extract_cited_passage_ids(report_text)
+    known_ids = {p.passage_id for p in all_passages}
+    cited_urls: list[str] = []
+    entries: list[CitationEntry] = []
+    anchored = 0
+    unanchored = 0
+    weak = 0
+    confidence: dict[str, str] = {}
+
+    for passage_id, writer_quote in report_claims:
+        passage = evidence.get(passage_id)
+        if passage is None:
+            unanchored += 1
+            continue
+        verdict = anchor_quote(writer_quote, [passage])
+        if verdict.matched:
+            anchored += 1
+        elif verdict.weak:
+            weak += 1
+        else:
+            unanchored += 1
+
+    for cited_id in cited_ids:
+        if cited_id not in known_ids:
+            unanchored += 1
+        passage = evidence.get(cited_id)
+        if passage is not None and passage.url not in cited_urls:
+            cited_urls.append(passage.url)
+
+    for page in evidence.pages():
+        if page.url not in cited_urls:
+            continue
+        passages = evidence.passages_for_url(page.url)
+        passage_ids = [p.passage_id for p in passages]
+        page_claims = sum(claims.get(pid, 0) for pid in passage_ids)
+        health = str(liveness.get(page.url, LivenessStatus.DEAD))
+        entries.append(
+            CitationEntry(
+                url=page.url,
+                visited_at=visited_at,
+                passages=passage_ids,
+                claims_supported=page_claims,
+                health=health,
+                authority_tier=authority_tier(page.url),
+            )
+        )
+        for passage in passages:
+            confidence[passage.passage_id] = (
+                "corroborated" if _corroborated(passage, evidence) else "single-source"
+            )
+
+    live = sum(1 for e in entries if e.health == "live")
+    stale = sum(1 for e in entries if e.health == "stale")
+    dead = sum(1 for e in entries if e.health == "dead")
+    total = len(entries)
+    ratio = round(live / total, 4) if total > 0 else 1.0
+    checklist = VerificationChecklist(
+        run_id=run_id,
+        citations_checked=total,
+        live=live,
+        stale=stale,
+        dead=dead,
+        anchored_claims=anchored,
+        unanchored_claims=unanchored,
+        weak_matches=weak,
+        confidence_labels=confidence,
+        liveness_ratio=ratio,
+    )
+    return CitationLedger(
+        run_id=run_id, generated_at=visited_at, entries=entries, checklist=checklist
+    )
+
+
+def _corroborated(passage: Passage, evidence: EvidenceStore) -> bool:
+    normalized = normalize(passage.text)
+    for other in evidence.writer_context():
+        if other.passage_id == passage.passage_id:
+            continue
+        if normalized in normalize(other.text):
+            return True
+    return False
+
+
+LIVENESS_EXPORT_GATE = 0.99
+
+
+def liveness_export_gate(ledger: CitationLedger) -> tuple[bool, list[str]]:
+    failures = [e.url for e in ledger.entries if e.health != "live"]
+    liveness_ok = ledger.checklist.liveness_ratio >= LIVENESS_EXPORT_GATE
+    anchoring_ok = ledger.checklist.unanchored_claims == 0
+    return liveness_ok and anchoring_ok, failures
+
+
+def export_checklist(ledger: CitationLedger) -> str:
+    gate_passed, failures = liveness_export_gate(ledger)
+    lines = [
+        "# Verification Checklist",
+        "",
+        f"Run: {ledger.run_id}",
+        f"Citations checked: {ledger.checklist.citations_checked}",
+        f"Live: {ledger.checklist.live} / Stale: {ledger.checklist.stale} / Dead: {ledger.checklist.dead}",
+        (
+            f"Liveness ratio: {ledger.checklist.liveness_ratio} (export gate >= {LIVENESS_EXPORT_GATE}: "
+            f"{'PASS' if gate_passed else 'FAIL'})"
+        ),
+        (
+            f"Anchoring gate: {'PASS' if ledger.checklist.unanchored_claims == 0 else 'FAIL'} "
+            f"({ledger.checklist.unanchored_claims} unanchored)"
+        ),
+        f"Anchored claims: {ledger.checklist.anchored_claims}",
+        f"Unanchored claims: {ledger.checklist.unanchored_claims}",
+        f"Weak matches (flagged, not accepted): {ledger.checklist.weak_matches}",
+        "",
+        "## Per-URL ledger",
+        "",
+    ]
+    for entry in ledger.entries:
+        lines.append(
+            f"- {entry.url} — health: {entry.health}, tier: {entry.authority_tier}, "
+            f"passages: {len(entry.passages)}, claims: {entry.claims_supported}"
+        )
+    if failures:
+        lines += ["", "## Liveness failures", ""]
+        lines += [f"- {url}" for url in failures]
+    return "\n".join(lines) + "\n"

backend/src/researchx/trust/liveness.py

@@ -0,0 +1,65 @@
+from enum import StrEnum
+
+import httpx
+
+from researchx.adapters.url_guard import url_allowed
+
+_LIVENESS_TIMEOUT = 10.0
+_MAX_RESPONSE_BYTES = 2 * 1024 * 1024
+_MAX_REDIRECTS = 5
+_USER_AGENT = "researchx/0.2 (liveness check)"
+
+
+class LivenessStatus(StrEnum):
+    LIVE = "live"
+    STALE = "stale"
+    DEAD = "dead"
+
+
+async def check_liveness(url: str, client: httpx.AsyncClient | None = None) -> LivenessStatus:
+    own_client = client is None
+    active: httpx.AsyncClient = client or httpx.AsyncClient(
+        timeout=_LIVENESS_TIMEOUT,
+        follow_redirects=False,
+    )
+    current_url = url
+    try:
+        for _ in range(_MAX_REDIRECTS + 1):
+            if not url_allowed(current_url):
+                return LivenessStatus.DEAD
+            response = await active.get(
+                current_url,
+                headers={"User-Agent": _USER_AGENT},
+            )
+            if 300 <= response.status_code < 400:
+                location = response.headers.get("location")
+                if not location:
+                    return LivenessStatus.STALE
+                from urllib.parse import urljoin
+
+                current_url = urljoin(current_url, location)
+                continue
+            content = b""
+            async for chunk in response.aiter_bytes():
+                content += chunk
+                if len(content) > _MAX_RESPONSE_BYTES:
+                    break
+            status = response.status_code
+            if 200 <= status < 300:
+                return LivenessStatus.LIVE
+            return LivenessStatus.DEAD
+        return LivenessStatus.STALE
+    except (httpx.HTTPError, OSError):
+        return LivenessStatus.DEAD
+    finally:
+        if own_client:
+            await active.aclose()
+
+
+async def liveness_report(
+    urls: list[str],
+) -> dict[str, LivenessStatus]:
+    report: dict[str, LivenessStatus] = {}
+    for url in dict.fromkeys(urls):
+        report[url] = await check_liveness(url)
+    return report

backend/tests/test_adapter_types.py

@@ -0,0 +1,21 @@
+import secrets as secrets_module
+from string import ascii_lowercase
+
+from researchx.adapters.local_storage import generate_run_id
+
+
+def test_generate_run_id_format() -> None:
+    run_id = generate_run_id()
+    assert isinstance(run_id, str)
+    assert len(run_id) == 8
+    assert all(c in ascii_lowercase + "23456789" for c in run_id)
+    assert "o" not in run_id and "l" not in run_id and "0" not in run_id and "1" not in run_id
+
+
+def test_generate_run_id_entropy() -> None:
+    ids = {generate_run_id() for _ in range(100)}
+    assert len(ids) == 100
+
+
+def test_generate_run_id_uses_secrets_module() -> None:
+    assert secrets_module.choice is not None

backend/tests/test_adversarial.py

@@ -0,0 +1,359 @@
+"""Adversarial suite (REQ-32): attacks on the trust loop, proven caught.
+
+Every test here is an attempt to fool the verifier. If one passes
+without being flagged, the trust loop is broken — the suite fails.
+"""
+
+import asyncio
+import json
+from datetime import UTC, datetime
+from pathlib import Path
+
+import httpx
+
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter
+from researchx.adapters.types import AdapterError, ChatResult
+from researchx.api.app import create_app
+from researchx.evidence.store import EvidenceStore
+from researchx.trust.anchoring import anchor_quote
+from researchx.trust.ledger import build_ledger, export_checklist, liveness_export_gate
+from researchx.trust.liveness import LivenessStatus, check_liveness
+
+
+def test_attack_hallucinated_url_fails_export_gate() -> None:
+    store = EvidenceStore()
+    store.add_passage("https://real.example.org/a", "A real stored passage about the topic " * 5)
+    report = (
+        "# Report\n\n"
+        "Real claim [p-1].\n\n"
+        "Supporting detail from a hallucinated source [p-2].\n"
+    )
+    ledger = build_ledger(
+        run_id="attack001",
+        report_text=report,
+        evidence=store,
+        liveness={"https://real.example.org/a": LivenessStatus.LIVE},
+        visited_at=datetime.now(UTC),
+    )
+    claim_counts = _claim_counts(ledger)
+    assert claim_counts.get("p-1", 0) >= 1
+    assert "p-2" in report
+    assert not any("p-2" in pids for pids in [e.passages for e in ledger.entries]), (
+        "hallucinated passage id must not appear in any ledger entry"
+    )
+    unanchored = ledger.checklist.unanchored_claims
+    assert unanchored >= 1, "hallucinated citation must be flagged as unanchored"
+
+
+def _claim_counts(ledger) -> dict[str, int]:
+    counts: dict[str, int] = {}
+    for entry in ledger.entries:
+        for pid in entry.passages:
+            counts[pid] = counts.get(pid, 0) + entry.claims_supported
+    return counts
+
+
+def test_attack_fabricated_quote_flagged_not_accepted() -> None:
+    store = EvidenceStore()
+    for page in CORPUS:
+        store.add_page(page.url, page.title, page.text)
+    passages = store.writer_context()
+
+    fabricated = "This sentence appears in exactly zero stored passages anywhere."
+    verdict = anchor_quote(fabricated, passages)
+    assert verdict.matched is False
+    assert verdict.weak is False
+
+    near_miss = passages[0].text[: len(passages[0].text) // 2] + " And a divergent clause."
+    near_verdict = anchor_quote(near_miss, passages)
+    assert near_verdict.matched is False or near_verdict.weak is True
+
+    exact = anchor_quote(passages[0].quote, passages)
+    assert exact.matched is True
+
+
+def test_attack_quote_from_other_passage_counts_as_corroboration_not_anchor() -> None:
+    from researchx.adapters.fakes import SHARED_SENTENCE
+
+    store = EvidenceStore()
+    first = store.add_passage("https://a.example.org", SHARED_SENTENCE)
+    second = store.add_passage("https://b.example.org", SHARED_SENTENCE + " Extra tail text.")
+    verdict_first = anchor_quote(second.quote, [first])
+    assert verdict_first.matched is True or verdict_first.ratio > 0.5
+
+
+async def test_attack_liveness_private_redirect_dies(monkeypatch) -> None:
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(302, headers={"location": "http://169.254.169.254/x"})
+
+    transport = httpx.MockTransport(handler)
+    async with httpx.AsyncClient(transport=transport) as client:
+        status = await check_liveness("https://example.org/redirect", client)
+    assert status == LivenessStatus.DEAD
+
+
+async def test_attack_liveness_redirect_chain_to_dead(monkeypatch) -> None:
+    def handler(request: httpx.Request) -> httpx.Response:
+        if "hop1" in str(request.url):
+            return httpx.Response(302, headers={"location": "https://example.org/hop2"})
+        if "hop2" in str(request.url):
+            return httpx.Response(302, headers={"location": "https://example.org/hop3"})
+        return httpx.Response(410)
+
+    transport = httpx.MockTransport(handler)
+    async with httpx.AsyncClient(transport=transport) as client:
+        status = await check_liveness("https://example.org/hop1", client)
+    assert status == LivenessStatus.DEAD
+
+
+async def test_attack_oversized_response_capped(monkeypatch) -> None:
+    huge = "x" * (5 * 1024 * 1024)
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(200, text=huge)
+
+    transport = httpx.MockTransport(handler)
+    async with httpx.AsyncClient(transport=transport) as client:
+        status = await check_liveness("https://example.org/huge", client)
+    assert status == LivenessStatus.LIVE
+
+
+async def test_attack_pause_resume_mid_depth_loop_over_http(tmp_path: Path) -> None:
+    plan_template = json.dumps(
+        {
+            "sub_questions": ["verification passes", "quote anchoring"],
+            "source_universe": ["web"],
+            "outline": ["intro", "findings"],
+        }
+    )
+    writer = "# Report\n\nClaim [p-1] and claim [p-2].\n"
+    canned = [
+        ChatResult(content=plan_template, model="fake-planner"),
+        ChatResult(content=plan_template, model="fake-planner"),
+        ChatResult(content=plan_template, model="fake-planner"),
+        ChatResult(content=writer, model="fake-writer"),
+    ]
+    app = create_app(
+        storage_dir=tmp_path,
+        model_adapter=FakeModelAdapter(canned=canned),
+        search_adapter=FakeSearchAdapter(CORPUS),
+    )
+    async with httpx.AsyncClient(
+        transport=httpx.ASGITransport(app=app), base_url="http://testserver"
+    ) as client:
+        created = await client.post(
+            "/api/runs",
+            json={"question": "q", "methodology": "deep-report"},
+        )
+        assert created.status_code == 201
+        run_id = created.json()["id"]
+
+        for _ in range(300):
+            status = (await client.get(f"/api/runs/{run_id}")).json()["status"]
+            if status == "awaiting_approval":
+                break
+            await asyncio.sleep(0.01)
+        assert status == "awaiting_approval"
+
+        await client.post(f"/api/runs/{run_id}/approve")
+
+        paused_seen = False
+        for _ in range(600):
+            status = (await client.get(f"/api/runs/{run_id}")).json()["status"]
+            if status in ("reflecting", "searching", "extracting"):
+                await client.post(f"/api/runs/{run_id}/pause")
+                await client.post(f"/api/runs/{run_id}/resume")
+                paused_seen = True
+                break
+            if status == "done":
+                break
+            await asyncio.sleep(0.005)
+
+        for _ in range(600):
+            status = (await client.get(f"/api/runs/{run_id}")).json()["status"]
+            if status == "done":
+                break
+            await asyncio.sleep(0.005)
+        assert status == "done"
+        assert paused_seen, "mid-loop pause/resume must have been exercised"
+
+        report = await client.get(f"/api/runs/{run_id}/report")
+        assert report.status_code == 200
+
+
+async def test_attack_cancel_mid_loop_persists(tmp_path: Path) -> None:
+    plan = json.dumps(
+        {
+            "sub_questions": ["verification passes", "quote anchoring"],
+            "source_universe": ["web"],
+            "outline": ["intro"],
+        }
+    )
+    app = create_app(
+        storage_dir=tmp_path,
+        model_adapter=FakeModelAdapter(
+            canned=[ChatResult(content=plan, model="fake-planner") for _ in range(10)]
+            + [ChatResult(content="# never reached", model="fake-writer")]
+        ),
+        search_adapter=FakeSearchAdapter(CORPUS),
+    )
+    async with httpx.AsyncClient(
+        transport=httpx.ASGITransport(app=app), base_url="http://testserver"
+    ) as client:
+        created = await client.post(
+            "/api/runs", json={"question": "q", "methodology": "deep-report"}
+        )
+        run_id = created.json()["id"]
+        for _ in range(300):
+            if (await client.get(f"/api/runs/{run_id}")).json()["status"] == "awaiting_approval":
+                break
+            await asyncio.sleep(0.01)
+        await client.post(f"/api/runs/{run_id}/approve")
+        for _ in range(600):
+            status = (await client.get(f"/api/runs/{run_id}")).json()["status"]
+            if status in ("searching", "extracting", "reflecting"):
+                await client.post(f"/api/runs/{run_id}/cancel")
+                break
+            await asyncio.sleep(0.005)
+        for _ in range(300):
+            status = (await client.get(f"/api/runs/{run_id}")).json()["status"]
+            if status == "cancelled":
+                break
+            await asyncio.sleep(0.01)
+        assert status == "cancelled"
+
+def test_attack_weak_band_pinned_real_input() -> None:
+    store = EvidenceStore()
+    passage_text = (
+        "The verification pipeline re-anchored every quoted claim to its stored "
+        "passage before the report was allowed to ship to the reading room."
+    )
+    passage = store.add_passage("https://example.org/weak", passage_text)
+    words = passage_text.split()
+    near_miss = " ".join(words[:11]) + " released to the audience."
+    verdict = anchor_quote(near_miss, [passage])
+    assert 0.80 <= verdict.ratio < 0.85, f"expected weak band, got {verdict.ratio}"
+    assert verdict.matched is False
+    assert verdict.weak is True, f"near-threshold must flag weak, got {verdict.ratio}"
+
+
+def test_attack_fully_fabricated_report_fails_export() -> None:
+    store = EvidenceStore()
+    real = store.add_passage("https://example.org/real", "A genuine stored passage " * 10)
+    fabricated_report = (
+        "# Report\n\nClaim [p-1].\n\nClaim [p-7]. Claim [p-42].\n"
+    )
+    ledger = build_ledger(
+        run_id="attack002",
+        report_text=fabricated_report,
+        evidence=store,
+        liveness={"https://example.org/real": LivenessStatus.LIVE},
+        visited_at=datetime.now(UTC),
+    )
+    passed, failures = liveness_export_gate(ledger)
+    assert passed is False, "fully-fabricated report must fail the export gate"
+    assert failures == []
+    assert ledger.checklist.unanchored_claims >= 2
+    del real
+
+
+def test_export_round_trip_json_validates_into_backend_model() -> None:
+    from researchx.trust.ledger import CitationLedger
+
+    store = EvidenceStore()
+    stored_text = "A passage with real content for the round-trip proof."
+    store.add_passage("https://example.org/a", stored_text)
+    report = f"# Report\n\n{stored_text} [p-1].\n"
+    ledger = build_ledger(
+        run_id="attack003",
+        report_text=report,
+        evidence=store,
+        liveness={"https://example.org/a": LivenessStatus.LIVE},
+        visited_at=datetime.now(UTC),
+    )
+    exported = ledger.model_dump_json()
+    restored = CitationLedger.model_validate_json(exported)
+    assert restored == ledger
+    checklist_md = export_checklist(ledger)
+    assert "Anchoring gate" in checklist_md
+    assert "PASS" in checklist_md
+
+
+def test_attack_fabricated_quote_on_real_passage_id_fails() -> None:
+    store = EvidenceStore()
+    stored = store.add_passage(
+        "https://example.org/real",
+        "The genuine finding about verification pipelines is that anchoring works. " * 3,
+    )
+    report = (
+        "# Report\n\n"
+        f"THIS FABRICATED QUOTE WAS NEVER STORED ANYWHERE AT ALL [{stored.passage_id}]\n"
+    )
+    ledger = build_ledger(
+        run_id="attack004",
+        report_text=report,
+        evidence=store,
+        liveness={"https://example.org/real": LivenessStatus.LIVE},
+        visited_at=datetime.now(UTC),
+    )
+    assert ledger.checklist.unanchored_claims >= 1, (
+        "a fabricated quote riding a real passage ID must be flagged (REQ-20)"
+    )
+    passed, _ = liveness_export_gate(ledger)
+    assert passed is False
+
+
+def test_attack_real_verbatim_quote_on_real_passage_anchors() -> None:
+    store = EvidenceStore()
+    stored_text = (
+        "The genuine finding about verification pipelines is that anchoring works."
+    )
+    stored = store.add_passage("https://example.org/real", stored_text + " " + stored_text)
+    report = f"# Report\n\n{stored_text} [{stored.passage_id}]\n"
+    ledger = build_ledger(
+        run_id="attack005",
+        report_text=report,
+        evidence=store,
+        liveness={"https://example.org/real": LivenessStatus.LIVE},
+        visited_at=datetime.now(UTC),
+    )
+    assert ledger.checklist.anchored_claims == 1
+    assert ledger.checklist.unanchored_claims == 0
+    passed, _ = liveness_export_gate(ledger)
+    assert passed is True
+
+
+async def test_attack_search_result_redirecting_to_private_ip_refused(monkeypatch) -> None:
+    import tempfile
+    from pathlib import Path as PathMod
+
+    import httpx as httpx_mod
+
+    from researchx.adapters.secrets import EnvFileSecretsProvider
+    from researchx.adapters.tavily import TavilySearchAdapter
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        env_file = PathMod(tmpdir) / ".env.secrets"
+        env_file.write_text("TAVILY_API_KEY=t-key\n", encoding="utf-8")
+        secrets = EnvFileSecretsProvider(paths=[env_file])
+        adapter = TavilySearchAdapter(secrets)
+
+        def handler(request: httpx_mod.Request) -> httpx_mod.Response:
+            if "boobytrap" in str(request.url):
+                return httpx_mod.Response(
+                    302, headers={"location": "http://169.254.169.254/latest/meta-data"}
+                )
+            return httpx_mod.Response(200, text="<html><body>ok</body></html>")
+
+        transport = httpx_mod.MockTransport(handler)
+        original = httpx_mod.AsyncClient
+        monkeypatch.setattr(
+            httpx_mod, "AsyncClient", lambda **kw: original(transport=transport, **kw)
+        )
+
+        try:
+            await adapter.fetch("https://example.org/boobytrap")
+        except AdapterError as exc:
+            assert "refused" in str(exc) or "not allowed" in str(exc)
+        else:
+            raise AssertionError("fetch of a private-redirecting URL must be refused")

backend/tests/test_api.py

@@ -0,0 +1,156 @@
+import asyncio
+import json
+from pathlib import Path
+
+import httpx
+
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter
+from researchx.adapters.types import ChatResult
+from researchx.api.app import create_app
+
+_PLAN = json.dumps(
+    {"sub_questions": ["verification passes"], "source_universe": ["web"], "outline": ["intro"]}
+)
+_WRITER = "# Report\n\nClaim [p-1] and claim [p-2].\n"
+
+
+def _app(tmp_path: Path):
+    return create_app(
+        storage_dir=tmp_path,
+        model_adapter=FakeModelAdapter(
+            canned=[
+                ChatResult(content=_PLAN, model="fake-planner"),
+                ChatResult(content=_WRITER, model="fake-writer"),
+            ]
+        ),
+        search_adapter=FakeSearchAdapter(CORPUS),
+    )
+
+
+async def _client(tmp_path: Path) -> httpx.AsyncClient:
+    return httpx.AsyncClient(
+        transport=httpx.ASGITransport(app=_app(tmp_path)),
+        base_url="http://testserver",
+    )
+
+
+async def test_config_status(tmp_path: Path) -> None:
+    async with await _client(tmp_path) as client:
+        response = await client.get("/api/config")
+        assert response.status_code == 200
+        body = response.json()
+        assert body["model_adapter"] == "FakeModelAdapter"
+        assert body["cost_counters"]["runs_created"] == 0
+
+
+async def test_methodology_cards(tmp_path: Path) -> None:
+    async with await _client(tmp_path) as client:
+        response = await client.get("/api/methodologies")
+        assert response.status_code == 200
+        cards = response.json()
+        slugs = [c["slug"] for c in cards]
+        assert "rapid-answer" in slugs and "deep-report" in slugs
+        for card in cards:
+            assert card["eta_minutes"] > 0
+            assert "estimate" in card["cost_estimate"]
+            assert card["why_recommended"]
+            assert card["dials"]["depth"] >= 1
+
+
+async def test_create_run_rejects_unknown_methodology(tmp_path: Path) -> None:
+    async with await _client(tmp_path) as client:
+        response = await client.post(
+            "/api/runs", json={"question": "q", "methodology": "nonexistent"}
+        )
+        assert response.status_code == 404
+
+
+async def _await_status(client: httpx.AsyncClient, run_id: str, status: str) -> None:
+    for _ in range(200):
+        current = (await client.get(f"/api/runs/{run_id}")).json()
+        if current["status"] == status:
+            return
+        await asyncio.sleep(0.01)
+    raise AssertionError(f"run never reached {status}: {current['status']}")
+
+
+async def test_run_lifecycle_over_http(tmp_path: Path) -> None:
+    async with await _client(tmp_path) as client:
+        created = await client.post(
+            "/api/runs", json={"question": "How do engines run?", "methodology": "rapid-answer"}
+        )
+        assert created.status_code == 201
+        run_id = created.json()["id"]
+
+        await _await_status(client, run_id, "awaiting_approval")
+        approved = await client.post(f"/api/runs/{run_id}/approve")
+        assert approved.status_code == 200
+
+        await _await_status(client, run_id, "done")
+        report = await client.get(f"/api/runs/{run_id}/report")
+        assert report.status_code == 200
+        assert "[p-1]" in report.json()["markdown"]
+
+        ledger = await client.get(f"/api/runs/{run_id}/ledger")
+        assert ledger.status_code == 200
+        assert ledger.json()["checklist"]["citations_checked"] >= 1
+
+        config = (await client.get("/api/config")).json()
+        assert config["cost_counters"]["runs_created"] == 1
+        assert config["cost_counters"]["runs_completed"] == 1
+
+
+async def test_missing_run_404(tmp_path: Path) -> None:
+    async with await _client(tmp_path) as client:
+        assert (await client.get("/api/runs/zzzz9999")).status_code == 404
+        assert (await client.post("/api/runs/zzzz9999/approve")).status_code == 404
+        assert (await client.get("/api/runs/zzzz9999/events")).status_code == 404
+
+
+async def test_sse_stream_replays_events(tmp_path: Path) -> None:
+    client = await _client(tmp_path)
+    try:
+        created = await client.post(
+            "/api/runs", json={"question": "q", "methodology": "rapid-answer"}
+        )
+        run_id = created.json()["id"]
+        await _await_status(client, run_id, "awaiting_approval")
+        await client.post(f"/api/runs/{run_id}/approve")
+        await _await_status(client, run_id, "done")
+
+        collected = b""
+        async with client.stream("GET", f"/api/runs/{run_id}/events") as response:
+            assert response.status_code == 200
+            assert response.headers["content-type"].startswith("text/event-stream")
+            async for chunk in response.aiter_bytes():
+                collected += chunk
+                if b"run_done" in collected:
+                    break
+        text = collected.decode()
+        assert "event: run_started" in text
+        assert "event: run_done" in text
+    finally:
+        await client.aclose()
+
+
+async def test_pause_resume_cancel_over_http(tmp_path: Path) -> None:
+    async with await _client(tmp_path) as client:
+        created = await client.post(
+            "/api/runs", json={"question": "q", "methodology": "rapid-answer"}
+        )
+        run_id = created.json()["id"]
+        await _await_status(client, run_id, "awaiting_approval")
+
+        paused = await client.post(f"/api/runs/{run_id}/pause")
+        assert paused.status_code == 200
+        resumed = await client.post(f"/api/runs/{run_id}/resume")
+        assert resumed.status_code == 200
+
+        cancelled = await client.post(f"/api/runs/{run_id}/cancel")
+        assert cancelled.status_code == 200
+        for _ in range(200):
+            status = (await client.get(f"/api/runs/{run_id}")).json()["status"]
+            if status == "cancelled":
+                break
+            await asyncio.sleep(0.01)
+        assert status == "cancelled"

backend/tests/test_capability_probe.py

@@ -0,0 +1,99 @@
+import httpx
+import pytest
+
+from researchx.adapters.capability_probe import probe_model_adapter
+from researchx.adapters.ollama import OllamaModelAdapter
+from researchx.adapters.probe import DEFAULT_CONTEXT_CAP, DEFAULT_EMBEDDING_BATCH
+from researchx.adapters.secrets import EnvFileSecretsProvider
+from researchx.adapters.types import AdapterError
+
+
+def _secrets(tmp_path, values: dict[str, str]) -> EnvFileSecretsProvider:
+    env_file = tmp_path / ".env.secrets"
+    env_file.write_text("".join(f"{k}={v}\n" for k, v in values.items()), encoding="utf-8")
+    return EnvFileSecretsProvider(paths=[env_file])
+
+
+def _ok_smoke_response() -> dict[str, object]:
+    return {
+        "choices": [{"message": {"role": "assistant", "content": '{"ok": true}'}}],
+        "usage": {"prompt_tokens": 3, "completion_tokens": 2},
+    }
+
+
+async def test_probe_green_on_supporting_model(tmp_path, monkeypatch) -> None:
+    secrets = _secrets(tmp_path, {"OLLAMA_API_KEY": "cloud-key"})
+    adapter = OllamaModelAdapter(secrets, planner_model="p", writer_model="w")
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        if str(request.url).endswith("/models"):
+            return httpx.Response(200, json={"data": [{"id": "w"}, {"id": "p"}]})
+        return httpx.Response(200, json=_ok_smoke_response())
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    probe = await probe_model_adapter(adapter)
+    assert probe.endpoint == "https://ollama.com/v1"
+    assert probe.models == ["w", "p"]
+    assert probe.context_window == DEFAULT_CONTEXT_CAP
+    assert probe.embedding_batch == DEFAULT_EMBEDDING_BATCH
+    assert probe.structured_outputs_supported is True
+    assert probe.structured_output_warning is None
+    assert probe.degraded is False
+
+
+async def test_probe_warns_on_weak_structured_output(tmp_path, monkeypatch) -> None:
+    secrets = _secrets(tmp_path, {"OLLAMA_API_KEY": "cloud-key"})
+    adapter = OllamaModelAdapter(secrets, planner_model="p", writer_model="writer-model")
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        if str(request.url).endswith("/models"):
+            return httpx.Response(200, json={"data": [{"id": "writer-model"}]})
+        return httpx.Response(200, json={"choices": [{"message": {"content": "not json"}}]})
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    probe = await probe_model_adapter(adapter)
+    assert probe.structured_outputs_supported is False
+    assert probe.structured_output_warning is not None
+    assert "writer-model" in probe.structured_output_warning
+    assert "degrade" in probe.structured_output_warning
+    assert probe.degraded is True
+
+
+async def test_probe_reports_endpoint_down_as_unsupported(tmp_path, monkeypatch) -> None:
+    secrets = _secrets(tmp_path, {"OLLAMA_API_KEY": "cloud-key"})
+    adapter = OllamaModelAdapter(secrets, planner_model="p", writer_model="w")
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(500, text="boom")
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    with pytest.raises(AdapterError):
+        await probe_model_adapter(adapter)
+
+
+async def test_list_models_falls_back_to_local(tmp_path, monkeypatch) -> None:
+    secrets = _secrets(tmp_path, {"OLLAMA_API_KEY": "cloud-key"})
+    adapter = OllamaModelAdapter(secrets, planner_model="p", writer_model="w")
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        if str(request.url).startswith("https://ollama.com"):
+            return httpx.Response(401, json={"error": "unauthorized"})
+        return httpx.Response(200, json={"data": [{"id": "local-model"}]})
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    models = await adapter.list_models()
+    assert models == ["local-model"]
+    assert adapter.active_base_url == "http://localhost:11434/v1"
+    assert adapter.last_fallback_reason is not None

backend/tests/test_dials.py

@@ -0,0 +1,66 @@
+import pytest
+from pydantic import ValidationError
+
+from researchx.config.dials import DIAL_REGISTRY, DialDescriptor, Dials
+
+EXPECTED_DIALS = {
+    "source_universe": "web",
+    "search_routing": "single",
+    "query_strategy": "decomposed",
+    "breadth": 2,
+    "depth": 1,
+    "quality_gates": "standard",
+    "citation_rigor": "per-claim",
+    "verification_passes": 1,
+    "synthesis_style": "memo",
+    "output_structure": "brief",
+    "memory_scope": "none",
+    "checkpoints": False,
+}
+
+
+def test_defaults_resolve() -> None:
+    assert Dials().model_dump() == EXPECTED_DIALS
+
+
+def test_all_twelve_dials_present() -> None:
+    assert set(Dials.model_fields) == set(EXPECTED_DIALS)
+    assert len(Dials.model_fields) == 12
+
+
+def test_registry_covers_all_dials() -> None:
+    assert set(DIAL_REGISTRY) == set(EXPECTED_DIALS)
+    for descriptor in DIAL_REGISTRY.values():
+        assert isinstance(descriptor, DialDescriptor)
+        assert descriptor.label
+        assert descriptor.description
+
+
+def test_literal_dial_rejects_invalid_value() -> None:
+    with pytest.raises(ValidationError):
+        Dials(source_universe="library")
+
+
+def test_bounded_int_rejects_out_of_range() -> None:
+    with pytest.raises(ValidationError):
+        Dials(breadth=6)
+    with pytest.raises(ValidationError):
+        Dials(depth=0)
+    with pytest.raises(ValidationError):
+        Dials(verification_passes=-1)
+
+
+def test_checkpoints_rejects_non_bool() -> None:
+    with pytest.raises(ValidationError):
+        Dials(checkpoints=5)
+
+
+def test_model_dump_round_trips() -> None:
+    dials = Dials(depth=3, breadth=5, checkpoints=True, synthesis_style="executive")
+    assert Dials.model_validate(dials.model_dump()) == dials
+
+
+def test_dials_are_immutable() -> None:
+    dials = Dials()
+    with pytest.raises(ValidationError):
+        dials.depth = 3

backend/tests/test_engine.py

@@ -0,0 +1,183 @@
+import asyncio
+import json
+from pathlib import Path
+
+import pytest
+
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter
+from researchx.adapters.local_storage import LocalStorageAdapter
+from researchx.adapters.types import ChatResult
+from researchx.engine.actor import RunActor, make_run_config
+from researchx.engine.events import EventBus
+from researchx.engine.states import RunStateName, can_transition
+from researchx.methodologies import registry
+
+_PLAN = json.dumps(
+    {
+        "sub_questions": ["methodology verification", "quote anchoring"],
+        "source_universe": ["web"],
+        "outline": ["intro", "findings"],
+    }
+)
+
+_WRITER_REPORT = (
+    "# Report\n\n"
+    "The verification pass re-anchored every quoted claim [p-1]. "
+    "Methodology-first selection converts ad-hoc prompting [p-1] "
+    "into reproducible decisions [p-2].\n"
+)
+
+
+def _canned() -> list[ChatResult]:
+    return [
+        ChatResult(content=_PLAN, model="fake-planner"),
+        ChatResult(content=_WRITER_REPORT, model="fake-writer"),
+    ]
+
+
+def _actor(tmp_path: Path) -> tuple[RunActor, EventBus, FakeSearchAdapter]:
+    _run_id, config = make_run_config(
+        question="How do verification pipelines keep citations honest?",
+        context="",
+        methodology_slug="rapid-answer",
+        overrides={},
+        registry=registry,
+        run_id="abcd2345",
+    )
+    model = FakeModelAdapter(canned=_canned())
+    search = FakeSearchAdapter(CORPUS)
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    bus = EventBus()
+    actor = RunActor(
+        run_config=config,
+        model=model,
+        search=search,
+        storage=storage,
+        registry=registry,
+        event_bus=bus,
+    )
+    return actor, bus, search
+
+
+async def test_full_walk_reaches_done(tmp_path: Path) -> None:
+    actor, bus, _ = _actor(tmp_path)
+    task = asyncio.create_task(actor.run())
+    while actor.state.state != RunStateName.AWAITING_APPROVAL:
+        await asyncio.sleep(0.01)
+        if task.done():
+            break
+    await actor.approve()
+    state = await task
+    assert state.state == RunStateName.DONE
+    assert state.plan is not None and len(state.plan.sub_questions) == 2
+
+    saved = await LocalStorageAdapter(base_dir=tmp_path).read_run_artifact("abcd2345", "state.json")
+    assert json.loads(saved)["state"] == "DONE"
+
+    report = await LocalStorageAdapter(base_dir=tmp_path).read_run_artifact("abcd2345", "report.md")
+    assert "[p-1]" in report
+
+    ledger_raw = await LocalStorageAdapter(base_dir=tmp_path).read_run_artifact(
+        "abcd2345", "ledger.json"
+    )
+    ledger = json.loads(ledger_raw)
+    assert ledger["checklist"]["citations_checked"] >= 1
+    assert ledger["checklist"]["liveness_ratio"] >= 0
+
+    checklist = await LocalStorageAdapter(base_dir=tmp_path).read_run_artifact(
+        "abcd2345", "checklist.md"
+    )
+    assert "Verification Checklist" in checklist
+
+    types = [e.type for e in bus.replay()]
+    assert "run_started" in types
+    assert "query_fired" in types
+    assert "source_visited" in types
+    assert "passage_extracted" in types
+    assert "run_done" in types
+
+
+async def test_halt_at_awaiting_approval_until_approved(tmp_path: Path) -> None:
+    actor, _, _ = _actor(tmp_path)
+    task = asyncio.create_task(actor.run())
+    for _ in range(100):
+        await asyncio.sleep(0.01)
+        if actor.state.state == RunStateName.AWAITING_APPROVAL:
+            break
+    assert actor.state.state == RunStateName.AWAITING_APPROVAL
+    await asyncio.sleep(0.05)
+    assert not task.done()
+    await actor.approve()
+    state = await task
+    assert state.state == RunStateName.DONE
+
+
+async def test_cancel_persists_cancelled_state(tmp_path: Path) -> None:
+    actor, _, _ = _actor(tmp_path)
+    task = asyncio.create_task(actor.run())
+    while actor.state.state != RunStateName.AWAITING_APPROVAL:
+        await asyncio.sleep(0.01)
+    actor.cancel()
+    await actor.approve()
+    with pytest.raises(asyncio.CancelledError):
+        await task
+    saved = await LocalStorageAdapter(base_dir=tmp_path).read_run_artifact("abcd2345", "state.json")
+    assert json.loads(saved)["state"] == "CANCELLED"
+
+
+async def test_pause_resume_mid_run(tmp_path: Path) -> None:
+    actor, _, _ = _actor(tmp_path)
+    task = asyncio.create_task(actor.run())
+    while actor.state.state != RunStateName.AWAITING_APPROVAL:
+        await asyncio.sleep(0.01)
+    await actor.approve()
+    actor.pause()
+    await asyncio.sleep(0.05)
+    assert not task.done()
+    actor.resume()
+    state = await task
+    assert state.state == RunStateName.DONE
+
+
+def test_illegal_transitions_rejected() -> None:
+    assert not can_transition(RunStateName.PLANNING, RunStateName.DONE)
+    assert not can_transition(RunStateName.DONE, RunStateName.PLANNING)
+    assert can_transition(RunStateName.PLANNING, RunStateName.AWAITING_APPROVAL)
+    assert can_transition(RunStateName.REFLECTING, RunStateName.SEARCHING)
+
+
+async def test_planner_non_json_fails_honestly(tmp_path: Path) -> None:
+    _run_id, config = make_run_config(
+        question="q",
+        context="",
+        methodology_slug="rapid-answer",
+        overrides={},
+        registry=registry,
+        run_id="abcd2345",
+    )
+    model = FakeModelAdapter(canned=[ChatResult(content="not json", model="fake-planner")])
+    actor = RunActor(
+        run_config=config,
+        model=model,
+        search=FakeSearchAdapter(CORPUS),
+        storage=LocalStorageAdapter(base_dir=tmp_path),
+        registry=registry,
+        event_bus=EventBus(),
+    )
+    task = asyncio.create_task(actor.run())
+    with pytest.raises(Exception, match="planner returned non-JSON plan"):
+        await task
+    saved = await LocalStorageAdapter(base_dir=tmp_path).read_run_artifact("abcd2345", "state.json")
+    assert json.loads(saved)["state"] == "FAILED"
+
+
+async def test_writer_context_is_visited_only(tmp_path: Path) -> None:
+    actor, _, _ = _actor(tmp_path)
+    task = asyncio.create_task(actor.run())
+    while actor.state.state != RunStateName.AWAITING_APPROVAL:
+        await asyncio.sleep(0.01)
+    await actor.approve()
+    await task
+    assert actor._store.writer_context(), "evidence collected"
+    outside_ids = {p.passage_id for p in actor._store.writer_context()}
+    assert all(pid.startswith("p-") for pid in outside_ids)

backend/tests/test_evidence.py

@@ -0,0 +1,56 @@
+from researchx.evidence.store import EvidenceStore, extract_passages
+
+
+def test_extract_passages_min_length() -> None:
+    text = "short\n" + ("x" * 150) + "\nanother short"
+    passages = extract_passages(text)
+    assert passages == ["x" * 150]
+
+
+def test_store_stable_ids() -> None:
+    store = EvidenceStore()
+    first = store.add_passage("https://a", "first passage text " * 10)
+    second = store.add_passage("https://a", "second passage text " * 10)
+    assert first.passage_id == "p-1"
+    assert second.passage_id == "p-2"
+
+
+def test_store_add_page_creates_passages() -> None:
+    store = EvidenceStore()
+    body = "\n".join(f"paragraph {i} " + "y" * 150 for i in range(3))
+    store.add_page("https://example.org/a", "Title A", body)
+    assert len(store) == 3
+    page = store.pages()[0]
+    assert page.url == "https://example.org/a"
+    assert page.title == "Title A"
+    assert len(page.passage_ids) == 3
+
+
+def test_writer_context_contains_only_stored() -> None:
+    store = EvidenceStore()
+    store.add_passage("https://a", "stored passage " * 20)
+    context = store.writer_context()
+    assert len(context) == 1
+    assert context[0].url == "https://a"
+
+    outside = EvidenceStore()
+    outside_context = outside.writer_context()
+    assert outside_context == []
+
+
+def test_dedupe_by_quote() -> None:
+    store = EvidenceStore()
+    text = "identical passage text " * 10
+    store.add_passage("https://a", text)
+    assert store.has_seen(text[:200])
+    assert not store.has_seen("something never stored " * 20)
+
+
+def test_passages_for_url() -> None:
+    store = EvidenceStore()
+    store.add_passage("https://a", "from a " * 30)
+    store.add_passage("https://b", "from b " * 30)
+    from_a = store.passages_for_url("https://a")
+    assert len(from_a) == 1
+    assert from_a[0].url == "https://a"
+    assert store.passages_for_url("https://missing") == []

backend/tests/test_fakes.py

@@ -0,0 +1,82 @@
+import inspect
+
+from researchx.adapters import fakes
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter, corpus
+from researchx.adapters.model import ModelAdapter, ModelRoles
+from researchx.adapters.search import SearchAdapter
+from researchx.adapters.types import AdapterError, ChatResult, ModelMessage
+
+
+def _model() -> FakeModelAdapter:
+    return FakeModelAdapter(canned=[ChatResult(content="ok", model="fake-model")])
+
+
+async def test_fake_model_full_interface() -> None:
+    model = _model()
+    assert isinstance(model, ModelAdapter)
+    result = await model.chat([ModelMessage(role="user", content="hi")], model="fake-model")
+    assert result.content == "ok"
+    assert await model.list_models() == ["fake-model"]
+    assert model.roles() == ModelRoles(planner="fake-planner", writer="fake-writer")
+
+
+async def test_fake_model_exhausted_raises() -> None:
+    model = _model()
+    await model.chat([ModelMessage(role="user", content="hi")], model="fake-model")
+    try:
+        await model.chat([ModelMessage(role="user", content="again")], model="fake-model")
+    except AdapterError:
+        pass
+    else:
+        raise AssertionError("expected AdapterError")
+
+
+async def test_fake_model_json_mode_recorded() -> None:
+    model = _model()
+    await model.chat([ModelMessage(role="user", content="hi")], model="fake-model", json_mode=True)
+    assert model.last_json_mode is True
+
+
+async def test_fake_search_full_interface() -> None:
+    search = FakeSearchAdapter(corpus())
+    assert isinstance(search, SearchAdapter)
+    results = await search.search("verification quoted claim", max_results=3)
+    assert 0 < len(results) <= 3
+    page = await search.fetch(results[0].url)
+    assert page.url == results[0].url
+
+
+async def test_fake_search_deterministic_order() -> None:
+    search = FakeSearchAdapter(corpus())
+    first = await search.search("methodology", max_results=5)
+    second = await search.search("methodology", max_results=5)
+    assert [r.url for r in first] == [r.url for r in second]
+
+
+async def test_fake_search_unknown_url_raises() -> None:
+    search = FakeSearchAdapter(corpus())
+    try:
+        await search.fetch("https://example.org/missing")
+    except AdapterError:
+        pass
+    else:
+        raise AssertionError("expected AdapterError")
+
+
+def test_corpus_shape() -> None:
+    pages = CORPUS
+    assert len(pages) >= 5
+    urls = [p.url for p in pages]
+    assert len(set(urls)) == len(urls)
+    texts = "\n".join(p.text for p in pages)
+    assert "—" in texts or "é" in texts or "近" in texts
+
+
+def test_corpus_shared_sentence() -> None:
+    sharing = [p for p in CORPUS if fakes.SHARED_SENTENCE in p.text]
+    assert len(sharing) == 2
+
+
+def test_fakes_no_httpx_dependency() -> None:
+    source = inspect.getsource(fakes)
+    assert "httpx" not in source

backend/tests/test_integration_p1.py

@@ -0,0 +1,84 @@
+from datetime import UTC, datetime
+
+import pytest
+
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter
+from researchx.adapters.local_storage import LocalStorageAdapter
+from researchx.adapters.types import ChatResult
+from researchx.config.run_config import RunConfig, UnknownOverrideError, new_run_id, resolve_dials
+from researchx.methodologies import registry
+
+
+async def test_registry_to_fake_model_to_snapshot_round_trip(tmp_path) -> None:
+    methodology = registry.get("deep-report")
+    canned = ChatResult(
+        content='{"sub_questions": ["What is verification?", "How does anchoring work?"]}',
+        model="fake-planner",
+    )
+    model = FakeModelAdapter(canned=[canned])
+    plan_result = await model.chat([], model=model.roles().planner, json_mode=True)
+    assert "sub_questions" in plan_result.content
+
+    run_id = new_run_id()
+    dials = resolve_dials("deep-report", {"breadth": 3}, registry)
+    run_config = RunConfig(
+        run_id=run_id,
+        methodology_slug="deep-report",
+        question="How do verification pipelines keep citations honest?",
+        resolved_dials=dials,
+        overrides={"breadth": 3},
+        created_at=datetime.now(UTC),
+    )
+    assert run_config.resolved_dials.breadth == 3
+
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    await storage.write_run_artifact(run_id, "run_config.json", run_config.model_dump_json())
+
+    restored = RunConfig.model_validate_json(
+        await storage.read_run_artifact(run_id, "run_config.json")
+    )
+    assert restored == run_config
+    assert restored.resolved_dials.depth == methodology.dials.depth
+
+
+def test_methodology_behavior_difference() -> None:
+    rapid = registry.get("rapid-answer")
+    deep = registry.get("deep-report")
+    assert rapid.dials.depth < deep.dials.depth
+    assert rapid.dials.breadth < deep.dials.breadth
+    assert rapid.output_shape != deep.output_shape
+    assert rapid.dials.synthesis_style != deep.dials.synthesis_style
+    assert rapid.dials.verification_passes < deep.dials.verification_passes
+    assert rapid.dials.output_structure != deep.dials.output_structure
+
+
+def test_registry_snapshot_immutability() -> None:
+    from pydantic import ValidationError
+
+    methodology = registry.get("rapid-answer")
+    frozen = registry.get("rapid-answer")
+    with pytest.raises(ValidationError):
+        frozen.dials.depth = 99
+    fresh = registry.get("rapid-answer")
+    assert fresh.dials.depth == methodology.dials.depth
+    assert fresh.dials.depth == 1
+
+
+def test_override_rejects_unknown_dial() -> None:
+    with pytest.raises(UnknownOverrideError):
+        resolve_dials("rapid-answer", {"nonexistent_dial": 1}, registry)
+
+
+def test_new_run_id_format() -> None:
+    run_id = new_run_id()
+    assert len(run_id) == 8
+    assert all(c in "0123456789abcdef" for c in run_id)
+
+
+async def test_fake_search_feeds_evidence_shape() -> None:
+    search = FakeSearchAdapter(CORPUS)
+    results = await search.search("methodology dials verification", max_results=5)
+    assert len(results) >= 1
+    for result in results:
+        page = await search.fetch(result.url)
+        assert page.text.strip()

backend/tests/test_live_smoke.py

@@ -0,0 +1,64 @@
+"""Opt-in live smoke tier (G-004): real-adapter probes, keyed only.
+
+These tests NEVER run in the zero-key CI suite: they are marked
+`live` and skip cleanly when OLLAMA_API_KEY / TAVILY_API_KEY are
+absent from the secrets scope. Run explicitly with:
+
+    uv run pytest -m live
+"""
+
+import os
+from pathlib import Path
+
+import httpx
+import pytest
+
+from researchx.adapters.capability_probe import probe_model_adapter
+from researchx.adapters.ollama import OllamaModelAdapter
+from researchx.adapters.secrets import EnvFileSecretsProvider
+from researchx.adapters.tavily import TavilySearchAdapter
+from researchx.trust.liveness import LivenessStatus, check_liveness
+
+pytestmark = pytest.mark.live
+
+_SECRETS_PATHS = [
+    Path.cwd() / ".ciagent" / ".env.secrets",
+    Path.cwd().parents[1] / ".ciagent" / ".env.secrets",
+]
+
+
+def _secrets() -> EnvFileSecretsProvider:
+    return EnvFileSecretsProvider(paths=_SECRETS_PATHS)
+
+
+def _needs_key(key: str) -> str:
+    value = _secrets().resolve(key) or os.environ.get(key)
+    if not value:
+        pytest.skip(f"{key} not present — live tier is opt-in")
+    return value
+
+
+async def test_live_ollama_probe_and_chat() -> None:
+    _needs_key("OLLAMA_API_KEY")
+    adapter = OllamaModelAdapter(
+        _secrets(), planner_model="gpt-oss:20b", writer_model="gpt-oss:20b"
+    )
+    probe = await probe_model_adapter(adapter)
+    assert probe.endpoint in ("https://ollama.com/v1", "http://localhost:11434/v1")
+    assert probe.context_window <= 8192
+    assert probe.embedding_batch == 8
+
+
+async def test_live_tavily_search() -> None:
+    _needs_key("TAVILY_API_KEY")
+    adapter = TavilySearchAdapter(_secrets())
+    results = await adapter.search("deep research agent verification", max_results=3)
+    assert 1 <= len(results) <= 3
+    assert all(r.url.startswith("http") for r in results)
+
+
+async def test_live_liveness_against_real_page() -> None:
+    status = await check_liveness("https://example.org/")
+    assert status in (LivenessStatus.LIVE, LivenessStatus.STALE, LivenessStatus.DEAD)
+    void_httpx = httpx.AsyncClient
+    del void_httpx

backend/tests/test_local_storage.py

@@ -0,0 +1,66 @@
+from pathlib import Path
+
+from researchx.adapters.local_storage import LocalStorageAdapter
+from researchx.adapters.storage import StorageAdapter
+from researchx.adapters.types import AdapterError
+
+
+async def test_storage_round_trip(tmp_path: Path) -> None:
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    assert isinstance(storage, StorageAdapter)
+    target = await storage.write_run_artifact("abcd2345", "state.json", '{"state": "PLANNING"}')
+    assert target.exists()
+    content = await storage.read_run_artifact("abcd2345", "state.json")
+    assert content == '{"state": "PLANNING"}'
+
+
+async def test_atomic_overwrite(tmp_path: Path) -> None:
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    await storage.write_run_artifact("abcd2345", "state.json", '{"v": 1}')
+    await storage.write_run_artifact("abcd2345", "state.json", '{"v": 2}')
+    assert await storage.read_run_artifact("abcd2345", "state.json") == '{"v": 2}'
+    leftovers = list((tmp_path / "runs" / "abcd2345").glob("*.tmp"))
+    assert leftovers == []
+
+
+async def test_run_dir_layout(tmp_path: Path) -> None:
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    run_dir = storage.run_dir("abcd2345")
+    assert run_dir == tmp_path / "runs" / "abcd2345"
+    await storage.write_run_artifact("abcd2345", "report.md", "# Report")
+    assert run_dir.is_dir()
+
+
+async def test_read_missing_raises(tmp_path: Path) -> None:
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    try:
+        await storage.read_run_artifact("zzzz9999", "state.json")
+    except AdapterError:
+        pass
+    else:
+        raise AssertionError("expected AdapterError")
+
+
+async def test_path_traversal_rejected(tmp_path: Path) -> None:
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    for bad_name in ["../escape.md", "/etc/passwd", "a/b.md", "", "."]:
+        try:
+            await storage.write_run_artifact("abcd2345", bad_name, "x")
+        except AdapterError:
+            pass
+        else:
+            raise AssertionError(f"expected AdapterError for name: {bad_name!r}")
+    for bad_run_id in ["../evil", "short", "waytoolongid123", "ABCD2345", "a b c d e"]:
+        try:
+            await storage.write_run_artifact(bad_run_id, "state.json", "x")
+        except AdapterError:
+            pass
+        else:
+            raise AssertionError(f"expected AdapterError for run_id: {bad_run_id!r}")
+
+
+async def test_no_tmp_leftover_after_write(tmp_path: Path) -> None:
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    await storage.write_run_artifact("abcd2345", "state.json", '{"v": 1}')
+    leftovers = list((tmp_path / "runs" / "abcd2345").glob("*.tmp"))
+    assert leftovers == []

backend/tests/test_methodologies.py

@@ -0,0 +1,95 @@
+import pytest
+from pydantic import ValidationError
+
+from researchx.methodologies import registry
+
+
+def test_registry_resolves_both_slugs() -> None:
+    rapid = registry.get("rapid-answer")
+    deep = registry.get("deep-report")
+    assert rapid.slug == "rapid-answer"
+    assert deep.slug == "deep-report"
+    assert rapid.name == "Rapid Answer"
+    assert deep.name == "Deep Report"
+
+
+def test_unknown_slug_raises_key_error() -> None:
+    with pytest.raises(KeyError):
+        registry.get("systematic-review")
+
+
+def test_list_ordered_by_name() -> None:
+    listed = registry.list()
+    assert [m.name for m in listed] == ["Deep Report", "Rapid Answer"]
+
+
+def test_builtin_dials_match_contracts() -> None:
+    rapid = registry.get("rapid-answer")
+    assert rapid.dials.depth == 1
+    assert rapid.dials.breadth == 1
+    assert rapid.dials.verification_passes == 1
+    assert rapid.dials.citation_rigor == "per-claim"
+    assert rapid.dials.synthesis_style == "memo"
+    assert rapid.dials.output_structure == "brief"
+    assert rapid.output_shape == "memo"
+
+    deep = registry.get("deep-report")
+    assert deep.dials.depth == 3
+    assert deep.dials.breadth == 2
+    assert deep.dials.verification_passes == 2
+    assert deep.dials.citation_rigor == "per-claim"
+    assert deep.dials.synthesis_style == "executive"
+    assert deep.dials.output_structure == "report"
+    assert deep.dials.checkpoints is True
+    assert deep.output_shape == "executive-report"
+
+
+def test_methodologies_differ_meaningfully() -> None:
+    rapid = registry.get("rapid-answer")
+    deep = registry.get("deep-report")
+    assert rapid.dials.depth != deep.dials.depth
+    assert rapid.dials.breadth != deep.dials.breadth
+    assert rapid.dials.verification_passes != deep.dials.verification_passes
+    assert rapid.dials.synthesis_style != deep.dials.synthesis_style
+    assert rapid.dials.output_structure != deep.dials.output_structure
+    assert rapid.output_shape != deep.output_shape
+
+
+def test_registry_entries_are_immutable() -> None:
+    snapshot = registry.get("rapid-answer")
+    with pytest.raises(ValidationError):
+        snapshot.dials.depth = 3
+    assert registry.get("rapid-answer").dials.depth == 1
+
+    listed = registry.list()
+    with pytest.raises(ValidationError):
+        listed[0].dials.checkpoints = True
+    assert registry.get("rapid-answer").dials.checkpoints is False
+
+
+def test_prompt_templates_render_placeholders() -> None:
+    deep = registry.get("deep-report")
+    planner = deep.render_planner_prompt(question="What changed?", context="none")
+    assert "What changed?" in planner
+    assert "none" in planner
+    writer = deep.render_writer_prompt(
+        question="What changed?", context="none", plan="p1", evidence="[p-1] (https://a) quote text"
+    )
+    assert "{plan}" not in writer
+    assert "{evidence}" not in writer
+    assert "p1" in writer
+    assert "[p-1] (https://a) quote text" in writer
+
+
+def test_writer_prompt_requires_evidence_slot() -> None:
+    for slug in ("rapid-answer", "deep-report"):
+        methodology = registry.get(slug)
+        assert "{evidence}" in methodology.writer_prompt
+
+
+def test_mutation_of_returned_copy_does_not_affect_registry() -> None:
+    original = registry.get("deep-report").dials.model_dump()
+    copy = registry.get("deep-report").dials.model_copy()
+    mutated = copy.model_copy(update={"depth": 1})
+    assert mutated.depth == 1
+    assert registry.get("deep-report").dials.model_dump() == original

backend/tests/test_p0_regressions.py

@@ -0,0 +1,215 @@
+import asyncio
+import json
+from datetime import UTC, datetime
+from pathlib import Path
+
+import httpx
+import pytest
+
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter
+from researchx.adapters.local_storage import LocalStorageAdapter
+from researchx.adapters.secrets import EnvFileSecretsProvider
+from researchx.adapters.tavily import TavilySearchAdapter
+from researchx.adapters.types import AdapterError, ChatResult, ModelMessage
+from researchx.engine.actor import RunActor, make_run_config
+from researchx.engine.events import EventBus
+from researchx.engine.run_state import Plan, RunState
+from researchx.engine.states import RunStateName
+from researchx.evidence.store import EvidenceStore
+from researchx.methodologies import registry
+from researchx.trust.anchoring import anchor_quote, extract_quotes_from_report
+
+
+class RecordingModel:
+    def __init__(self, canned: list[ChatResult]) -> None:
+        self._canned = list(canned)
+        self.prompts: list[str] = []
+
+    async def chat(
+        self, messages: list[ModelMessage], *, model: str, temperature: float = 0.2,
+        json_mode: bool = False,
+    ) -> ChatResult:
+        self.prompts.append(messages[0].content)
+        return self._canned.pop(0)
+
+    async def list_models(self) -> list[str]:
+        return ["fake-model"]
+
+    def roles(self):
+        from researchx.adapters.model import ModelRoles
+
+        return ModelRoles(planner="fake-planner", writer="fake-writer")
+
+
+_PLAN = json.dumps({"sub_questions": ["verification"], "source_universe": ["web"], "outline": []})
+
+
+async def test_evidence_reaches_writer_prompt(tmp_path: Path) -> None:
+    _rid, config = make_run_config(
+        question="q", context="", methodology_slug="rapid-answer",
+        overrides={}, registry=registry, run_id="abcd2345",
+    )
+    model = RecordingModel(
+        canned=[
+            ChatResult(content=_PLAN, model="fake-planner"),
+            ChatResult(content="# Report\n\nClaim [p-1].\n", model="fake-writer"),
+        ]
+    )
+    actor = RunActor(
+        run_config=config,
+        model=model,  # type: ignore[arg-type]
+        search=FakeSearchAdapter(CORPUS),
+        storage=LocalStorageAdapter(base_dir=tmp_path),
+        registry=registry,
+        event_bus=EventBus(),
+    )
+    task = asyncio.create_task(actor.run())
+    while actor.state.state == RunStateName.PLANNING:
+        await asyncio.sleep(0.01)
+    await actor.approve()
+    await task
+
+    writer_prompt = model.prompts[-1]
+    assert "[p-1]" in writer_prompt
+    assert "(https://example.org/" in writer_prompt
+    assert "Evidence passages:" in writer_prompt
+
+
+async def test_engine_refuses_private_urls_at_extract(tmp_path: Path, monkeypatch) -> None:
+    env_file = tmp_path / ".env.secrets"
+    env_file.write_text("TAVILY_API_KEY=t-key\n", encoding="utf-8")
+    secrets = EnvFileSecretsProvider(paths=[env_file])
+    tavily = TavilySearchAdapter(secrets)
+
+    called_urls: list[str] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        called_urls.append(str(request.url))
+        return httpx.Response(200, text="<html><body>never</body></html>")
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kw: original(transport=transport, **kw))
+
+    with pytest.raises(AdapterError, match="fetch refused"):
+        await tavily.fetch("http://169.254.169.254/latest/meta-data")
+    assert called_urls == []
+
+
+async def test_resume_from_searching_mid_run(tmp_path: Path) -> None:
+    _rid, config = make_run_config(
+        question="q", context="", methodology_slug="rapid-answer",
+        overrides={}, registry=registry, run_id="abcd2345",
+    )
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    mid_state = RunState(
+        run_id="abcd2345",
+        question="q",
+        methodology_slug="rapid-answer",
+        state=RunStateName.SEARCHING,
+        plan=Plan(sub_questions=["verification"], source_universe=["web"], outline=[]),
+        depth_cursor=0,
+        depth_target=1,
+    )
+    await storage.write_run_artifact("abcd2345", "state.json", mid_state.model_dump_json())
+
+    model = RecordingModel(
+        canned=[
+            ChatResult(content="# Report\n\nClaim [p-1].\n", model="fake-writer"),
+        ]
+    )
+    actor = RunActor(
+        run_config=config,
+        model=model,  # type: ignore[arg-type]
+        search=FakeSearchAdapter(CORPUS),
+        storage=storage,
+        registry=registry,
+        event_bus=EventBus(),
+    )
+    actor.state = RunState.model_validate_json(
+        await storage.read_run_artifact("abcd2345", "state.json")
+    )
+    state = await actor.run()
+    assert state.state == RunStateName.DONE
+
+
+async def test_cancel_after_approval_persists_cancelled(tmp_path: Path) -> None:
+    _rid, config = make_run_config(
+        question="q", context="", methodology_slug="rapid-answer",
+        overrides={}, registry=registry, run_id="abcd2345",
+    )
+    model = FakeModelAdapter(
+        canned=[
+            ChatResult(content=_PLAN, model="fake-planner"),
+            ChatResult(content="# Report\n\nClaim [p-1].\n", model="fake-writer"),
+        ]
+    )
+    actor = RunActor(
+        run_config=config,
+        model=model,
+        search=FakeSearchAdapter(CORPUS),
+        storage=LocalStorageAdapter(base_dir=tmp_path),
+        registry=registry,
+        event_bus=EventBus(),
+    )
+    task = asyncio.create_task(actor.run())
+    while actor.state.state == RunStateName.PLANNING:
+        await asyncio.sleep(0.01)
+    await actor.approve()
+    actor.pause()
+    actor.cancel()
+    with pytest.raises(asyncio.CancelledError):
+        await task
+    saved = json.loads(
+        await LocalStorageAdapter(base_dir=tmp_path).read_run_artifact("abcd2345", "state.json")
+    )
+    assert saved["state"] == "CANCELLED"
+
+
+def test_quote_mismatch_flagged_in_ledger_path() -> None:
+    store = EvidenceStore()
+    real_passage = store.add_passage("https://a", "The verified sentence about anchoring " * 5)
+    hallucinated = "This quote was never in any stored passage at all whatsoever."
+
+    verdict = anchor_quote(hallucinated, [real_passage])
+    assert verdict.matched is False
+    assert verdict.weak is False
+
+    good = anchor_quote(real_passage.quote, [real_passage])
+    assert good.matched is True
+
+    report = f"Claim [p-1].\n\n> {hallucinated} [p-1]\n"
+    quotes = extract_quotes_from_report(report, store)
+    assert len(quotes) == 2
+    bad_verdict = anchor_quote(hallucinated, store.writer_context())
+    assert bad_verdict.matched is False
+
+
+def test_ledger_export_gate() -> None:
+    from researchx.trust.ledger import build_ledger, liveness_export_gate
+    from researchx.trust.liveness import LivenessStatus
+
+    store = EvidenceStore()
+    stored_text = "The verified sentence used for the export gate test."
+    store.add_passage("https://a", stored_text)
+    ledger = build_ledger(
+        run_id="abcd2345",
+        report_text=f"{stored_text} [p-1]",
+        evidence=store,
+        liveness={"https://a": LivenessStatus.LIVE},
+        visited_at=datetime.now(UTC),
+    )
+    passed, failures = liveness_export_gate(ledger)
+    assert passed is True
+    assert failures == []
+
+    ledger_dead = build_ledger(
+        run_id="abcd2345",
+        report_text=f"{stored_text} [p-1]",
+        evidence=store,
+        liveness={"https://a": LivenessStatus.DEAD},
+        visited_at=datetime.now(UTC),
+    )
+    passed, failures = liveness_export_gate(ledger_dead)
+    assert passed is False
+    assert failures == ["https://a"]

backend/tests/test_probe_wiring.py

@@ -0,0 +1,129 @@
+import asyncio
+import json
+from pathlib import Path
+
+import httpx
+import pytest
+
+from researchx.adapters.capability_probe import probe_model_adapter
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter
+from researchx.adapters.local_storage import LocalStorageAdapter
+from researchx.adapters.ollama import OllamaModelAdapter
+from researchx.adapters.secrets import EnvFileSecretsProvider
+from researchx.adapters.types import ChatResult
+from researchx.engine.actor import RunActor, make_run_config
+from researchx.engine.events import EventBus
+from researchx.engine.states import RunStateName
+from researchx.methodologies import registry
+
+
+async def test_probe_attaches_to_run_state(tmp_path: Path, monkeypatch) -> None:
+    env_file = tmp_path / ".env.secrets"
+    env_file.write_text("OLLAMA_API_KEY=cloud-key\n", encoding="utf-8")
+    secrets = EnvFileSecretsProvider(paths=[env_file])
+    adapter = OllamaModelAdapter(secrets, planner_model="p", writer_model="w")
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        if str(request.url).endswith("/models"):
+            return httpx.Response(200, json={"data": [{"id": "w"}]})
+        return httpx.Response(
+            200, json={"choices": [{"message": {"content": '{"ok": true}'}}]}
+        )
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kw: original(transport=transport, **kw))
+
+    probe = await probe_model_adapter(adapter)
+    assert probe.structured_outputs_supported is True
+
+    _rid, config = make_run_config(
+        question="q",
+        context="",
+        methodology_slug="rapid-answer",
+        overrides={},
+        registry=registry,
+        run_id="abcd2345",
+    )
+    plan = json.dumps({"sub_questions": ["verification"], "source_universe": ["web"], "outline": []})
+    writer = "# Report\n\nClaim [p-1].\n"
+    fake_model = FakeModelAdapter(
+        canned=[
+            ChatResult(content=plan, model="fake-planner"),
+            ChatResult(content=writer, model="fake-writer"),
+        ]
+    )
+    actor = RunActor(
+        run_config=config,
+        model=fake_model,
+        search=FakeSearchAdapter(CORPUS),
+        storage=LocalStorageAdapter(base_dir=tmp_path),
+        registry=registry,
+        event_bus=EventBus(),
+    )
+    await actor.attach_probe(probe.model_dump(mode="json"))
+    assert actor.state.probe is not None
+    assert actor.state.probe["structured_outputs_supported"] is True
+
+    task = asyncio.create_task(actor.run())
+    while actor.state.state == RunStateName.PLANNING:
+        await asyncio.sleep(0.01)
+    await actor.approve()
+    state = await task
+    assert state.state == RunStateName.DONE
+    saved = json.loads(
+        await LocalStorageAdapter(base_dir=tmp_path).read_run_artifact("abcd2345", "state.json")
+    )
+    assert saved["probe"]["endpoint"] == "https://ollama.com/v1"
+
+
+async def test_probe_failure_never_crashes_the_run(tmp_path: Path, monkeypatch) -> None:
+    env_file = tmp_path / ".env.secrets"
+    env_file.write_text("OLLAMA_API_KEY=cloud-key\n", encoding="utf-8")
+    secrets = EnvFileSecretsProvider(paths=[env_file])
+    adapter = OllamaModelAdapter(secrets, planner_model="p", writer_model="w")
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(500, text="down")
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kw: original(transport=transport, **kw))
+
+    from researchx.adapters.types import AdapterError
+
+    with pytest.raises(AdapterError):
+        await probe_model_adapter(adapter)
+
+    _rid, config = make_run_config(
+        question="q",
+        context="",
+        methodology_slug="rapid-answer",
+        overrides={},
+        registry=registry,
+        run_id="abcd2345",
+    )
+    plan = json.dumps({"sub_questions": ["verification"], "source_universe": ["web"], "outline": []})
+    writer = "# Report\n\nClaim [p-1].\n"
+    fake_model = FakeModelAdapter(
+        canned=[
+            ChatResult(content=plan, model="fake-planner"),
+            ChatResult(content=writer, model="fake-writer"),
+        ]
+    )
+    bus = EventBus()
+    actor = RunActor(
+        run_config=config,
+        model=fake_model,
+        search=FakeSearchAdapter(CORPUS),
+        storage=LocalStorageAdapter(base_dir=tmp_path),
+        registry=registry,
+        event_bus=bus,
+    )
+    task = asyncio.create_task(actor.run())
+    while actor.state.state == RunStateName.PLANNING:
+        await asyncio.sleep(0.01)
+    await actor.approve()
+    state = await task
+    assert state.state == RunStateName.DONE
+    assert state.probe is None

backend/tests/test_real_adapters.py

@@ -0,0 +1,203 @@
+import httpx
+import pytest
+
+from researchx.adapters.duckduckgo import DuckDuckGoSearchAdapter
+from researchx.adapters.model import ModelRoles
+from researchx.adapters.ollama import OllamaModelAdapter
+from researchx.adapters.probe import CapabilityProbe, cap_context_window, structured_output_warning
+from researchx.adapters.secrets import EnvFileSecretsProvider
+from researchx.adapters.tavily import TavilySearchAdapter
+from researchx.adapters.types import AdapterError, ModelMessage
+
+
+def _secrets(tmp_path, values: dict[str, str]) -> EnvFileSecretsProvider:
+    env_file = tmp_path / ".env.secrets"
+    env_file.write_text(
+        "".join(f"{k}={v}\n" for k, v in values.items()),
+        encoding="utf-8",
+    )
+    return EnvFileSecretsProvider(paths=[env_file])
+
+
+def _chat_payload_ok() -> dict[str, object]:
+    return {
+        "choices": [{"message": {"role": "assistant", "content": '{"ok": true}'}}],
+        "usage": {"prompt_tokens": 10, "completion_tokens": 5},
+    }
+
+
+async def test_ollama_adapter_uses_cloud_when_keyed(tmp_path, monkeypatch) -> None:
+    secrets = _secrets(tmp_path, {"OLLAMA_API_KEY": "cloud-key"})
+    adapter = OllamaModelAdapter(secrets, planner_model="p", writer_model="w")
+
+    calls: list[tuple[str, dict[str, str]]] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        calls.append((str(request.url), dict(request.headers)))
+        return httpx.Response(200, json=_chat_payload_ok())
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    result = await adapter.chat([ModelMessage(role="user", content="hi")], model="w")
+    assert result.content == '{"ok": true}'
+    assert calls[0][0].startswith("https://ollama.com/v1")
+    assert "Bearer cloud-key" in calls[0][1]["authorization"]
+
+
+async def test_ollama_adapter_falls_back_to_local_on_cloud_failure(tmp_path, monkeypatch) -> None:
+    secrets = _secrets(tmp_path, {"OLLAMA_API_KEY": "cloud-key"})
+    adapter = OllamaModelAdapter(secrets, planner_model="p", writer_model="w")
+
+    bases_hit: list[str] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        url = str(request.url)
+        bases_hit.append(url)
+        if url.startswith("https://ollama.com"):
+            return httpx.Response(401, json={"error": "bad key"})
+        return httpx.Response(200, json=_chat_payload_ok())
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    result = await adapter.chat([ModelMessage(role="user", content="hi")], model="w")
+    assert result.content == '{"ok": true}'
+    assert any(u.startswith("http://localhost:11434/v1") for u in bases_hit)
+    assert adapter.last_fallback_reason is not None
+    assert adapter.active_base_url == "http://localhost:11434/v1"
+
+
+async def test_ollama_roles(tmp_path) -> None:
+    secrets = _secrets(tmp_path, {})
+    adapter = OllamaModelAdapter(secrets, planner_model="planner-model", writer_model="writer-model")
+    assert adapter.roles() == ModelRoles(planner="planner-model", writer="writer-model")
+
+
+def test_context_cap() -> None:
+    assert cap_context_window(None) == 8192
+    assert cap_context_window(100_000) == 8192
+    assert cap_context_window(4_096) == 4_096
+    assert cap_context_window(0) == 8192
+
+
+def test_structured_output_warning_contract() -> None:
+    assert structured_output_warning(True, "m") is None
+    warning = structured_output_warning(False, "writer-model")
+    assert warning is not None
+    assert "writer-model" in warning
+    assert "degrade" in warning
+    probe = CapabilityProbe(
+        endpoint="http://localhost:11434/v1",
+        models=["m"],
+        context_window=8192,
+        embedding_batch=8,
+        structured_outputs_supported=False,
+        structured_output_warning=warning,
+    )
+    assert probe.degraded
+
+
+async def test_tavily_requires_key(tmp_path) -> None:
+    secrets = _secrets(tmp_path, {})
+    with pytest.raises(AdapterError):
+        TavilySearchAdapter(secrets)
+
+
+async def test_tavily_search_returns_results(tmp_path, monkeypatch) -> None:
+    secrets = _secrets(tmp_path, {"TAVILY_API_KEY": "t-key"})
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        import json
+
+        body = json.loads(request.content.decode())
+        assert body["api_key"] == "t-key"
+        return httpx.Response(
+            200,
+            json={
+                "results": [
+                    {"title": "T1", "url": "https://example.org/a", "content": "snippet one"},
+                    {"title": "T2", "url": "https://example.org/b", "content": "snippet two"},
+                ]
+            },
+        )
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    adapter = TavilySearchAdapter(secrets)
+    results = await adapter.search("deep research", max_results=2)
+    assert [r.title for r in results] == ["T1", "T2"]
+
+
+async def test_ddg_parses_html_results(monkeypatch) -> None:
+    html = """
+    <div class="results">
+      <a rel="nofollow" class="result__a" href="//duckduckgo.com/l/?uddg=https%3A%2F%2Fexample.org%2Fx&amp;rut=abc">Example One</a>
+      <a class="result__snippet" href="#">First snippet text</a>
+      <a rel="nofollow" class="result__a" href="https://example.org/y">Example Two</a>
+      <a class="result__snippet" href="#">Second snippet text</a>
+    </div>
+    """
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(200, text=html)
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    adapter = DuckDuckGoSearchAdapter()
+    results = await adapter.search("anything", max_results=8)
+    assert [r.url for r in results] == ["https://example.org/x", "https://example.org/y"]
+    assert results[0].snippet == "First snippet text"
+    assert adapter.last_degradation is None
+
+
+async def test_ddg_rate_limit_degrades_with_typed_warning(monkeypatch) -> None:
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(403, text="forbidden")
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    adapter = DuckDuckGoSearchAdapter()
+    results = await adapter.search("anything")
+    assert results == []
+    assert adapter.last_degradation is not None
+    assert "rate-limited" in adapter.last_degradation
+
+
+async def test_ddg_fetch_extracts_text(monkeypatch) -> None:
+    html = "<html><head><title>Page Title</title></head><body><script>var x=1;</script><p>Hello world</p></body></html>"
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(200, text=html)
+
+    transport = httpx.MockTransport(handler)
+    original = httpx.AsyncClient
+    monkeypatch.setattr(httpx, "AsyncClient", lambda **kwargs: original(transport=transport, **kwargs))
+
+    adapter = DuckDuckGoSearchAdapter()
+    page = await adapter.fetch("https://example.org/x")
+    assert page.title == "Page Title"
+    assert "Hello world" in page.text
+    assert "var x" not in page.text
+
+
+def test_resolve_search_adapter_prefers_tavily(tmp_path) -> None:
+    from researchx.adapters.duckduckgo import resolve_search_adapter
+
+    keyed = _secrets(tmp_path, {"TAVILY_API_KEY": "t-key"})
+    adapter, name = resolve_search_adapter(keyed)
+    assert name == "tavily"
+    assert isinstance(adapter, TavilySearchAdapter)
+
+    keyless = _secrets(tmp_path, {})
+    adapter, name = resolve_search_adapter(keyless)
+    assert name == "duckduckgo-keyless"
+    assert isinstance(adapter, DuckDuckGoSearchAdapter)

backend/tests/test_resume.py

@@ -0,0 +1,105 @@
+import json
+from pathlib import Path
+
+from researchx.adapters.fakes import CORPUS, FakeModelAdapter, FakeSearchAdapter
+from researchx.adapters.local_storage import LocalStorageAdapter
+from researchx.adapters.types import ChatResult
+from researchx.engine.actor import RunActor, make_run_config
+from researchx.engine.events import EventBus
+from researchx.engine.run_state import Plan, RunState
+from researchx.engine.states import RunStateName
+from researchx.methodologies import registry
+
+_PLAN = json.dumps(
+    {
+        "sub_questions": ["verification passes"],
+        "source_universe": ["web"],
+        "outline": ["intro"],
+    }
+)
+_WRITER = "# Report\n\nClaim [p-1] and claim [p-2].\n"
+
+
+def test_run_id_generator_is_the_storage_one() -> None:
+    from researchx.engine.actor import make_run_config as mrc
+
+    run_id, _ = mrc(
+        question="q", context="", methodology_slug="rapid-answer", overrides={}, registry=registry
+    )
+    assert len(run_id) == 8
+    alphabet = set("abcdefghjkmnpqrstuvwxyz23456789")
+    assert all(c in alphabet for c in run_id)
+
+
+async def test_state_file_round_trip_enables_restart(tmp_path: Path) -> None:
+    run_id, config = make_run_config(
+        question="How do engines resume?",
+        context="",
+        methodology_slug="rapid-answer",
+        overrides={},
+        registry=registry,
+        run_id="abcd2345",
+    )
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    state = RunState(
+        run_id=run_id,
+        question=config.question,
+        methodology_slug="rapid-answer",
+        state=RunStateName.SEARCHING,
+        depth_cursor=1,
+        depth_target=3,
+    )
+    await storage.write_run_artifact(run_id, "state.json", state.model_dump_json())
+
+    restored = RunState.model_validate_json(
+        await storage.read_run_artifact(run_id, "state.json")
+    )
+    assert restored.depth_cursor == 1
+    assert restored.depth_target == 3
+    assert restored.state == RunStateName.SEARCHING
+
+
+async def test_actor_resumes_from_restored_state(tmp_path: Path) -> None:
+    run_id, config = make_run_config(
+        question="How do engines resume?",
+        context="",
+        methodology_slug="rapid-answer",
+        overrides={},
+        registry=registry,
+        run_id="abcd2345",
+    )
+    storage = LocalStorageAdapter(base_dir=tmp_path)
+    mid_state = RunState(
+        run_id=run_id,
+        question=config.question,
+        methodology_slug="rapid-answer",
+        state=RunStateName.AWAITING_APPROVAL,
+        depth_cursor=0,
+        depth_target=1,
+        plan=Plan(sub_questions=["verification passes"], source_universe=["web"], outline=["intro"]),
+    )
+    await storage.write_run_artifact(run_id, "state.json", mid_state.model_dump_json())
+
+    model = FakeModelAdapter(
+        canned=[
+            ChatResult(content=_PLAN, model="fake-planner"),
+            ChatResult(content=_WRITER, model="fake-writer"),
+        ]
+    )
+    actor = RunActor(
+        run_config=config,
+        model=model,
+        search=FakeSearchAdapter(CORPUS),
+        storage=storage,
+        registry=registry,
+        event_bus=EventBus(),
+    )
+    restored = RunState.model_validate_json(
+        await storage.read_run_artifact(run_id, "state.json")
+    )
+    actor.state = restored
+    await actor.approve()
+    state = await actor.run()
+    assert state.state == RunStateName.DONE
+    assert state.plan is not None
+    assert state.plan.sub_questions == ["verification passes"]

backend/tests/test_run_config.py

@@ -0,0 +1,96 @@
+from datetime import UTC, datetime
+
+import pytest
+from pydantic import ValidationError
+
+from researchx.config.dials import Dials
+from researchx.config.run_config import (
+    RunConfig,
+    UnknownOverrideError,
+    new_run_id,
+    resolve_dials,
+)
+from researchx.methodologies import registry
+
+
+def test_resolve_applies_overrides_on_top_of_bundle() -> None:
+    resolved = resolve_dials("deep-report", {"depth": 1, "checkpoints": False}, registry)
+    assert resolved.depth == 1
+    assert resolved.checkpoints is False
+    assert resolved.breadth == 2
+    assert resolved.verification_passes == 2
+
+
+def test_resolve_empty_overrides_returns_bundle() -> None:
+    resolved = resolve_dials("rapid-answer", {}, registry)
+    assert resolved == registry.get("rapid-answer").dials
+
+
+def test_resolve_rejects_unknown_override_keys() -> None:
+    with pytest.raises(UnknownOverrideError):
+        resolve_dials("rapid-answer", {"temperature": 0.7}, registry)
+
+
+def test_resolve_rejects_invalid_override_values() -> None:
+    with pytest.raises(ValidationError):
+        resolve_dials("rapid-answer", {"depth": 9}, registry)
+    with pytest.raises(ValidationError):
+        resolve_dials("deep-report", {"synthesis_style": "poetic"}, registry)
+
+
+def test_resolve_does_not_mutate_registry_bundle() -> None:
+    resolve_dials("deep-report", {"depth": 1}, registry)
+    assert registry.get("deep-report").dials.depth == 3
+
+
+def _run_config(**overrides: object) -> RunConfig:
+    return RunConfig(
+        run_id=new_run_id(),
+        methodology_slug="deep-report",
+        question="What changed in the market?",
+        context="Q3 earnings season",
+        resolved_dials=resolve_dials("deep-report", overrides, registry),
+        created_at=datetime.now(UTC),
+        overrides=dict(overrides),
+    )
+
+
+def test_run_config_accepts_valid_id() -> None:
+    config = _run_config(depth=2)
+    assert config.run_id == "abcd1234" or len(config.run_id) == 8
+
+
+def test_run_config_rejects_invalid_run_id() -> None:
+    with pytest.raises(ValidationError):
+        RunConfig(
+            run_id="short",
+            methodology_slug="rapid-answer",
+            question="q",
+            resolved_dials=Dials(),
+            created_at=datetime.now(UTC),
+        )
+
+
+def test_run_config_rejects_empty_question() -> None:
+    with pytest.raises(ValidationError):
+        RunConfig(
+            run_id=new_run_id(),
+            methodology_slug="rapid-answer",
+            question="",
+            resolved_dials=Dials(),
+            created_at=datetime.now(UTC),
+        )
+
+
+def test_run_config_snapshot_round_trips_json() -> None:
+    config = _run_config(depth=2, checkpoints=False)
+    restored = RunConfig.model_validate_json(config.model_dump_json())
+    assert restored == config
+    assert restored.resolved_dials.depth == 2
+    assert restored.overrides == {"depth": 2, "checkpoints": False}
+
+
+def test_run_config_is_immutable() -> None:
+    config = _run_config()
+    with pytest.raises(ValidationError):
+        config.question = "different"

backend/tests/test_secrets.py

@@ -0,0 +1,46 @@
+from pathlib import Path
+
+from researchx.adapters.secrets import EnvFileSecretsProvider, SecretsProvider
+
+
+def test_secrets_provider_conformance(tmp_path: Path) -> None:
+    env_file = tmp_path / ".env.secrets"
+    env_file.write_text("OLLAMA_API_KEY=test-key-value\n", encoding="utf-8")
+    provider = EnvFileSecretsProvider(paths=[env_file])
+    assert isinstance(provider, SecretsProvider)
+    assert provider.resolve("OLLAMA_API_KEY") == "test-key-value"
+    assert provider.resolve("MISSING_VAR") is None
+
+
+def test_secrets_later_file_wins(tmp_path: Path) -> None:
+    first = tmp_path / ".env"
+    second = tmp_path / ".env.secrets"
+    first.write_text("TAVILY_API_KEY=first-key\nOLLAMA_API_KEY=ollama-first\n", encoding="utf-8")
+    second.write_text("OLLAMA_API_KEY=ollama-second\n", encoding="utf-8")
+    provider = EnvFileSecretsProvider(paths=[first, second])
+    assert provider.resolve("TAVILY_API_KEY") == "first-key"
+    assert provider.resolve("OLLAMA_API_KEY") == "ollama-second"
+
+
+def test_secrets_parse_skips_comments_and_blanks(tmp_path: Path) -> None:
+    env_file = tmp_path / ".env"
+    env_file.write_text(
+        "# comment line\n\nGITEA_TOKEN='quoted-token'\nBROKEN_LINE_NO_EQUALS\n",
+        encoding="utf-8",
+    )
+    provider = EnvFileSecretsProvider(paths=[env_file])
+    assert provider.resolve("GITEA_TOKEN") == "quoted-token"
+    assert provider.resolve("BROKEN_LINE_NO_EQUALS") is None
+
+
+def test_secrets_repr_never_leaks_values(tmp_path: Path) -> None:
+    env_file = tmp_path / ".env.secrets"
+    env_file.write_text("OLLAMA_API_KEY=super-secret-value-123\n", encoding="utf-8")
+    provider = EnvFileSecretsProvider(paths=[env_file])
+    assert "super-secret-value-123" not in repr(provider)
+    assert "super-secret-value-123" not in str(provider)
+
+
+def test_secrets_missing_file_ignored(tmp_path: Path) -> None:
+    provider = EnvFileSecretsProvider(paths=[tmp_path / ".env.absent"])
+    assert provider.resolve("ANY_KEY") is None

backend/tests/test_smoke.py

@@ -0,0 +1,5 @@
+import researchx
+
+
+def test_package_imports() -> None:
+    assert researchx.__name__ == "researchx"

backend/tests/test_trust.py

@@ -0,0 +1,159 @@
+from datetime import UTC, datetime
+
+import httpx
+
+from researchx.adapters.fakes import CORPUS, SHARED_SENTENCE
+from researchx.evidence.store import EvidenceStore
+from researchx.trust.anchoring import anchor_quote, normalize
+from researchx.trust.ledger import build_ledger, export_checklist
+from researchx.trust.liveness import LivenessStatus, check_liveness, liveness_report, url_allowed
+
+
+def test_normalize_pipeline() -> None:
+    assert normalize("  Foo   Bar  ") == "foo bar"
+    assert normalize("Café") == normalize("café")
+
+
+def test_anchor_exact_substring_short_circuits() -> None:
+    store = EvidenceStore()
+    passage = store.add_passage("https://a", SHARED_SENTENCE)
+    verdict = anchor_quote(SHARED_SENTENCE, [passage])
+    assert verdict.matched is True
+    assert verdict.ratio == 1.0
+    assert verdict.weak is False
+
+
+def test_anchor_weak_match_flagged() -> None:
+    store = EvidenceStore()
+    passage = store.add_passage("https://a", SHARED_SENTENCE)
+    mutated = SHARED_SENTENCE.replace(
+        "The verification pass re-anchored every quoted claim",
+        "A liveness check validated the cited evidence",
+    )
+    verdict = anchor_quote(mutated, [passage])
+    assert verdict.ratio < 0.85
+
+
+def test_anchor_high_fuzzy_match() -> None:
+    store = EvidenceStore()
+    passage = store.add_passage("https://a", "The pipeline verifies every quoted claim against its stored passage before shipping.")
+    near = "The pipeline verify every quoted claim against its stored passage before shipping."
+    verdict = anchor_quote(near, [passage])
+    assert verdict.ratio >= 0.85
+    assert verdict.matched is True
+
+
+def test_anchor_no_match_returns_unmatched() -> None:
+    store = EvidenceStore()
+    passage = store.add_passage("https://a", SHARED_SENTENCE)
+    verdict = anchor_quote("completely unrelated text about something else entirely", [passage])
+    assert verdict.matched is False
+    assert verdict.weak is False
+    assert verdict.passage_id is None
+
+
+def test_url_guard_blocks_private_and_schemes() -> None:
+    assert url_allowed("http://169.254.169.254/latest/meta-data") is False
+    assert url_allowed("http://localhost:8000/api") is False
+    assert url_allowed("http://127.0.0.1/x") is False
+    assert url_allowed("http://10.0.0.1/x") is False
+    assert url_allowed("file:///etc/passwd") is False
+    assert url_allowed("ftp://example.org/x") is False
+    assert url_allowed("not a url") is False
+
+
+async def test_liveness_classification_live(monkeypatch) -> None:
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(200, text="alive page")
+
+    transport = httpx.MockTransport(handler)
+    async with httpx.AsyncClient(transport=transport, follow_redirects=True) as client:
+        status = await check_liveness("https://example.org/live", client)
+    assert status == LivenessStatus.LIVE
+
+
+async def test_liveness_dead_on_error(monkeypatch) -> None:
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(500, text="boom")
+
+    transport = httpx.MockTransport(handler)
+    async with httpx.AsyncClient(transport=transport) as client:
+        status = await check_liveness("https://example.org/dead", client)
+    assert status == LivenessStatus.DEAD
+
+
+async def test_liveness_report_dedupes_and_covers() -> None:
+    report = await liveness_report(["https://a", "https://a", "https://b"])
+    assert report["https://a"] == LivenessStatus.DEAD
+    assert len(report) == 2
+
+
+async def test_liveness_blocked_url_reports_dead() -> None:
+    status = await check_liveness("http://169.254.169.254/latest/meta-data")
+    assert status == LivenessStatus.DEAD
+
+
+def _store_with_report() -> tuple[EvidenceStore, str]:
+    store = EvidenceStore()
+    for page in CORPUS[:3]:
+        store.add_page(page.url, page.title, page.text)
+    first_passage = store.pages()[0].passage_ids[0]
+    stored = store.get(first_passage)
+    sentence = (stored.text if stored else "").split(".")[0] + "."
+    report = f"# Report\n\n{sentence} [{first_passage}]\n\nMore context [{first_passage}]\n"
+    return store, report
+
+
+async def test_ledger_build_and_checklist_export(monkeypatch) -> None:
+    store, report = _store_with_report()
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(200, text="ok")
+
+    transport = httpx.MockTransport(handler)
+    async with httpx.AsyncClient(transport=transport, follow_redirects=True) as client:
+        liveness = {}
+        for page in store.pages():
+            liveness[page.url] = await check_liveness(page.url, client)
+
+    ledger = build_ledger(
+        run_id="abcd2345",
+        report_text=report,
+        evidence=store,
+        liveness=liveness,
+        visited_at=datetime.now(UTC),
+    )
+    assert ledger.run_id == "abcd2345"
+    cited_url = store.pages()[0].url
+    assert [e.url for e in ledger.entries] == [cited_url]
+    assert ledger.checklist.citations_checked == 1
+    assert ledger.checklist.live == 1
+    assert ledger.checklist.dead == 0
+    assert ledger.checklist.anchored_claims >= 1
+    assert all(
+        entry.authority_tier in ("reference", "official", "academic", "general")
+        for entry in ledger.entries
+    )
+
+    checklist = export_checklist(ledger)
+    assert "Verification Checklist" in checklist
+    assert "Live:" in checklist
+    assert "Weak matches" in checklist
+
+
+def test_ledger_confidence_labels_single_vs_corroborated() -> None:
+    store = EvidenceStore()
+    store.add_passage("https://a", SHARED_SENTENCE)
+    store.add_passage("https://b", SHARED_SENTENCE)
+    report = "[p-1] [p-2]"
+    ledger = build_ledger(
+        run_id="abcd2345",
+        report_text=report,
+        evidence=store,
+        liveness={"https://a": LivenessStatus.LIVE, "https://b": LivenessStatus.LIVE},
+        visited_at=datetime.now(UTC),
+    )
+    labels = ledger.checklist.confidence_labels
+    assert len(labels) == 2
+    corroborated = [v for v in labels.values() if v == "corroborated"]
+    assert len(corroborated) >= 1

backend/uv.lock

@@ -0,0 +1,630 @@
+version = 1
+revision = 3
+requires-python = ">=3.12"
+resolution-markers = [
+    "python_full_version >= '3.15'",
+    "python_full_version < '3.15'",
+]
+
+[[package]]
+name = "annotated-types"
+version = "0.8.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/5f/56/a8120250d128bed162cd73c76d45f6ef9991f3e068f62a8ee060afa3104a/annotated_types-0.8.0.tar.gz", hash = "sha256:13b2beaad985e05e2d6407ee4c4f35590b11f8d693a258a561055cac8f64cab7", size = 15893, upload-time = "2026-07-23T20:16:13.995Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/99/91/8acff4f5e50511b911bbccb72b8628a49c68ce14148cd9f6431094859a90/annotated_types-0.8.0-py3-none-any.whl", hash = "sha256:f072f4d804ea359e4eaf198b1af7a8b0943881a87f31bb764f8bf219bb9419e0", size = 13427, upload-time = "2026-07-23T20:16:12.938Z" },
+]
+
+[[package]]
+name = "anyio"
+version = "4.15.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "idna" },
+    { name = "typing-extensions", marker = "python_full_version < '3.15'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a9/d2/f4d173e22df740bc37b1db102b386ba719b66e95b0f0d751f556b387e6d2/anyio-4.15.1.tar.gz", hash = "sha256:9f28306018cbd6d329e64a36d58256edff76dd996fe423bc957326e578b82a94", size = 276966, upload-time = "2026-09-05T10:42:39.44Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/12/b8/4bd346e22b28902df4d651910f5242c28d84e4a5c2435ca5c3f797ed7e2e/anyio-4.15.1-py3-none-any.whl", hash = "sha256:6152fdbbf9a77fdec97731721bebf7c4c44f7c29b424b0065826173efc7ed101", size = 132079, upload-time = "2026-09-05T10:42:37.923Z" },
+]
+
+[[package]]
+name = "ast-serialize"
+version = "0.11.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/54/1e/4f6082cdd6e5a29093513e9a3eabc5ed1c5331a9a84386b2fece80a00a48/ast_serialize-0.11.2.tar.gz", hash = "sha256:976a5bd75845d22f4b52905ddf53ab669ef1b14dba7735f5512841a2ef2b5450", size = 954387, upload-time = "2026-09-13T18:48:55.673Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a3/2e/beec3364eef4b01793a676d8cd16e9014c42044a5505000ceae3955e33fa/ast_serialize-0.11.2-cp314-cp314-pyemscripten_2026_0_wasm32.whl", hash = "sha256:f6a8dfc5ab204a706f6e5d39c6f77c18c27ef084fa2081803a64a9160ce89277", size = 897089, upload-time = "2026-09-13T18:47:22.69Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/d7/ef56443df2891c6ba2c4019c2cb3dcaf97c9948da6d963068e04e8dac6ea/ast_serialize-0.11.2-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:cb073bfa15742699d408ac50f60878383b5665ae1791d1b6799ea6f08633cd77", size = 1235218, upload-time = "2026-09-13T18:47:24.541Z" },
+    { url = "https://files.pythonhosted.org/packages/42/8d/cff58d17ba1d0272ff0b7ab5d3bdfcf8f47317eb0f47c001d394bffebf95/ast_serialize-0.11.2-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:1d6ad94edbe93bf1dabc06c9f37d55b898fdabc456aa6d7ced5e23c14f795f32", size = 1216399, upload-time = "2026-09-13T18:47:26.202Z" },
+    { url = "https://files.pythonhosted.org/packages/de/d2/a1da7675af5f42335c36e4da6d86ef4fd7168cead18de81df0a2d6faeb1a/ast_serialize-0.11.2-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:40b2801cf2221bd922d9f69d2f0ebc373c3db47207315d525b2d87fa161a2af4", size = 1282064, upload-time = "2026-09-13T18:47:27.787Z" },
+    { url = "https://files.pythonhosted.org/packages/97/89/5a400a13b2c9c0152ebb5ad45408a3fe5e4e60e325d3ac4e5cf6e915a0cc/ast_serialize-0.11.2-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fd666cebd6ab3b3c0fd348a6202c26e18a401ee34293c3804d3472266bc146f6", size = 1285864, upload-time = "2026-09-13T18:47:29.667Z" },
+    { url = "https://files.pythonhosted.org/packages/02/b8/80a381c70fd49f0316fb0383c4f9e4c13e81b010b64889bd45898ce8f5f4/ast_serialize-0.11.2-cp314-cp314t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0d01f61352c96370febf6c0dbd488dee9183a731fb2702170da9163ae317cded", size = 1554755, upload-time = "2026-09-13T18:47:31.257Z" },
+    { url = "https://files.pythonhosted.org/packages/90/97/dcaa34a32d2db789221c125b3eb10feb5089715fe53d9874d627afc26231/ast_serialize-0.11.2-cp314-cp314t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a0fd40c668b0fa19b8fdb61d9e63d547e2e19cfbfe053a51ef0b6c37070298a8", size = 1301807, upload-time = "2026-09-13T18:47:32.714Z" },
+    { url = "https://files.pythonhosted.org/packages/5c/9a/84a22420cb312642d7d31547c644d09a3d101418c6d6b9ef2ec30735cf11/ast_serialize-0.11.2-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:efa819d7c14c8e4153dcd84671826331538be7cbe460383fc6386f5eea5bd234", size = 1301941, upload-time = "2026-09-13T18:47:34.418Z" },
+    { url = "https://files.pythonhosted.org/packages/20/8a/aa5f3dcf1aed9678c25982f40d366004e3c0cac47bc0c240f6b837dcbb1f/ast_serialize-0.11.2-cp314-cp314t-manylinux_2_31_riscv64.whl", hash = "sha256:a9ffa8a197a721f07a352d0be6185f5b3e6f9aaebfdb66169ed652108531ae3b", size = 1307910, upload-time = "2026-09-13T18:47:36.253Z" },
+    { url = "https://files.pythonhosted.org/packages/78/79/91a5102797fe3dc992171382d8579bcb33cbd1424b864ad3117ac43fb3fe/ast_serialize-0.11.2-cp314-cp314t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:00119a8fb8c1dc0f1fab023f4d8071fa49e3b0208ee54d589fd463c16ab0124e", size = 1356258, upload-time = "2026-09-13T18:47:37.984Z" },
+    { url = "https://files.pythonhosted.org/packages/51/52/54eeef9918e187ced417c4363eecea66975314cd5b9c91759eef7f7b714b/ast_serialize-0.11.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:0de02520c11391a026e62987a9aa2c3c2ff01545155059ddf0c4bdf2c5ecbe9f", size = 1459057, upload-time = "2026-09-13T18:47:39.891Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/cb/fd84b52b15d42f2423319cffd1fb7f1e9df5d5198e69ab0b449c450254cf/ast_serialize-0.11.2-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:b4e4558956b6a0fb35e18fba58f7d1810b1f2c0e6b52352572cd5dfb6b4ef33a", size = 1562447, upload-time = "2026-09-13T18:47:41.727Z" },
+    { url = "https://files.pythonhosted.org/packages/be/92/9fb34f2e64b84a63cca92fb86bd0847b995a63b67477f44c20502fb60352/ast_serialize-0.11.2-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:6061a54f39e82a9f2cbcb9c268fc441890e4818a6636473caa4f4063254e0750", size = 1556423, upload-time = "2026-09-13T18:47:43.357Z" },
+    { url = "https://files.pythonhosted.org/packages/75/0f/c43c44449e7ebc4e83ebd48750088fb06234622faa2d62d2a6dc8970d2a3/ast_serialize-0.11.2-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:85fbb01e83967a126d71f679f2b9528ef0912cb0854aa1a4657314c34e255b57", size = 1687156, upload-time = "2026-09-13T18:47:44.995Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/a7/9e520f4a79b639da9ee20c1e747c3d739329e902fc55ac38065f25419f56/ast_serialize-0.11.2-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:7aaaffc32905159774a107d3cf33dad59bd41b7a0d1bc9885532186753ee7439", size = 1481008, upload-time = "2026-09-13T18:47:46.602Z" },
+    { url = "https://files.pythonhosted.org/packages/48/a8/bdd3989f19de09cffcd8179c131f6741a5a8619705fc75b09541ff61530b/ast_serialize-0.11.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:08eda88a0f290a36c38cab33df8bf7e35eb95bc802ca5beb2c8fcda471a7d10c", size = 1501597, upload-time = "2026-09-13T18:47:48.265Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/8a/ca2dce2950875a4ef1d7c298196f803b0adcdb7c15ed0cecc71d84bccd70/ast_serialize-0.11.2-cp314-cp314t-win32.whl", hash = "sha256:76cc294246e60a914326b4ca88c6a5ea89c064906614aaf1537ce82f09e9449f", size = 1119503, upload-time = "2026-09-13T18:47:49.896Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/12/3f38e3613d07c46f9f81c5b1352748c6552397cc52825502e2c6ae44c6ea/ast_serialize-0.11.2-cp314-cp314t-win_amd64.whl", hash = "sha256:43b51e6ebe6549bf21416c3c78ee886147b80875a87cc6f69e303dde0d75be0b", size = 1156828, upload-time = "2026-09-13T18:47:51.454Z" },
+    { url = "https://files.pythonhosted.org/packages/22/90/f89a4f67428a261daafdb69a0d0132c27933268702d1ba47e0b61c51aff1/ast_serialize-0.11.2-cp314-cp314t-win_arm64.whl", hash = "sha256:8df32ad4ff7843734a6c2f067ee974f6d3109ee5a2c3e1a9d2f79347bd282a9a", size = 1128298, upload-time = "2026-09-13T18:47:53.008Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/55/a1962188abf0e62d84d55892bb044347e434711763b9a1d4ad867a70c1be/ast_serialize-0.11.2-cp315-abi3.abi3t-macosx_10_12_x86_64.whl", hash = "sha256:ab924ba260efd7509492f272d4e236d24564033f20c005d7c63a107c6a76fc85", size = 1235457, upload-time = "2026-09-13T18:47:54.554Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/ad/439c2959150718446af76fbe2f4000f35eba9869ef8564f3d9a3d0b1c370/ast_serialize-0.11.2-cp315-abi3.abi3t-macosx_11_0_arm64.whl", hash = "sha256:a586be418eb70a9f1396cea29ddac8f4b9bf277fb73ea2340db31e218bc00f32", size = 1215705, upload-time = "2026-09-13T18:47:56.178Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/d8/2c6542fc3e7c56a0a25d8d12d034d5a2d2e1900e292567b1c1dca8e83124/ast_serialize-0.11.2-cp315-abi3.abi3t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8532f20916fa3189d4d785ef2a62d93c4d651ec9c5bffda66d2fc36898351f34", size = 1282530, upload-time = "2026-09-13T18:47:57.619Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/ad/6f6755cd0842db46c3b10b1e4735f14aad78d71dea4753eb46933101711b/ast_serialize-0.11.2-cp315-abi3.abi3t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ee732ae167e686d1d3c00f98d7d82b23138304694f0441b14d7ddf9c0f8a921c", size = 1287792, upload-time = "2026-09-13T18:47:59.227Z" },
+    { url = "https://files.pythonhosted.org/packages/03/40/5da672f5dd23fb7dc0c884c97711e56a3540f2fe3c4355a81f8beb385911/ast_serialize-0.11.2-cp315-abi3.abi3t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:75a1c7f46b9c19fc0ae01ca6fd076301628faa2ed7a8edbd55c6353c483946a3", size = 1557971, upload-time = "2026-09-13T18:48:00.96Z" },
+    { url = "https://files.pythonhosted.org/packages/df/c7/2bb25684f697801eb72866fdb94ed5edbff3867ce878b0e542a4a5b9dab9/ast_serialize-0.11.2-cp315-abi3.abi3t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2fdf31a0bb85ea2575cc91669f005e6647d2efed491231c4dc1497bc9a5b3aa6", size = 1303230, upload-time = "2026-09-13T18:48:02.337Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/85/754681846f26e0ff1da729b1ffe3171e93c22f0aa6ec3cea5b14e3703846/ast_serialize-0.11.2-cp315-abi3.abi3t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3b78e6fdef3b06c86ed263e1962fee5a7b9d2d158e738b212d13b2c605ee12f5", size = 1302271, upload-time = "2026-09-13T18:48:03.915Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/dc/f5521d8cb44b69095c3982ae3658a12c403e0efa19e51aeb9c8a79dff60c/ast_serialize-0.11.2-cp315-abi3.abi3t-manylinux_2_31_riscv64.whl", hash = "sha256:8d62a47714c8bc432b9fabcc29989c815c5da17327d35151f2fd0d85c2a7a5ff", size = 1309529, upload-time = "2026-09-13T18:48:05.562Z" },
+    { url = "https://files.pythonhosted.org/packages/73/0d/649182c7fd7c4f782279bed514de2dd67e48a5afecb605a098d64fdc01fd/ast_serialize-0.11.2-cp315-abi3.abi3t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:8a5ffa70e76191dcf240d3c43e20c93b3bfd26f54d89148c762d57837f5bcd2c", size = 1356869, upload-time = "2026-09-13T18:48:07.534Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/cc/aff4d84c16afa742d13a75384127c7d24594dc8c304f0558a15924fd51af/ast_serialize-0.11.2-cp315-abi3.abi3t-musllinux_1_2_aarch64.whl", hash = "sha256:bfbe47a3a7c368f28836e78b2440a3643ac0ec4c67d9fe53588e1448f0a3d35d", size = 1460006, upload-time = "2026-09-13T18:48:09.162Z" },
+    { url = "https://files.pythonhosted.org/packages/94/a7/891cbec2e5e0d7159196159d3ff0646622f3120ff4576c839ac2dd56c719/ast_serialize-0.11.2-cp315-abi3.abi3t-musllinux_1_2_armv7l.whl", hash = "sha256:7f1823275b246f9c7d373be6879e4eec09686948895d4ad083f4b27fd7e4da70", size = 1562935, upload-time = "2026-09-13T18:48:10.978Z" },
+    { url = "https://files.pythonhosted.org/packages/45/c4/2c8c4498340ea9aff87a9fd408309aa25d56dd51d7bbddfdb46a3c31424a/ast_serialize-0.11.2-cp315-abi3.abi3t-musllinux_1_2_i686.whl", hash = "sha256:57c0f5cb0021a5beb1e5e4d6e840ae2f23a28909703ef4d256a144cc1ad3d437", size = 1557109, upload-time = "2026-09-13T18:48:12.616Z" },
+    { url = "https://files.pythonhosted.org/packages/0d/8b/c5d4e5226fa18885fe17f949aee3ab1aeb8389c384d946ec1b7c9489cc94/ast_serialize-0.11.2-cp315-abi3.abi3t-musllinux_1_2_ppc64le.whl", hash = "sha256:cd320a5c4f1f2742af97eea22954f776379175c5ef2504801e9a155f2ff9a4d7", size = 1691603, upload-time = "2026-09-13T18:48:14.293Z" },
+    { url = "https://files.pythonhosted.org/packages/73/d6/1d2ca472586f9e3416a289a22f36eeb6dd6f47d77b1a4aba358405babbc7/ast_serialize-0.11.2-cp315-abi3.abi3t-musllinux_1_2_riscv64.whl", hash = "sha256:13b13afe32e845c86a573497729e1b7ddeb26c572c78bf50ece51da23b8fad5e", size = 1483053, upload-time = "2026-09-13T18:48:15.789Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/16/d3703a7c1e3c76b144ac9349a54d3926d0749918a8dc13a66cede208b8ec/ast_serialize-0.11.2-cp315-abi3.abi3t-musllinux_1_2_x86_64.whl", hash = "sha256:9d80a81ec84660422579bdb8e789f656a794b48c7a1ae1261f6bd8bc1897d17d", size = 1502499, upload-time = "2026-09-13T18:48:17.405Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/e4/d974e55c2e247ef26ed1df01c74940583db9a5b3a8bcaad5732c6e2047fb/ast_serialize-0.11.2-cp315-abi3.abi3t-win32.whl", hash = "sha256:af8c003ce721b0099dd55cef4ba733500fc3054ea0cc8565d8957aaf7cccdeb4", size = 1119739, upload-time = "2026-09-13T18:48:19.005Z" },
+    { url = "https://files.pythonhosted.org/packages/0d/00/d229443488e095054d5e0c0cc20689a2633b899d735849ff1b2c8e4f0cbf/ast_serialize-0.11.2-cp315-abi3.abi3t-win_amd64.whl", hash = "sha256:554d117cb916d8032d85007c654d179efbbfd446174c048062778136a922944f", size = 1158602, upload-time = "2026-09-13T18:48:20.524Z" },
+    { url = "https://files.pythonhosted.org/packages/11/75/389fc1a6cfa0c4b2ce522f47d8401329d8bb11732e516d46465960fef1d9/ast_serialize-0.11.2-cp315-abi3.abi3t-win_arm64.whl", hash = "sha256:d60515335750d431e462af6e722bb55720a5e7827192777bddfd9c4376065a4d", size = 1128842, upload-time = "2026-09-13T18:48:22.052Z" },
+    { url = "https://files.pythonhosted.org/packages/45/7d/c4f36898f19c728d091cdfdf960c9488e8d82bbe2e49ba13c05f43907a5d/ast_serialize-0.11.2-cp315-cp315-pyemscripten_2026_5_wasm32.whl", hash = "sha256:89499a439955931281986e97ca4dd3c064bf0d2e0027c0017344eb86667733a1", size = 897204, upload-time = "2026-09-13T18:48:23.695Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/54/f67120006fc73a55b6d057d4662d061fbb4eceafce3047c76ca8b382eb11/ast_serialize-0.11.2-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:daadf1c3e0224621607ffe16f1379e4bd372271ed2e1db8a67878f0bab3ef7e4", size = 1240734, upload-time = "2026-09-13T18:48:25.287Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/7e/8f2ab68bddbe58a66fbbaad87beeae3e7d7edddb17263d1fc423936cf34d/ast_serialize-0.11.2-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:1844ed9a487fb3de7325c52ddb33f2918b66b65cd54d3f8d83d23785ffe99fa4", size = 1228053, upload-time = "2026-09-13T18:48:26.788Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/1b/8a69ab68f4c1603819f0481d756abdd8caf27cec7f1d77caa71007ebe997/ast_serialize-0.11.2-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b17869f4ba261a5fa468a753328a548f4dbaf74b4eadae9e28aff66df7f1425b", size = 1292542, upload-time = "2026-09-13T18:48:28.295Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/ce/872f2e00f0467c289e483f0a34543463347243a2d0632748d89fcee5e0dc/ast_serialize-0.11.2-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:feb16d9c2a720e0120c58dd5d6e7b3c7c86b43249b60a3bc212bcb8fa031e2dd", size = 1294791, upload-time = "2026-09-13T18:48:29.969Z" },
+    { url = "https://files.pythonhosted.org/packages/3a/82/36277c12af861c64b375c316135d8feffe3f400568463a8d2b2de4c2c4fb/ast_serialize-0.11.2-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f3109fe4805384effc8d0f8e41fbf875aa8f389af91b4348c1cfb60ea6e4cb82", size = 1567583, upload-time = "2026-09-13T18:48:31.85Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/d7/ec643df91cea8bcbcb4e8011d6a8b08e5119b84f9554879f3e3c786d29d1/ast_serialize-0.11.2-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:abdb3e49ba053c3486ac1263bee9f16cc9a4a8abd9f8c90bfc21e3669f3ad9d1", size = 1312878, upload-time = "2026-09-13T18:48:33.495Z" },
+    { url = "https://files.pythonhosted.org/packages/04/6f/4c992cd7841ba589fefb14ddc9aff2f6db7f2a615d4074f9ad04115b5ce0/ast_serialize-0.11.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a7004ba572f09be34342ccb98dcd4bad5707d3d81adc8cb4c3f685d2a2c51bbc", size = 1312642, upload-time = "2026-09-13T18:48:35.294Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/e3/22aaa209c231a83cfea004fd67dee7a7a54da3f169c6c460b14b96887385/ast_serialize-0.11.2-cp39-abi3-manylinux_2_31_riscv64.whl", hash = "sha256:59c25f47524efa052971b860e128b1add0c94ede7dd16b2962952c85c3582365", size = 1319776, upload-time = "2026-09-13T18:48:36.866Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/f7/d4685fb54d10108ce44d3bc893ef670854d61645d47ed96d73524db90c23/ast_serialize-0.11.2-cp39-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f3a367e0e05ed2d1b747ceb07aa728a8c204cc008b589127e9bd4f40053d7575", size = 1365324, upload-time = "2026-09-13T18:48:38.412Z" },
+    { url = "https://files.pythonhosted.org/packages/42/3a/250643ffad02bda520c50a9a5f02a5d43259a06f34ce393c91761d134d7e/ast_serialize-0.11.2-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:00bbf1f6669f813b48925b759f7ae4591067d456d443924055cab386e7e0a719", size = 1467653, upload-time = "2026-09-13T18:48:40.348Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/da/af66a646b9b7f8fdec95ce83fc7b1fe538b06864bc79bd554ac4fae2e6ea/ast_serialize-0.11.2-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:ec1c20f89c3e0d83576e3c06f79375ce936266591fe0d5fd969914af3185cbaa", size = 1571914, upload-time = "2026-09-13T18:48:41.968Z" },
+    { url = "https://files.pythonhosted.org/packages/34/82/77a9714564b9e8800087a8afec41527c65c39e49282baae2ac847b9c1c6a/ast_serialize-0.11.2-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:c58bb119b73657fdc5569692f316e1e25ca114bd62f7782eb527c6be438ba3a9", size = 1569862, upload-time = "2026-09-13T18:48:43.701Z" },
+    { url = "https://files.pythonhosted.org/packages/65/06/fa77b52f46b9bd6dcd8ff2b880e3781f8c1a316bb1342bc3de92907c6f96/ast_serialize-0.11.2-cp39-abi3-musllinux_1_2_ppc64le.whl", hash = "sha256:f739e0b601be7300c5697a2573d9200bd1db74b34ab111ef9537b9d5dcd7f106", size = 1699020, upload-time = "2026-09-13T18:48:45.261Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/09/239c83153c7e0798e5867d6909cb06f53dccfef02f6999c8e2e21ecb98c3/ast_serialize-0.11.2-cp39-abi3-musllinux_1_2_riscv64.whl", hash = "sha256:cae5addfbb54cc1d47fe947ef9138e9d83849ed1cbc72b819cf36d96a2315b07", size = 1492869, upload-time = "2026-09-13T18:48:46.922Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/eb/6108fb9a43fc7ab5529856e38e33c6e3e064fbfe375fdcbb208c7cd5438d/ast_serialize-0.11.2-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:2fa3be25f7f5351b1b39c9f8a52779b2dbf21199efbae564b4746422e8edca4e", size = 1511621, upload-time = "2026-09-13T18:48:48.667Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/82/60367e58ef346a41ebc90d3f28593c1b8f5c2cb5314c7b2bbd98910ee131/ast_serialize-0.11.2-cp39-abi3-win32.whl", hash = "sha256:d70556a2f9230a44c99a655774cde823f056efc34466eabfb4085f0cb1ea9f99", size = 1125873, upload-time = "2026-09-13T18:48:50.661Z" },
+    { url = "https://files.pythonhosted.org/packages/23/bf/b419c3205ce1143ba7c69baef4f0ba43c14d8712113bf34f9e0d27d609be/ast_serialize-0.11.2-cp39-abi3-win_amd64.whl", hash = "sha256:b9065dd23131a23b41f5bab3bf4e9b3c350a3fe8e36e8200eded9b729fcea484", size = 1165434, upload-time = "2026-09-13T18:48:52.169Z" },
+    { url = "https://files.pythonhosted.org/packages/91/a7/c8bbb2173f7a7131b3b2412035b2d814ab5ef2ce9799bd06f07c451640e4/ast_serialize-0.11.2-cp39-abi3-win_arm64.whl", hash = "sha256:dab599cbdcb7b45b18c41fad746645580b3a24357082b7f0e8921cd373804f27", size = 1136031, upload-time = "2026-09-13T18:48:54.04Z" },
+]
+
+[[package]]
+name = "certifi"
+version = "2026.7.22"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a3/c2/24167ea9858356b47a87a50d39908bfdb72ceeefe0041586e704e5376b3a/certifi-2026.7.22.tar.gz", hash = "sha256:741e2c3b351ddf169a738da9f2c048608ff7f2c5cc02f1ebc6b118bb090d5d55", size = 138112, upload-time = "2026-07-22T03:35:12.644Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0b/a7/71ac2cff56fec219ed242bb11b8efb69fcc4bec75db06fb7bfe35de520e6/certifi-2026.7.22-py3-none-any.whl", hash = "sha256:62f22742b58a1a33014a2b6b706588a8d7e2a88ae7bd1a6ebe8c992928483775", size = 136983, upload-time = "2026-07-22T03:35:11.276Z" },
+]
+
+[[package]]
+name = "click"
+version = "8.5.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/c7/0e/7fa0ef50764b67090eca4114772a2abf8b6148198475e54c660b97caeee6/click-8.5.0.tar.gz", hash = "sha256:ba0d2089de75ea0310e2dde03160e6ca10009947fb95a182f9b54021bb272e34", size = 382235, upload-time = "2026-08-26T13:33:14.56Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/58/50/6c0d534c5f134586a8e1ba4e330569e32f057e33372ae556463212fb4cd3/click-8.5.0-py3-none-any.whl", hash = "sha256:255bc9599cf7748b4b1a446ccc735421bd08a2ae529a8b88597d3de5664ee360", size = 125251, upload-time = "2026-08-26T13:33:12.928Z" },
+]
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d8/53/6f443c9a4a8358a93a6792e2acffb9d9d5cb0a5cfd8802644b7b1c9a02e4/colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44", size = 27697, upload-time = "2022-10-25T02:36:22.414Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" },
+]
+
+[[package]]
+name = "fastapi"
+version = "0.115.14"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pydantic" },
+    { name = "starlette" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ca/53/8c38a874844a8b0fa10dd8adf3836ac154082cf88d3f22b544e9ceea0a15/fastapi-0.115.14.tar.gz", hash = "sha256:b1de15cdc1c499a4da47914db35d0e4ef8f1ce62b624e94e0e5824421df99739", size = 296263, upload-time = "2025-06-26T15:29:08.21Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/53/50/b1222562c6d270fea83e9c9075b8e8600b8479150a18e4516a6138b980d1/fastapi-0.115.14-py3-none-any.whl", hash = "sha256:6c0c8bf9420bd58f565e585036d971872472b4f7d3f6c73b698e10cffdefb3ca", size = 95514, upload-time = "2025-06-26T15:29:06.49Z" },
+]
+
+[[package]]
+name = "h11"
+version = "0.16.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/01/ee/02a2c011bdab74c6fb3c75474d40b3052059d95df7e73351460c8588d963/h11-0.16.0.tar.gz", hash = "sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1", size = 101250, upload-time = "2025-04-24T03:35:25.427Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/04/4b/29cac41a4d98d144bf5f6d33995617b185d14b22401f75ca86f384e87ff1/h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86", size = 37515, upload-time = "2025-04-24T03:35:24.344Z" },
+]
+
+[[package]]
+name = "httpcore"
+version = "1.0.9"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "h11" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/06/94/82699a10bca87a5556c9c59b5963f2d039dbd239f25bc2a63907a05a14cb/httpcore-1.0.9.tar.gz", hash = "sha256:6e34463af53fd2ab5d807f399a9b45ea31c3dfa2276f15a2c3f00afff6e176e8", size = 85484, upload-time = "2025-04-24T22:06:22.219Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7e/f5/f66802a942d491edb555dd61e3a9961140fd64c90bce1eafd741609d334d/httpcore-1.0.9-py3-none-any.whl", hash = "sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55", size = 78784, upload-time = "2025-04-24T22:06:20.566Z" },
+]
+
+[[package]]
+name = "httpx"
+version = "0.28.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+    { name = "certifi" },
+    { name = "httpcore" },
+    { name = "idna" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b1/df/48c586a5fe32a0f01324ee087459e112ebb7224f646c0b5023f5e79e9956/httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc", size = 141406, upload-time = "2024-12-06T15:37:23.222Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517, upload-time = "2024-12-06T15:37:21.509Z" },
+]
+
+[[package]]
+name = "idna"
+version = "3.20"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f5/08/8eea9d4b8302028f3abb2c0813953f7aec26d33b7a8960ed760e65ff29fa/idna-3.20.tar.gz", hash = "sha256:a7db850025b95ded1eae8a46181a1a6c56c92c96f0e2b005d9ff8dc0210cab44", size = 216463, upload-time = "2026-09-17T14:11:04.752Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/58/a2/bb081bab032533a855d44de1d56f8e8426114ff1ba5d1f07a438a0a654f8/idna-3.20-py3-none-any.whl", hash = "sha256:ab7ae7122974553370f0bdb919e1a960b2cd1bc1ef0276416d896db81c14582c", size = 69583, upload-time = "2026-09-17T14:11:03.168Z" },
+]
+
+[[package]]
+name = "iniconfig"
+version = "2.3.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/72/34/14ca021ce8e5dfedc35312d08ba8bf51fdd999c576889fc2c24cb97f4f10/iniconfig-2.3.0.tar.gz", hash = "sha256:c76315c77db068650d49c5b56314774a7804df16fee4402c1f19d6d15d8c4730", size = 20503, upload-time = "2025-10-18T21:55:43.219Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cb/b1/3846dd7f199d53cb17f49cba7e651e9ce294d8497c8c150530ed11865bb8/iniconfig-2.3.0-py3-none-any.whl", hash = "sha256:f631c04d2c48c52b84d0d0549c99ff3859c98df65b3101406327ecc7d53fbf12", size = 7484, upload-time = "2025-10-18T21:55:41.639Z" },
+]
+
+[[package]]
+name = "librt"
+version = "0.15.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/36/9b/356320fbae2ac8467e21c5e73e1389c80468e4998c62cc7d3536cc51b614/librt-0.15.0.tar.gz", hash = "sha256:4e66cbe84437497d951b799d3e1551291b6fb3d643820a7014b3655d57a59162", size = 214338, upload-time = "2026-08-07T10:49:42.663Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ba/39/99c25030e782bdfb7a21be8c05254806a2e4bbb05c8d50c2a2130acbfa05/librt-0.15.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:e87bc679f86a99aa3b26e3c78eeb821a247c9a28eae48eaafcc32c3bf4c3bb9e", size = 151021, upload-time = "2026-08-07T10:47:00.057Z" },
+    { url = "https://files.pythonhosted.org/packages/14/43/f4b1bd1b2888798a1409808889a25ea1ba49eaabce7d681ed27734c2df9d/librt-0.15.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:71599e011ac880e8e45d46047d714871894c7d4ab6f25626f8d4f89da21f368d", size = 155267, upload-time = "2026-08-07T10:47:01.311Z" },
+    { url = "https://files.pythonhosted.org/packages/0c/db/3ad9c965c72f1e1d6beeec44ec10a54e17be8ae042fbb4baade16cbadced/librt-0.15.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c802434092b769b1d613ed2e13fac15fbfce1934a74bd10283b03c0fae231cd1", size = 503136, upload-time = "2026-08-07T10:47:02.45Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/07/5888a6d76acd62ebce66c61b74d94e9370b9c32929f111e487bb6546f8ed/librt-0.15.0-cp312-cp312-manylinux2014_i686.manylinux_2_17_i686.manylinux_2_28_i686.whl", hash = "sha256:5500eeae393a184d14e1f35645962c27129d20c81afa4069e6ef826ebc2b3aaa", size = 496670, upload-time = "2026-08-07T10:47:03.675Z" },
+    { url = "https://files.pythonhosted.org/packages/29/39/ab57cc2f5b276156da02bb7f5a8921bada1cb1993ffec99acf811c602c23/librt-0.15.0-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6ecfc32dfb46fb7b565bcd6abf9412acf978775a998273d22888a6d7953730dd", size = 513688, upload-time = "2026-08-07T10:47:04.981Z" },
+    { url = "https://files.pythonhosted.org/packages/a7/b9/bdbb0b648b5c2befb031f4c6f3b1dd857415e8fb492a25a3c764a6681e6c/librt-0.15.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:89cc46cfd15022e35084355478c9ac809d90b1152222706ac9a7655ec21df6fa", size = 531904, upload-time = "2026-08-07T10:47:06.211Z" },
+    { url = "https://files.pythonhosted.org/packages/93/26/473c2e4b6c104e9e58e27ce95fc8005c8bd4fc36cae4f254371125a92db8/librt-0.15.0-cp312-cp312-manylinux_2_34_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d5f51401d102c885b9ca509e62c79b1dbff286e1b9b047fde6f763780789356d", size = 524427, upload-time = "2026-08-07T10:47:07.592Z" },
+    { url = "https://files.pythonhosted.org/packages/26/60/03b3abb82b41714671b907bf6989b228e31e6a8af52dec82b5b0728dc250/librt-0.15.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:cc30523e3f1a23fb7511cc659834a0d01a1042bb9de359bc1c131cc4ec6c9656", size = 543155, upload-time = "2026-08-07T10:47:08.866Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/0e/9bb1f0a4affbd0a1888f4f79dc03ed2a299d9a2c26c59ab2a97dcbf11903/librt-0.15.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:59fe030d8ae4a57e3fb7756bf35a858de74e04066fc8555c53d0af979132af81", size = 546890, upload-time = "2026-08-07T10:47:10.327Z" },
+    { url = "https://files.pythonhosted.org/packages/dc/84/6937a280d461f7de6e031ffb02edc2b7c3c90d49d630565ce8ff27cbc5f2/librt-0.15.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:5a6526a2a956bbb1e4ae3568c82e650fc99119c66bb011ea60715744955a2b4d", size = 555163, upload-time = "2026-08-07T10:47:11.798Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/95/2a2853c1ee014bf102116e7f897a04beeaeb2461b45b79af98bdfb95f1ef/librt-0.15.0-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:85ea21ec6730194d67156b0e0b5430ccb1d61f8b8b907e39b37f9812b74a13f0", size = 535812, upload-time = "2026-08-07T10:47:13.279Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/4c/cf9601c1b4c5f09280acd5d83abdb2e68527a2be8257136eb42304218622/librt-0.15.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:1e47b8ba865d7ede071a91a7163073bbaeb72541f1ef8a07d512c45c7b5007f2", size = 573688, upload-time = "2026-08-07T10:47:14.727Z" },
+    { url = "https://files.pythonhosted.org/packages/47/6d/9ac7cbec46189a7625af4b5acbd25f10d827f4141b2002181848c8418923/librt-0.15.0-cp312-cp312-win32.whl", hash = "sha256:a5207ec414d1c4a2a7231b2086970dc036f94293cdf338190984958a013a42f1", size = 106138, upload-time = "2026-08-07T10:47:15.973Z" },
+    { url = "https://files.pythonhosted.org/packages/38/d0/2ae99c83be86ce23f925ac1aeeedc777e97f427c4a8d190c70d0a16e9a87/librt-0.15.0-cp312-cp312-win_amd64.whl", hash = "sha256:73b30cfa976659b3917c8f6153bdb0591c6a9ec6583599fd24a689b690622022", size = 126974, upload-time = "2026-08-07T10:47:17.049Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/ef/dd24f9635c730b86b87587967dda7516b1845e8b17684603d31607fed598/librt-0.15.0-cp312-cp312-win_arm64.whl", hash = "sha256:a54cf9e0ef47b96af580849db5471142200568ce1e02cbf416addab551369570", size = 112292, upload-time = "2026-08-07T10:47:18.222Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/42/467b53a601b406ccd7b97c1fd54b59cb34f9185ad5ce7e9d5c3c4e8961c8/librt-0.15.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:db13ca398005abcbe538deda87b686d9bd08b7001cf40c4c06b444960ae10a26", size = 151029, upload-time = "2026-08-07T10:47:19.312Z" },
+    { url = "https://files.pythonhosted.org/packages/3e/e6/36c2299b7a94b84fdd01220d8a777a71be5be0925bb0dbdf71c0a06a34d9/librt-0.15.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:aa1f1995789dca3698bc550aaceb09a51bd5df0a057ff84ff15296cd1975b801", size = 155194, upload-time = "2026-08-07T10:47:20.398Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/b6/ed5071f9325845e670bd36012757419767fbf56af77ed483077b9e4db541/librt-0.15.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:55456ea87d8df21808446d03817be2f65e20391c1c615d9187440dff28cd08dc", size = 502568, upload-time = "2026-08-07T10:47:21.652Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/81/6450c67c3615d87704bcbc21323fafc69c799b06a044c447529f725d4b01/librt-0.15.0-cp313-cp313-manylinux2014_i686.manylinux_2_17_i686.manylinux_2_28_i686.whl", hash = "sha256:5a86a5a08c2235316bdb359d5dbb6ce0abfca7fac06363103e2c5af571d92f95", size = 496153, upload-time = "2026-08-07T10:47:22.925Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/d6/5f52b722bc75076954b3bfd49be15ea362df4d580c6fb315d0f617100d30/librt-0.15.0-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e56b6a368529bed262da40ce13f8fef590db0479819cca84f16a1f01ac356d0b", size = 513336, upload-time = "2026-08-07T10:47:24.213Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/e2/c08fd1d36ce63ea5a12b85c5d37f4550b5f86a692167e41e5a74222607ae/librt-0.15.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:234d8d394721fa0d786af15ebf1f3fb7f3ed82fd1cd0cde45c2f247b5d4281d2", size = 531661, upload-time = "2026-08-07T10:47:25.507Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/d8/d9482fcbeb177b9eb87bb3899eeb3b42be690313c652f9e146b1d0681fb2/librt-0.15.0-cp313-cp313-manylinux_2_34_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d8363d7accb0286ac3a0e633f396e93800dafb8150494505daf9515bbda591f3", size = 524487, upload-time = "2026-08-07T10:47:26.79Z" },
+    { url = "https://files.pythonhosted.org/packages/10/cc/075171517b41f861753034fbb151b42cfc83bcc853849f24f5e66fd60ccf/librt-0.15.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:0f0ee3644d951f31055ad07d77d92520e84505dd7a432cc4cd501dd70ee06785", size = 543201, upload-time = "2026-08-07T10:47:27.999Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/03/42c2330f37eeb475b6affeedd06518f60035f323af3a839335e3fc9fef2d/librt-0.15.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:2cfd1a81a648806e6a7717be4cc4d1bb392fa229752bf8444ba365e381e984d6", size = 546467, upload-time = "2026-08-07T10:47:29.396Z" },
+    { url = "https://files.pythonhosted.org/packages/57/1e/1ad4c5638f7e64d8560328bd25c54b409a661bdb6ff254b38ff90744288d/librt-0.15.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:a6cd22c9da0d866558e46a041f1cc0c2bbb26b61b137b2347fa834c332e1d101", size = 555139, upload-time = "2026-08-07T10:47:30.815Z" },
+    { url = "https://files.pythonhosted.org/packages/49/41/39fa7d15db1204cd1cbe6514680fbdc243adf754a0885061308f43afc013/librt-0.15.0-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:6d5225ef8801e4ea5e482fa9b5dfb891dd9ef6f6d870f1f25d449ca2c70ac218", size = 536050, upload-time = "2026-08-07T10:47:32.222Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/88/c6dcf0dd8e26dc0c9a499a2abab8646c86dcaf9ecea9524cb46d3686331a/librt-0.15.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6d28a05796b99f749bf8794f17ba9ba1612d0076b802e9cfc62c554634e9ce3b", size = 573700, upload-time = "2026-08-07T10:47:33.527Z" },
+    { url = "https://files.pythonhosted.org/packages/1b/9b/ab54c71a7918a7c34fa5327fb61390a77446a07a146fbfb1165250a61035/librt-0.15.0-cp313-cp313-pyemscripten_2025_0_wasm32.whl", hash = "sha256:2067ff438048cead9d223ca5675bae2a25e520a7c3e6c1498bf9c6892d22caab", size = 82194, upload-time = "2026-08-07T10:47:34.835Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/b2/4f9a243bb892395f3becb80789ade13771701091f9f07ab8230247953ba8/librt-0.15.0-cp313-cp313-win32.whl", hash = "sha256:1cd3b721f24c206398b9e26da3c3a9c011e6e89d06f318ba8ebefc30f1003890", size = 106231, upload-time = "2026-08-07T10:47:36.251Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/af/64aff4885a40b93132382f2c314647d722574605416504379184ef3045ea/librt-0.15.0-cp313-cp313-win_amd64.whl", hash = "sha256:f395a4a9a03ac062dbe9a9f82e0c720502e590a38feee6a757bc82e9c63afbd8", size = 126996, upload-time = "2026-08-07T10:47:37.453Z" },
+    { url = "https://files.pythonhosted.org/packages/27/83/335bccf6c7cb9028cb0b54aead27d9ece3f01f83bc6baa2abace5da655c1/librt-0.15.0-cp313-cp313-win_arm64.whl", hash = "sha256:0a15cb554761247d84a3ec0cbdf4078d70725384f0e4662c0fa3b26266eb60ad", size = 112188, upload-time = "2026-08-07T10:47:38.729Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/93/949053fb462eecc4a9a5ee770a81f4b40be7b79538b245545d4aebc6b58b/librt-0.15.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:f5de7feedc56337a088eb15cd9fafa9938367362221d8cc62c642b7f94821993", size = 149833, upload-time = "2026-08-07T10:47:39.86Z" },
+    { url = "https://files.pythonhosted.org/packages/61/ca/8281aa6cd560a3420e4497729f6b704b53be3eeaaef82d5aeadddaf7441f/librt-0.15.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:6c0eb900c0e91f4aebe680845242e614f1864edfd44106380d0752ac29522bf8", size = 154088, upload-time = "2026-08-07T10:47:41.065Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/02/1a1662dceaba6a086360891448d5ce9a7d3555976cae59a31a39d744b9c7/librt-0.15.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e8c9a650a188e38bac005048cbe6342e81407782944d01934540ab75e417df21", size = 494215, upload-time = "2026-08-07T10:47:42.388Z" },
+    { url = "https://files.pythonhosted.org/packages/69/84/99211619dc656370a3740c33d2b0b6d5a3fb1e73689314f6ed477a397dc4/librt-0.15.0-cp314-cp314-manylinux2014_i686.manylinux_2_17_i686.manylinux_2_28_i686.whl", hash = "sha256:92bfed8deec93df30286b9fe9e3b1dd17329cc076a192b4ee5ec223841d54953", size = 491173, upload-time = "2026-08-07T10:47:43.683Z" },
+    { url = "https://files.pythonhosted.org/packages/d4/aa/5448d0b05f4579b635d3899176817ebf561af0e57bacd425b5b1887264c1/librt-0.15.0-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:ec4b19788f835711a2072f9dbe6b03b3bf32ed1f0fb30cf399bdd59d9f0c33fa", size = 505512, upload-time = "2026-08-07T10:47:45.314Z" },
+    { url = "https://files.pythonhosted.org/packages/95/82/01940e40b83c43a546c4a3c896cf34ca272a9690899d55914e4827b3dcce/librt-0.15.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d4c7bacb70930f3d0a56f4ecf1be474a1f0d941b01dd73b756f3c256d42cb879", size = 523073, upload-time = "2026-08-07T10:47:46.66Z" },
+    { url = "https://files.pythonhosted.org/packages/88/fa/759c0030f3ee371439eb26de34fc745807caf0abb878af7af4b8b7c3dd3d/librt-0.15.0-cp314-cp314-manylinux_2_34_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:3e79f05e4a08b4d880342673312bbc895b56df7765605796f15902eb5367d3ae", size = 515080, upload-time = "2026-08-07T10:47:48.319Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/27/894e072228fcb159703c655da69f8cd10dbed489c36e3df7dd032a2483be/librt-0.15.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:a417149c0cba4d50b61e992e5a15e69eaf96746609b461cc4ed168aeef6b79dd", size = 534164, upload-time = "2026-08-07T10:47:49.875Z" },
+    { url = "https://files.pythonhosted.org/packages/98/a3/0078e91c1f36f8815db17827de15650b9a3fe56c55fbf998c854b34e40d3/librt-0.15.0-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:da7a94d6a3411f579d72aa3e3bc5fbca7ed4549f3dbd7e5de3aa567333374285", size = 540616, upload-time = "2026-08-07T10:47:51.408Z" },
+    { url = "https://files.pythonhosted.org/packages/86/33/81a29b796dd52a45e9ef7974c7732926e8f10f15b8d2be505665979f896d/librt-0.15.0-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:856f743ae607f2c1380eccb566c0038a9fb3eabf0fc2be2704d76d9f73557239", size = 545890, upload-time = "2026-08-07T10:47:52.818Z" },
+    { url = "https://files.pythonhosted.org/packages/05/82/8be1baa1350e5d30cfd70ae79d0a6f4dc5862ef47f7bb2808aabc9bb86e5/librt-0.15.0-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:779a6e7c894737e5983e7790a9c78c4000c30e23c9aada08081bdbea53b0fa60", size = 523287, upload-time = "2026-08-07T10:47:54.165Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/4f/d1be6a01a35c20ef734e0e44113f87d4af756a9354a89dcfbe3b4f8af5e1/librt-0.15.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:96bb17dbe8bab3c0954fbebfc69ed395599de75b6bbc35e3270a878e15d4dd65", size = 565868, upload-time = "2026-08-07T10:47:55.566Z" },
+    { url = "https://files.pythonhosted.org/packages/67/88/649cfa33f5825927b160610f670bdab012a64d627eddb94fa795ea4292fd/librt-0.15.0-cp314-cp314-pyemscripten_2026_0_wasm32.whl", hash = "sha256:7220697efaa6e5348fc3d18ee7f8563d4bfecd9872b37ffb915bfc1d08840622", size = 81619, upload-time = "2026-08-07T10:47:56.886Z" },
+    { url = "https://files.pythonhosted.org/packages/22/31/8e88a8d5e48fc8d1a817787fb6811dfff6499acd6c8683dd83934aa6ede0/librt-0.15.0-cp314-cp314-win32.whl", hash = "sha256:f54598964d357b1c5ab77cf5d92f21e598fe0e23cdbe9618480807f81b4eba15", size = 100138, upload-time = "2026-08-07T10:47:58.093Z" },
+    { url = "https://files.pythonhosted.org/packages/80/92/20fd6c4b6a1b1a564b076d55cd3d427d8428217d7638dc25a654cc4791d4/librt-0.15.0-cp314-cp314-win_amd64.whl", hash = "sha256:3ff5893a2c23d886aa9ce786de5ac6ddc74aeeaf90743682b74d920e117d2e28", size = 121258, upload-time = "2026-08-07T10:47:59.564Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/28/6af430b44d9ebb897b865a3c363b6dcace51357be2347cc0f8f869656a86/librt-0.15.0-cp314-cp314-win_arm64.whl", hash = "sha256:3722a099730704c9a3d70c879fc0f51daec25fe5f1555672d97bc595abeafb95", size = 106467, upload-time = "2026-08-07T10:48:01.097Z" },
+    { url = "https://files.pythonhosted.org/packages/7e/aa/b42bb798942ced219f6d63b27e07f91237887a8d0bd0921666db79a13790/librt-0.15.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:38c0c7d4b6fc06c3324b3f9162c8391bfc4fd9dde53afe1033ce7edb48d5a714", size = 159523, upload-time = "2026-08-07T10:48:02.442Z" },
+    { url = "https://files.pythonhosted.org/packages/75/03/1b53cd4ef904e73b1d828a5f90143bf94a2967d7cfff0b9ccf93e12aa9b4/librt-0.15.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:8b2fdd7ead3c995c37940a790690660d0ca006c302db26cc51933f6766866fc3", size = 161638, upload-time = "2026-08-07T10:48:03.725Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/c4/9f9c9fba097d49e9e694c2b4dc331df31884645ecbc58a93b4b5fc69d2c5/librt-0.15.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2fde98cf1fc4bac144ce23c2c4c017b924ba714509ea9334977b0b27050c837d", size = 701795, upload-time = "2026-08-07T10:48:05.135Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/05/0966840bda0380c8ae167b9043c6230202941cc90ea29c48e096964c765e/librt-0.15.0-cp314-cp314t-manylinux2014_i686.manylinux_2_17_i686.manylinux_2_28_i686.whl", hash = "sha256:e3b461183c5fa7681b48560f91515f53a953122fb30c71e07abc67d7ddf58c38", size = 682147, upload-time = "2026-08-07T10:48:06.555Z" },
+    { url = "https://files.pythonhosted.org/packages/18/af/1c47ca573c30ea47d195aec26133af522fea1104afaace028d7b32247ea8/librt-0.15.0-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4bbcc257e3babea20a91715c361b24554ec4e8f51aa578568afc230799fe1a19", size = 696397, upload-time = "2026-08-07T10:48:08.03Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/0f/1aed6223d4f9f9d1171a8596ff100ea4c3f7699fea7a4ba657c3e60daa6c/librt-0.15.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b845b8d48088fad0cadc84be4b8fda63203be7e9237b71015b3925443c1f35ab", size = 722542, upload-time = "2026-08-07T10:48:09.569Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/22/9e3a929aea456c97d69e6ef3884efea56d4807f97399471cc946baebd8af/librt-0.15.0-cp314-cp314t-manylinux_2_34_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:b30e600e8f337b9bd7f39b86d9fdfedc73cc46e3d0f745931a23a234220bb7e2", size = 729709, upload-time = "2026-08-07T10:48:11.129Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/1b/c327ef6018e3a9ca0b8e7c5eddeeb331ba8f9b76c24e126d37d0f6d62faf/librt-0.15.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:64b0c8c35aa4c4ed79896359f3e0b285cbe4e610042106500da4811c322cc108", size = 752891, upload-time = "2026-08-07T10:48:12.558Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/d1/d5f1ea02c56930087009e39db9b70660a663e76c730b27b925d786718457/librt-0.15.0-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:0da0d94cb802f32a0524653e7201f2cef72d5f700a5407678f5290483d4fcd08", size = 745301, upload-time = "2026-08-07T10:48:14.55Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/3c/5f7c585d15ebb2250c73e7c0ee4e9e47be72c65d520c07ddbcdc62037674/librt-0.15.0-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:4a6369168d371207339b1e50d4532b06a7121586141f82599505a3f315751d47", size = 747921, upload-time = "2026-08-07T10:48:16.453Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/52/1443a446486eba966bcbca1696b472e4f210320ec42f490a47f48fbf0fdc/librt-0.15.0-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:c434e072557ade9cbc642d052c89d031efe47d5c9614523619d0d74a02378e81", size = 727561, upload-time = "2026-08-07T10:48:18.089Z" },
+    { url = "https://files.pythonhosted.org/packages/79/91/2270a9380f11725cf83ce1925a5e32dd1dde2be9bba597f25c10a38644e7/librt-0.15.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:c7eec6a42018bc1d45763b1c162d3d2bf7c3b9a1b0ed30d3e91dcba390efefcc", size = 774417, upload-time = "2026-08-07T10:48:19.611Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/3b/f4b1548d4f5b99186737fe27aec238e9823e8d5d23bf4df007c030689dc5/librt-0.15.0-cp314-cp314t-win32.whl", hash = "sha256:6912fa5e635d74529ac7cdb1bdf6ca3af4453da8d1edbe0110ee1cb4ad407ebf", size = 104381, upload-time = "2026-08-07T10:48:21.048Z" },
+    { url = "https://files.pythonhosted.org/packages/80/b6/134afad262def1de04c0843c376d02135f1168af43f22e09a52bd8394727/librt-0.15.0-cp314-cp314t-win_amd64.whl", hash = "sha256:8e11699ed745931c395acd3621b07062e0f840efa6935aad87a64ed0995f0915", size = 127034, upload-time = "2026-08-07T10:48:22.561Z" },
+    { url = "https://files.pythonhosted.org/packages/99/5f/1b6846b20572bd699c9e9ec321a5f781845bee477df2aa2a43b28bc40119/librt-0.15.0-cp314-cp314t-win_arm64.whl", hash = "sha256:5d2a91724463bfed4f573cd7a9fdc856d2e230d0c0e5a61416a93481dccd8605", size = 110827, upload-time = "2026-08-07T10:48:23.804Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/44/4de9f4ddadb009a55c7758eb5736d62534a7daaf27bd71bc50e64b606b06/librt-0.15.0-cp315-cp315-macosx_10_15_x86_64.whl", hash = "sha256:8443e38dcfcfdbcf5add5118c623efd788d65ac2e25756d6251a54a06a4d0aca", size = 149843, upload-time = "2026-08-07T10:48:25.148Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/eb/5d9ab71e30119c44094e0275f38b47dd327aea0f843a080396677029d508/librt-0.15.0-cp315-cp315-macosx_11_0_arm64.whl", hash = "sha256:6d15a29033c57490cfe2069097c6fc4049e4e65ffbb749be7dc453b7c4c68965", size = 154510, upload-time = "2026-08-07T10:48:26.485Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/9c/8505d1b8f5e8c19587bd03f7429993b3e9ce5c06819d856bfb11d919374c/librt-0.15.0-cp315-cp315-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d2c05c729b589e734c09578bf5964be48a911765484840d017bbc84f49d4c4ad", size = 497543, upload-time = "2026-08-07T10:48:28.045Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/9a/3a8390775cb095765aded027ac9c63e7c8ea74e731498607544c6505de0e/librt-0.15.0-cp315-cp315-manylinux2014_i686.manylinux_2_17_i686.manylinux_2_28_i686.whl", hash = "sha256:fa60887537e1d0cd2d9982269d33a709bf54b195cd2b9364fc0a758022af5bd9", size = 480452, upload-time = "2026-08-07T10:48:29.531Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/40/258a4a7117ee915d66de5cd9b8ade65a440993161107ce3a686f1859955c/librt-0.15.0-cp315-cp315-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:d8bc24219b24c0af375718942ab75e3544b2763085f40f965be4326734ae8328", size = 507768, upload-time = "2026-08-07T10:48:31.007Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/c6/2f4dd296c97a0b85b98894519b279408ec9dd602d4f692b1ea0e25dee670/librt-0.15.0-cp315-cp315-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:86a21a7bd3fe3a419512ef424cc1c020f6771d0b29cfddff36d1635a855e63f0", size = 525122, upload-time = "2026-08-07T10:48:32.7Z" },
+    { url = "https://files.pythonhosted.org/packages/49/dd/29eab42be13b2bf0ea8cb227135a45d44693e30a7e8b92871981ff56b82b/librt-0.15.0-cp315-cp315-manylinux_2_34_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:dbab647e88d90b3167b91efe7091e248653688ed4337e4f90907a722c7361bb9", size = 520371, upload-time = "2026-08-07T10:48:34.294Z" },
+    { url = "https://files.pythonhosted.org/packages/91/ed/4bad71adeca8fe208b775c2a35417fa5a2584c8f4791daaf89a89450fea1/librt-0.15.0-cp315-cp315-musllinux_1_2_aarch64.whl", hash = "sha256:d8edcf6f550e918dca779c069b9e156385c60b406f99fc7641f32c52f7193659", size = 537258, upload-time = "2026-08-07T10:48:35.88Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/63/59dba6143fdcc7240c54458b629f3250000a61b8945890fc9efd451b19c5/librt-0.15.0-cp315-cp315-musllinux_1_2_i686.whl", hash = "sha256:8b62076030baa2d8b1501a46bf0e19c27a489aa90671c55665bff7887f7660b0", size = 527432, upload-time = "2026-08-07T10:48:37.466Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/21/21a24c6a2327d8362580efebe77286bf47b0f4062ec5ea41766e609d3c7d/librt-0.15.0-cp315-cp315-musllinux_1_2_ppc64le.whl", hash = "sha256:d00d20d1818e82a07a0ee0aa89a98b17ed7916b92441090b683719cb20a59b6d", size = 548108, upload-time = "2026-08-07T10:48:39.384Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/6d/fc68c89a7971418b41f9a873623ff935cb864097544c6a2f8ce491c8ef5d/librt-0.15.0-cp315-cp315-musllinux_1_2_riscv64.whl", hash = "sha256:4e6ee93fc3cf848dcbf0cce2eca73d8e7dcd0cc2b6df3a529d57750b30a4c55c", size = 529681, upload-time = "2026-08-07T10:48:41.392Z" },
+    { url = "https://files.pythonhosted.org/packages/65/7e/c2d98766124400d722063a630b0fde38a9fc768705d37eecca15c47dc192/librt-0.15.0-cp315-cp315-musllinux_1_2_x86_64.whl", hash = "sha256:32896a0af72508ea979e0acb4e4c04cbeeae04938167950d535c83c45597167d", size = 567736, upload-time = "2026-08-07T10:48:43.124Z" },
+    { url = "https://files.pythonhosted.org/packages/55/6c/f8c34a95e3a515c6e1c192b89511e7253c89a7760c6b500d57ffdb8d2dc8/librt-0.15.0-cp315-cp315-pyemscripten_2026_5_wasm32.whl", hash = "sha256:ec3ba415afaf951f6951b1dd16d3c8e4f540065fc382d7e70b823a79567ca374", size = 81673, upload-time = "2026-08-07T10:48:44.645Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/9e/e23fa8e78679ec45728188650b39e8ff476c83b691c96f749217df3b1b7c/librt-0.15.0-cp315-cp315-win32.whl", hash = "sha256:d2813ba2503764f0450680c533d13df7cff9b49df1411062eded5f67db4195b9", size = 100081, upload-time = "2026-08-07T10:48:46.171Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/dc/3eb4c5e297343f0620a55532cd7c8d764d3001fa2159212dadf480464827/librt-0.15.0-cp315-cp315-win_amd64.whl", hash = "sha256:b87d67e33afaf265262f2a66db578284b88ee2e6fcd224579cb5c15518677ad8", size = 121228, upload-time = "2026-08-07T10:48:47.631Z" },
+    { url = "https://files.pythonhosted.org/packages/97/70/43abce19f04e49762f8ec834c8fafee13cc40fd6b94a72a24e534febfcd0/librt-0.15.0-cp315-cp315-win_arm64.whl", hash = "sha256:713bd7df21170b982e729e46870f31d6b437bd1a9b4648cffb529bd3c2ec5c4b", size = 106487, upload-time = "2026-08-07T10:48:49.095Z" },
+    { url = "https://files.pythonhosted.org/packages/de/15/83f2deddb9368b8951ec8c9477269b5b9b8bd9bbf15e57402d0f38817dca/librt-0.15.0-cp315-cp315t-macosx_10_15_x86_64.whl", hash = "sha256:3de789c82752730f94782a5ee518baf9c05edf85733aeaf73bb6e518755cdf54", size = 159448, upload-time = "2026-08-07T10:48:50.649Z" },
+    { url = "https://files.pythonhosted.org/packages/06/bf/043097353f9b3c73b583d07f6b8e552795463f4bfc8caf85e42eee50c26a/librt-0.15.0-cp315-cp315t-macosx_11_0_arm64.whl", hash = "sha256:e0b5deec9a8664eb722c797241970fd4aa1894d25fda36a1ddac0f7407606bd6", size = 161686, upload-time = "2026-08-07T10:48:52.174Z" },
+    { url = "https://files.pythonhosted.org/packages/f4/2a/8ae77f9719d42ce71cd708560a3557b38ac3c17a0383e57f87084de45bbe/librt-0.15.0-cp315-cp315t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5563302a8359bc2295bb7084d1a8ed1519df96afb30eb2aa4e0bff7b54228988", size = 710668, upload-time = "2026-08-07T10:48:53.782Z" },
+    { url = "https://files.pythonhosted.org/packages/61/34/c0436ea134deb9a0d6da80a396a2739a81cb31e0418f7227239e23140898/librt-0.15.0-cp315-cp315t-manylinux2014_i686.manylinux_2_17_i686.manylinux_2_28_i686.whl", hash = "sha256:22d6263b9d39d7bbb286fa791945646e3218f1be2d693e36fb630f1d0e59cd13", size = 679396, upload-time = "2026-08-07T10:48:55.645Z" },
+    { url = "https://files.pythonhosted.org/packages/4a/9f/001e0d99aa9250d5cd5715a9081291a20656083459f9019cda15255329e1/librt-0.15.0-cp315-cp315t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:39ffd14646190c454f0d86e0d256b33f00a87a26ab410e619773b841d0e41416", size = 704313, upload-time = "2026-08-07T10:48:57.46Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/53/b34fa9d0ff00f136f4d58ebb4c411ff634baed1eb412bb602a2bc8dcafcb/librt-0.15.0-cp315-cp315t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c47318cd3a61401452de11282242937e3e057c4fd3dbaf601e269d0928a06c0a", size = 729847, upload-time = "2026-08-07T10:48:59.231Z" },
+    { url = "https://files.pythonhosted.org/packages/86/ac/fa4d7a424665040e95baf480a6d523446057684b6758624c85338e8a23b2/librt-0.15.0-cp315-cp315t-manylinux_2_34_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:a56a1d4f859a82ca5b99fc4b82c9b027b15e3c455c5cd99e7d0719f27bb20b6c", size = 742736, upload-time = "2026-08-07T10:49:01.151Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/f1/e17a9bb5de6fb8c3186ed1a7d68d21618b027ac2d3633e03d3b6109c67ae/librt-0.15.0-cp315-cp315t-musllinux_1_2_aarch64.whl", hash = "sha256:077471b3182db4e17c36ae91555f36a4d2c00080b267f749bcad34a478a9a302", size = 763454, upload-time = "2026-08-07T10:49:03.039Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/ec/ecd02cd30935b931b9cdbfed6ab5a099c51b280b4e7baa274da80978ed27/librt-0.15.0-cp315-cp315t-musllinux_1_2_i686.whl", hash = "sha256:411ca4d1b905b860ceba7570dd6717a71dedaddcc4b0f77ece710aa41ee11f8d", size = 743296, upload-time = "2026-08-07T10:49:04.941Z" },
+    { url = "https://files.pythonhosted.org/packages/e6/b5/b3c2b8353ce820a4854f78d19321344242f89fa71c975b71132ba9bf242a/librt-0.15.0-cp315-cp315t-musllinux_1_2_ppc64le.whl", hash = "sha256:1256589e0b0adb31751d685a68bce29d73407ddf4ef05d4188f49d5dcf9566d9", size = 756217, upload-time = "2026-08-07T10:49:06.825Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/52/6cc22542ba59146b05cca2a656f9ff8bb67e38e63d12c3b0cc183d837bf1/librt-0.15.0-cp315-cp315t-musllinux_1_2_riscv64.whl", hash = "sha256:f42b74a53e5f26a0ba0007411a7455b66c67ce4022a39cc1f56fc4efd65bcbab", size = 741934, upload-time = "2026-08-07T10:49:08.839Z" },
+    { url = "https://files.pythonhosted.org/packages/40/32/a04b72b1aa86e3be23b2ecff8c1aad2dcc955bd3956d6d26e7e34267e57a/librt-0.15.0-cp315-cp315t-musllinux_1_2_x86_64.whl", hash = "sha256:291bf73caf78b9e88d6fae9bfd693207ff7d832e2fdbe2cf8e746bc13f5f892b", size = 783763, upload-time = "2026-08-07T10:49:10.661Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/f0/89eb11dffbe9279ff37144dec786927314502ae0b114f1449dc78c458aab/librt-0.15.0-cp315-cp315t-win32.whl", hash = "sha256:c16d15ee371643ab48dc8248a3e680ebbeca573a13af2c3dd0c985b142d77162", size = 104313, upload-time = "2026-08-07T10:49:12.305Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/4a/1f1978c200f563beda63c36adff2d65bbecb81e365e8e69e572f5f70fbc6/librt-0.15.0-cp315-cp315t-win_amd64.whl", hash = "sha256:dbd605739f228912dc49027cb764456b9757750bdc2b6b7773164db7096c6fd1", size = 126889, upload-time = "2026-08-07T10:49:13.881Z" },
+    { url = "https://files.pythonhosted.org/packages/38/a6/800800bfed7b1fb10fc3f3d557785c3854e80d3f7a9800d784b176a1fc2d/librt-0.15.0-cp315-cp315t-win_arm64.whl", hash = "sha256:84d244b00604d17df3fc7736c327892d6bba66181254aa4087be807b6c342bdc", size = 110700, upload-time = "2026-08-07T10:49:15.499Z" },
+]
+
+[[package]]
+name = "mypy"
+version = "2.3.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "ast-serialize" },
+    { name = "librt", marker = "platform_python_implementation != 'PyPy'" },
+    { name = "mypy-extensions" },
+    { name = "pathspec" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/82/6a/878cc1097d4035f82bd516658d0c528d2a9955bc7b363afcbd0b07fea11b/mypy-2.3.1.tar.gz", hash = "sha256:47c1b1207258513a9d93495f69c8be9de73916186f0e52703e8c461b7a623419", size = 3992554, upload-time = "2026-08-15T03:03:38.549Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/85/da/d6effc4f808a842d91edc22535dc9e799d2ff6e91449168b7f47a0771f54/mypy-2.3.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a32bbbb940af990d3be0b8af321c7b6815bb1b3b48142fe7459b9cc5f58959ff", size = 14047547, upload-time = "2026-08-15T03:02:57.707Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/e6/478229701dab76f26485fc8ff5d6f241f393da22447400bbc56f6946aebe/mypy-2.3.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ff715e45b2231a8e85de1d163d1b42791e4d7aab8f5145f85fee1b710b735aff", size = 14216515, upload-time = "2026-08-15T03:01:26.496Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/fe/7c42327a3b21e84681f691982cbfe43f334a3685f3b683b72c376476c4fa/mypy-2.3.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:858fc57d3d91fa728e33e7ad71def60fc6272694607b306cd3292db53ae39080", size = 15307789, upload-time = "2026-08-15T03:03:31.62Z" },
+    { url = "https://files.pythonhosted.org/packages/59/f4/7e597edbe01b5a56fa958ce541302dcaabfed979966f1dffedbea0ea0fc2/mypy-2.3.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:851833db876e7b650f93719c74b7879a08e338979c96054fdfc3bfd90a486355", size = 15548831, upload-time = "2026-08-15T03:03:15.55Z" },
+    { url = "https://files.pythonhosted.org/packages/a3/52/cb31e084bc0314a1e384bdd677a4b80e55af04ccac077545e2238b9d320a/mypy-2.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:4c5095a327483591c94e0c8d3ef9e50d4ab1369b541eae007c1f23bc2a41f6bb", size = 11226359, upload-time = "2026-08-15T03:03:29.002Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/47/88fcf6217b43fa2da81a8c2611370af18141536a4f0294bbf98b457d456d/mypy-2.3.1-cp312-cp312-win_arm64.whl", hash = "sha256:bbfe022634a2a195406bd469e888d2eaf193b02ba7e607391cd7640374aaae3b", size = 10214707, upload-time = "2026-08-15T03:02:48.807Z" },
+    { url = "https://files.pythonhosted.org/packages/de/cf/862010ee800ca9c2bd0c4c0dacf0f092e5411824a09b8f97ad4be8fe250e/mypy-2.3.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:114dff494000f18bd10d5d95d84b8567b26da60279ecbe838131841df20e635d", size = 13964542, upload-time = "2026-08-15T03:02:21.43Z" },
+    { url = "https://files.pythonhosted.org/packages/75/5a/3f3a2107b41e3e92e617e25daaee121413b91e9784bea733131ed4fecc5d/mypy-2.3.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c8637731bb5eee3671eb2c3200827aa3564ed8a9309ecee4d1afe77e6d031bdb", size = 14168922, upload-time = "2026-08-15T03:03:00.351Z" },
+    { url = "https://files.pythonhosted.org/packages/8b/41/04dc4fe7e63d7820fa4eff272e95157d30cbea921388f3ab3fe77794cd0b/mypy-2.3.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1c80fbc405ed8020f5ff3802dc18cf060197bcdd3fbdd6a26ef2fd34dfdd5226", size = 15244791, upload-time = "2026-08-15T03:02:31.089Z" },
+    { url = "https://files.pythonhosted.org/packages/96/fc/c3053b26b9054949285aa868cb6af8c10e7591541cacd79c5dcc06a1fcf9/mypy-2.3.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:84081f538ce27375045c02e3d7f81bd11d853400621ae245d87ce7b6c420ec74", size = 15501627, upload-time = "2026-08-15T03:03:34.128Z" },
+    { url = "https://files.pythonhosted.org/packages/70/4e/d77daab008bbc4e5001374d7928f4a260d28f0e6747af444fc4763f7a310/mypy-2.3.1-cp313-cp313-win_amd64.whl", hash = "sha256:e9144ac16fde007096f9563eb2041b4433c2d705c4218edeb79e7e9d01035ee6", size = 11243961, upload-time = "2026-08-15T03:02:11.952Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/f8/7eb68c136e4abd30569fe31ef2bfcb7eceae9952cab80017c04cd09f5d0c/mypy-2.3.1-cp313-cp313-win_arm64.whl", hash = "sha256:77ad9529e67dca28e511f5cd5671436584ce91f6d3bac159a353158187b986ac", size = 10213219, upload-time = "2026-08-15T03:02:26.361Z" },
+    { url = "https://files.pythonhosted.org/packages/be/c4/42a49d44aeff804edf1b19acce0b49e8bd1a9c57dee9605dd8d980aa43d7/mypy-2.3.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:192abaedf75da1bc0b1cef104927e70ec49c1ef0031cc4825c7ee10a438ed24d", size = 13986778, upload-time = "2026-08-15T03:01:33.69Z" },
+    { url = "https://files.pythonhosted.org/packages/45/13/9331fd2dfed7194d66c5304072894a8be3e51e9deda6863c1eceaa35a43d/mypy-2.3.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:bf678dffd16efcda2c15cbd30e9ecc0081388e29ea23687a88e686ed92638dc3", size = 14188467, upload-time = "2026-08-15T03:02:40.554Z" },
+    { url = "https://files.pythonhosted.org/packages/78/f7/f4a34edab45667c5465855dc585a20e87978ffa8aee711445b7239d120c6/mypy-2.3.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8e036f06b41630f4c8a1d48f9ac6aa26acc65f8be089973f5519da643318f03f", size = 15225538, upload-time = "2026-08-15T03:03:09.761Z" },
+    { url = "https://files.pythonhosted.org/packages/40/05/534b3590757bd05794f73e07f6666c2a77b8597ffed795c94ce570096aa0/mypy-2.3.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:71af9c8a894e862b58e92abb08e53b05a384a1e5e5d6dc7cda59126211a53d82", size = 15480805, upload-time = "2026-08-15T03:01:41.134Z" },
+    { url = "https://files.pythonhosted.org/packages/55/da/bdfba852e2562f599624af5bb7d29e36b0b4f526f2b8bac85efe0dd1803d/mypy-2.3.1-cp314-cp314-pyemscripten_2026_0_wasm32.whl", hash = "sha256:3c80cd23d85368bdd9f37d5231dfd97d35bcbf5bf41af96ef3a9b078ad1957f9", size = 7761712, upload-time = "2026-08-15T03:02:36.008Z" },
+    { url = "https://files.pythonhosted.org/packages/98/31/60fc64a74cdba4f2a5d642d32317993e479163e1ac7d91b695e5d15e2264/mypy-2.3.1-cp314-cp314-win_amd64.whl", hash = "sha256:4956f34d145e145562a0a0bf367f642bbc85c04ec2baf47ae015947c3169a85d", size = 11423968, upload-time = "2026-08-15T03:02:06.931Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/23/eb5950b24cd26ba3b78f87707a275568d633c77dae8e61c9661be6055ca6/mypy-2.3.1-cp314-cp314-win_arm64.whl", hash = "sha256:cfb12e360242d23d91f5e978d94f58ea66acf5804c4fb6f2f794a20d4cb1b595", size = 10399323, upload-time = "2026-08-15T03:02:33.671Z" },
+    { url = "https://files.pythonhosted.org/packages/82/c7/f80f4e46c0b9a00eb5f78a79d49dda8bdf56a5230f7257fb33e76be04da7/mypy-2.3.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:e5f1c50bb05b64e2026b52867e8d21106f01313c744a2c4ecc34c90d12e8d6e2", size = 15121308, upload-time = "2026-08-15T03:01:46.053Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/74/9b04f17c7074cc5188f02fb63a2ca1d43fedf479e84fe3091c39061a1d7f/mypy-2.3.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:667196b352f4cf304ded4c10f90cfc179263a1acfb3cdcfa984bdfd340d498bc", size = 15536590, upload-time = "2026-08-15T03:01:35.941Z" },
+    { url = "https://files.pythonhosted.org/packages/26/04/c837ef6208e567774e2ed1f863f8ba6ec4817b1b6dd426315e5d559b6ec9/mypy-2.3.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b9c53e395c12cad2c6d4b67d5da7c6057638a132d85c08b73646b18f802a0045", size = 16791074, upload-time = "2026-08-15T03:01:31.073Z" },
+    { url = "https://files.pythonhosted.org/packages/37/68/48730230afa45192d5bd429a6a2ff24a6f8dedda90fdf2b221792b54518f/mypy-2.3.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:18162b128c3f9c703cd35f5537446900b0d21a2549aa7a95d21380d2ef643fb0", size = 17069183, upload-time = "2026-08-15T03:02:28.566Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/ea/ca23fc9c20eeda09a15c9cbcf50015d0e73f409f6ead059e42aa69a608ff/mypy-2.3.1-cp314-cp314t-win_amd64.whl", hash = "sha256:30c0477d4aab7b7f39c8397dc877f2c96b9fe5588ec379f372c56eb63d599f63", size = 12154679, upload-time = "2026-08-15T03:02:04.809Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/67/8d982126034990869466f73b8db80dcb2234a7ac39b4dad093e047a79835/mypy-2.3.1-cp314-cp314t-win_arm64.whl", hash = "sha256:6941ab3619377bc3f32ca02876b07d27f216f5201604b664d3937ea0fdd23bb4", size = 10969159, upload-time = "2026-08-15T03:02:38.152Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/f7/41e7f2d8117fbc7a7587286162ffe2f688984b69c46ed63cf5f2e4fc3bae/mypy-2.3.1-cp315-cp315-macosx_11_0_arm64.whl", hash = "sha256:6f041a6de52c9217ca125e78ba0a335cb7fd98a1c0580978e49ab2b126f70b57", size = 13990694, upload-time = "2026-08-15T03:03:21.919Z" },
+    { url = "https://files.pythonhosted.org/packages/06/85/8f665811a0c8f3bf6fa1d9acd665ec2d97a2bcc453ae68dcd92340941cd6/mypy-2.3.1-cp315-cp315-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5159ae60f5dbc3a498af5ba8365505808ac8031bc63f9e00304ad545d40bdd9b", size = 14203518, upload-time = "2026-08-15T03:01:48.455Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/82/91b866c8546b120bff83b73a439d90d2d63ef3aff113599e6b8e4d566848/mypy-2.3.1-cp315-cp315-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:47a8a7a0a7f6f6e63995c0ac36fa0c07b127413fdc81f0439b7f3dccafd33561", size = 15220224, upload-time = "2026-08-15T03:01:23.577Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/78/c226c99208ee40de7c768369fa533f933afa003dfdc606ff021450724e91/mypy-2.3.1-cp315-cp315-musllinux_1_2_x86_64.whl", hash = "sha256:2329c0501293d4e1f33bc15d04d6304d65a1cdda967ee93a05c1e681a3923133", size = 15501512, upload-time = "2026-08-15T03:02:09.453Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/e7/7cfb3f106c393979f4cc37ad6c0586044d50401e3c35b0c003e4f3ba6bc9/mypy-2.3.1-cp315-cp315-pyemscripten_2026_5_wasm32.whl", hash = "sha256:bb26deed807bdb0457cf3e3f1cd7c4a1cf9d66864eaf1b4a61e06805d4c6b1f9", size = 7761913, upload-time = "2026-08-15T03:01:55.65Z" },
+    { url = "https://files.pythonhosted.org/packages/99/3c/52affefa273b97939a1f474ae4a349c8718635c15b941112dfab4291b0c1/mypy-2.3.1-cp315-cp315-win_amd64.whl", hash = "sha256:375d7013876a8233b2d05be185bfa09f689696cd999ce8b1cfe6acac5c80e8a3", size = 11422533, upload-time = "2026-08-15T03:03:24.101Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/b7/75643e70c72a5b346d8a9b1543c967ea8824df2ee3fb7ccba652c272b7bb/mypy-2.3.1-cp315-cp315-win_arm64.whl", hash = "sha256:586b3612214cceabb3c0f588c97e7d1e535393f06a60e912e994f6b3ace97523", size = 10397931, upload-time = "2026-08-15T03:02:55.265Z" },
+    { url = "https://files.pythonhosted.org/packages/10/ce/53be21f2d4adfcd26f63f1184a13ed797015ab463853f117e2e11e4d726f/mypy-2.3.1-cp315-cp315t-macosx_11_0_arm64.whl", hash = "sha256:ef0c6335cda9d807f8193d8ff6204a72bc909fa9882aacbca14f43cdb7188306", size = 15118669, upload-time = "2026-08-15T03:02:51.479Z" },
+    { url = "https://files.pythonhosted.org/packages/62/43/20de757cd42989d291a17fad607742c4c74e875ce5cea00e5a5225020ac1/mypy-2.3.1-cp315-cp315t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e598c8c66401d26b150872154a286e6d484cf2789c3bb28a7556806298423021", size = 15545627, upload-time = "2026-08-15T03:03:05.132Z" },
+    { url = "https://files.pythonhosted.org/packages/7e/fc/092bdf77ad280eaf501422f0f3b966012b528076cc13e41a774861c907d1/mypy-2.3.1-cp315-cp315t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:eda22fd4efa9dcd39331d1dede9b5b8b8a7fd69af07592e778433da98610d29e", size = 16764157, upload-time = "2026-08-15T03:02:23.958Z" },
+    { url = "https://files.pythonhosted.org/packages/94/5c/c94c4d62d909b07f552d0d9356d7acc943825558e602a64822ffa2231536/mypy-2.3.1-cp315-cp315t-musllinux_1_2_x86_64.whl", hash = "sha256:2a0ba2e57847849fb0d1fcdabb32786d223095ed8bc121dfe322bcdb3d9c46bc", size = 17073258, upload-time = "2026-08-15T03:02:14.573Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/f7/511a88b89e478053c02d22039bb8f3ce4183efe8fd7a4f0a5910a8bb0a32/mypy-2.3.1-cp315-cp315t-win_amd64.whl", hash = "sha256:3f7e865dd51f235f60a2dbcd8728a1c095f5ca28f095d48a725b84cd935735c4", size = 12135505, upload-time = "2026-08-15T03:02:16.714Z" },
+    { url = "https://files.pythonhosted.org/packages/71/bf/02573b56964ecb0f7c644f915f53c325ae15c3faec521c5adf11599a32df/mypy-2.3.1-cp315-cp315t-win_arm64.whl", hash = "sha256:8ad80807dc3ab8ea978b1b2b6e4a657194ace1d4ef03e0e731aff1abd517da29", size = 10962647, upload-time = "2026-08-15T03:01:43.712Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/41/9675c7a1e78edecfba0b79e587a52594c56e189368261dc7b3a7fffb9527/mypy-2.3.1-py3-none-any.whl", hash = "sha256:6ed5c7e3419083268e5c9258bd1c1ef91af44a9e89374dbcaf37b775716e72eb", size = 2754338, upload-time = "2026-08-15T03:02:53.4Z" },
+]
+
+[[package]]
+name = "mypy-extensions"
+version = "1.1.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a2/6e/371856a3fb9d31ca8dac321cda606860fa4548858c0cc45d9d1d4ca2628b/mypy_extensions-1.1.0.tar.gz", hash = "sha256:52e68efc3284861e772bbcd66823fde5ae21fd2fdb51c62a211403730b916558", size = 6343, upload-time = "2025-04-22T14:54:24.164Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/79/7b/2c79738432f5c924bef5071f933bcc9efd0473bac3b4aa584a6f7c1c8df8/mypy_extensions-1.1.0-py3-none-any.whl", hash = "sha256:1be4cccdb0f2482337c4743e60421de3a356cd97508abadd57d47403e94f5505", size = 4963, upload-time = "2025-04-22T14:54:22.983Z" },
+]
+
+[[package]]
+name = "packaging"
+version = "26.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/7d/fa/3944b40b07da9ce895c0e6303a5ab7d53da063554f534556b134a54d6093/packaging-26.3.tar.gz", hash = "sha256:94edc256424af38762eb31306eed28beb9f0efc50a8837492c9d6fd6004aed79", size = 313412, upload-time = "2026-08-04T18:15:28.737Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/63/34/ba1c580383c9eada3711951fef0795c80b829a078d72188184bcab9dd527/packaging-26.3-py3-none-any.whl", hash = "sha256:d7193f7c8e4e93f444fde0262bf90af30e16fa0ad0ad44cb553c87339b23cd1c", size = 129956, upload-time = "2026-08-04T18:15:27.159Z" },
+]
+
+[[package]]
+name = "pathspec"
+version = "1.1.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/5a/82/42f767fc1c1143d6fd36efb827202a2d997a375e160a71eb2888a925aac1/pathspec-1.1.1.tar.gz", hash = "sha256:17db5ecd524104a120e173814c90367a96a98d07c45b2e10c2f3919fff91bf5a", size = 135180, upload-time = "2026-04-27T01:46:08.907Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f1/d9/7fb5aa316bc299258e68c73ba3bddbc499654a07f151cba08f6153988714/pathspec-1.1.1-py3-none-any.whl", hash = "sha256:a00ce642f577bf7f473932318056212bc4f8bfdf53128c78bbd5af0b9b20b189", size = 57328, upload-time = "2026-04-27T01:46:07.06Z" },
+]
+
+[[package]]
+name = "pluggy"
+version = "1.6.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f9/e2/3e91f31a7d2b083fe6ef3fa267035b518369d9511ffab804f839851d2779/pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3", size = 69412, upload-time = "2025-05-15T12:30:07.975Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538, upload-time = "2025-05-15T12:30:06.134Z" },
+]
+
+[[package]]
+name = "pydantic"
+version = "2.13.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "annotated-types" },
+    { name = "pydantic-core" },
+    { name = "typing-extensions" },
+    { name = "typing-inspection" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/53/ef/fc4f868f4e2cee79f863883abffceff107875f569b848507319842d2a681/pydantic-2.13.5.tar.gz", hash = "sha256:51a9c5f7b2f8e636f04c6cada605d9b6a3bf1348fdf945a3d8869b19bba0ee08", size = 845750, upload-time = "2026-08-28T14:04:00.916Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/eb/47/c95ffc2009878c7aac0c5e08528022dcb885933252a88b5f170058014464/pydantic-2.13.5-py3-none-any.whl", hash = "sha256:346a034f080da3755d8e9cb5e00e8b07de1d39e4f6e2c87d8ab7cafa0b269a73", size = 472589, upload-time = "2026-08-28T14:03:59.136Z" },
+]
+
+[[package]]
+name = "pydantic-core"
+version = "2.46.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/af/f9/8a06bea35ef8daf588f707784c973a7046e0034c8d8cfb08828eeffb8b75/pydantic_core-2.46.5.tar.gz", hash = "sha256:10416c15b8839ecc4ef4d0885da76da6fd0f67333a0eb8aff6d93c4b8f2910fc", size = 472262, upload-time = "2026-08-28T10:01:31.677Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/82/3f/76358795aa7a8c6d4f36e2cb828ad1c90ee118e1393a9281664f5aade9d4/pydantic_core-2.46.5-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:b9fe6fb92520e3fd61f2e49000b6911b188824f089b75973ea06d6267f0b476d", size = 2076516, upload-time = "2026-08-28T09:58:21.576Z" },
+    { url = "https://files.pythonhosted.org/packages/db/50/26b091836076ce4cb2fac264186936acc069e0595772cfd02a563bc4761a/pydantic_core-2.46.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a39ac25a9a2fa4072efdb429833c4a4c8009a51ff9eea3eeae131713cd27991e", size = 1922874, upload-time = "2026-08-28T09:58:23.766Z" },
+    { url = "https://files.pythonhosted.org/packages/09/f0/2a8ce3849e299d44e2d2c196b6082643a3235565a735cb51db7a6261f614/pydantic_core-2.46.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4fdc8b93a41521988916eeaa271173fcca7fa0803d62f87675aac8dcec1c8e29", size = 1951772, upload-time = "2026-08-28T09:58:25.435Z" },
+    { url = "https://files.pythonhosted.org/packages/87/46/ac0dc8bdd9e6048183a14eb127764e7ad9240021c17513074a4711b0e31e/pydantic_core-2.46.5-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:b98134087d9de723658d17a42c7d0da8d6e2ef08015dee7dc93889047315f5e4", size = 2031832, upload-time = "2026-08-28T09:58:27.102Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/c2/339de5bef7be36301a2231eaa52e62163742c2281f11b5f4892bc79785cd/pydantic_core-2.46.5-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e652ab17569c94bff5475520f907b7148b8c24036a8ebbe5cf7cf7493d28579a", size = 2208645, upload-time = "2026-08-28T09:58:28.948Z" },
+    { url = "https://files.pythonhosted.org/packages/7b/a0/9ff22b797724262da14427abaed4dd1d864a139693fc5e7809114376a716/pydantic_core-2.46.5-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d925f3d9afd05a8c0fb3a1031463a8d59ebe5e2afad297e29c78be19e13b4e62", size = 2265935, upload-time = "2026-08-28T09:58:30.625Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/a4/eb9409ec0736e50aa70a412f16c204ed149516846912f7e6724d4c73ee53/pydantic_core-2.46.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0fc5be0abd4a407e200d844b404e33639a554e7bd0d448e7b9ae181be4789ac2", size = 2066284, upload-time = "2026-08-28T09:58:32.289Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/02/7f6156ffc926857f1c37c07d9a388682865a81830ab6a1b637082c25e399/pydantic_core-2.46.5-cp312-cp312-manylinux_2_31_riscv64.whl", hash = "sha256:816ff0a6550ffc06c098ccd2e0698600f9aa7da192a79eaa6f9af504a35db869", size = 2105889, upload-time = "2026-08-28T09:58:33.986Z" },
+    { url = "https://files.pythonhosted.org/packages/92/b1/e781d357ebe09fc929f995700f1b3503e8897f1cece183ecb1300d4d67e9/pydantic_core-2.46.5-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c7ea57fc63aa7da93a1bd2d644e6577befae10c52c4e36377635eea1056a74f5", size = 2158006, upload-time = "2026-08-28T09:58:35.647Z" },
+    { url = "https://files.pythonhosted.org/packages/70/0a/644597d84ab400e50609c192120b85c9681c22d3a20461b9060a79be0a7a/pydantic_core-2.46.5-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:efd62a42486f1bda5d24cb4f63d15a3c7768375fe83d36f9417b4ad7a2fb20b3", size = 2158408, upload-time = "2026-08-28T09:58:37.38Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/ee/ca3b7b3a4b3769ffe9ce9432a7c9be755de9593a46d3b0d54d0409323e44/pydantic_core-2.46.5-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:2bc9419666990c06d7397831f2126a1ecc3594aaa3ff7de5bf2d066802f4e07b", size = 2309609, upload-time = "2026-08-28T09:58:39.22Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/52/39fa1f451486019524ca685020390e7ca351832fd874530ba30c8628e6dc/pydantic_core-2.46.5-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:18a09e1e1011b462f2e32774f25859ef1223d5c2b0546a633cf56654710721e0", size = 2342618, upload-time = "2026-08-28T09:58:40.89Z" },
+    { url = "https://files.pythonhosted.org/packages/81/5e/468fc630568c61dcef3cd47ad32ffbeed9af643f49208d1ea86ab4f890c4/pydantic_core-2.46.5-cp312-cp312-win32.whl", hash = "sha256:5cb482e9e84c851f4e623fe4acc1ced89168cf1fe18f7089db4548c8f5bbb65b", size = 1939475, upload-time = "2026-08-28T09:58:42.591Z" },
+    { url = "https://files.pythonhosted.org/packages/cf/c9/4c19f41b84cf6b622a72fbeed7665b25d47a187d68d47d0d430c07f23268/pydantic_core-2.46.5-cp312-cp312-win_amd64.whl", hash = "sha256:5e81740c09e310f5aa5cbd3e434a01c154d4bef93241c7877b39f211d2b78ba8", size = 2043140, upload-time = "2026-08-28T09:58:44.272Z" },
+    { url = "https://files.pythonhosted.org/packages/af/dd/0c1a050299147c746e5256db16d645ab5efd4f78c59937d581a0524e74a2/pydantic_core-2.46.5-cp312-cp312-win_arm64.whl", hash = "sha256:f7b0ec93a2893de856652154d73b7ba622f26fa97726487dcac373de5f4c6084", size = 1997729, upload-time = "2026-08-28T09:58:46.13Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/37/5abe39a8372a61d3dc3c1338fc504281c01b32fdb3169cd7187153b56d3e/pydantic_core-2.46.5-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:b7ca9034437b6022f941f4857459562ee00a560b97e7cce8a0ec5a74fc6766e0", size = 2075885, upload-time = "2026-08-28T09:58:47.856Z" },
+    { url = "https://files.pythonhosted.org/packages/21/43/6323b1f8b217780454c61304bcd2b38ae4762f50754414124603ccc90bb2/pydantic_core-2.46.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:f332f0e72a5a0400141f830744e141bf9f97917878dbe968669e8a7fefea78ff", size = 1922768, upload-time = "2026-08-28T09:58:49.58Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/a3/c05ca796e1197618a774b01e596aeedfefc2f7d8c01ae3054e910b120e8a/pydantic_core-2.46.5-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:193375f3548919d3f0b60936ca113ada3e38f264f91b9b8e0508efaad57be931", size = 1951241, upload-time = "2026-08-28T09:58:51.511Z" },
+    { url = "https://files.pythonhosted.org/packages/68/32/33bc39ac705c52cffc908e8389f9754fdb208aea5c69cceddf4eb3ce99af/pydantic_core-2.46.5-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:79bdfa52f843137045b2d081cc05c120ba6665d29b7559c2c47690906f39279f", size = 2031975, upload-time = "2026-08-28T09:58:53.166Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/70/2333e885c0f6a67bc105c5916965dac9b57f2718ee20d81d1a06a4ebdc13/pydantic_core-2.46.5-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:24922243639cbdac66c75fcb6fd6495a9cb52b213d62f9a0d16f0310b1ff8038", size = 2208542, upload-time = "2026-08-28T09:58:55.017Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/ea/296debfb4264207bbda5936133892e027c0a58875ad53ebd512fba8ec3a2/pydantic_core-2.46.5-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c76fe65e607be28c7fd4d56fc3c42b1583aa058ce3408b7ad0fd540171d31f9f", size = 2264692, upload-time = "2026-08-28T09:58:56.767Z" },
+    { url = "https://files.pythonhosted.org/packages/d3/f2/9e4de77a6271e07a76d2d58b11c091a979c191ed2939bf80067568b369d2/pydantic_core-2.46.5-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f7b393a8b3da82f5c1fc0751e6d01ac6c55b93c18226a60bdfba4a724efafd1", size = 2066633, upload-time = "2026-08-28T09:58:58.531Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/db/f9e9d0c97445987b2084823d5c240de88087338f04fc2cfaa2df186b8049/pydantic_core-2.46.5-cp313-cp313-manylinux_2_31_riscv64.whl", hash = "sha256:7ac031912d54f3d83ef3b3eb98dfabc1608802e2202263d25957eeed40b94761", size = 2105235, upload-time = "2026-08-28T09:59:00.421Z" },
+    { url = "https://files.pythonhosted.org/packages/07/c5/79169b047b3b2c3e99e04bc76372af9637e0bf6db638274fa927df96369e/pydantic_core-2.46.5-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:837b396ca3d7b74091ca623f6cbd8351bd42d670a79c2683e79fb089f06a2de5", size = 2157367, upload-time = "2026-08-28T09:59:02.442Z" },
+    { url = "https://files.pythonhosted.org/packages/26/b5/ba6057afb7c291bd449f51b867f95aef2072941c4ce4e5c31d6ffd132d3b/pydantic_core-2.46.5-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:5ee239d575f80b08eca11f6e20f90c4c695de7825c67eefe6091fbf20dda648e", size = 2158420, upload-time = "2026-08-28T09:59:04.2Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/28/2057abecaafdc22912afa819603a51f0a62d40643b7c4871c51721fea9be/pydantic_core-2.46.5-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:e80675d75ae2cd14372cb65cad5400d9347a3d3f6c13000183f22dfd027283ed", size = 2309588, upload-time = "2026-08-28T09:59:06.048Z" },
+    { url = "https://files.pythonhosted.org/packages/71/9d/881156dc404e27479c4246128d73538464cab4a239bec61995e227644c30/pydantic_core-2.46.5-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:9c4b71f10dd532fb7a5cbc8f58707779e64f03a258c2bf8bfbaecfcd9970b519", size = 2341866, upload-time = "2026-08-28T09:59:08.539Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/38/d66f443a259f84d13babdceae568e572b0ed26da17ca5d0a649ebb110a67/pydantic_core-2.46.5-cp313-cp313-win32.whl", hash = "sha256:97bf8de4d541598c94a59344eeb988a94c08ff76b5723c41f6567ec18c7892ea", size = 1938580, upload-time = "2026-08-28T09:59:10.402Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/1e/1d5371213f4cc9a7ed70c0bfcc7911de22311ee99a662a56077d7292d2ac/pydantic_core-2.46.5-cp313-cp313-win_amd64.whl", hash = "sha256:15f4a94963c95accac15b7b657bb177d3ad82bb90b0d0526d9a9b85079925db5", size = 2041980, upload-time = "2026-08-28T09:59:12.396Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/48/4222d90b1c67568bace4dec6dca6271449c66de3595d72b6d098f5fde597/pydantic_core-2.46.5-cp313-cp313-win_arm64.whl", hash = "sha256:d22a945598fb91236b4dd793a6e42e4f3dd7740bb5aace5ebd7d4c08d13bb575", size = 1997213, upload-time = "2026-08-28T09:59:14.245Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/8a/14596f2a8367da50cf7cbac48169ee5d9c8e11d486a3b527082384630c72/pydantic_core-2.46.5-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:c1c43ad4339643d70ebb8124e1305a7dab423001eff58bb41a0f731adbc98355", size = 2074081, upload-time = "2026-08-28T09:59:16.141Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/d5/d8a4eb6d6c7f66b91dd37c576d76e9e60fba900caf5372c17bcf949febc2/pydantic_core-2.46.5-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:1a353f84de772f423b5ffb11d7ae352fbbef0f446f3c0b0af0f8236d7233606e", size = 1920497, upload-time = "2026-08-28T09:59:18.065Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/26/092079428f86e927e030b2c0ced87df69dbb1c875cdeaa67bf42ea2be746/pydantic_core-2.46.5-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5086029a57366b8cf81b130a43908738095c270c21a8d7f0e8bdfdb89718e2f3", size = 1952130, upload-time = "2026-08-28T09:59:20.476Z" },
+    { url = "https://files.pythonhosted.org/packages/08/c3/8ec0e290a9ebaebd64047bf5fda94be835c6b1551b02437e4b76778fbcd7/pydantic_core-2.46.5-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:46c25dda9d092a06c08db76ffe0a197107904d0dfac653f7d5306bbcd6d6119c", size = 2026371, upload-time = "2026-08-28T09:59:22.227Z" },
+    { url = "https://files.pythonhosted.org/packages/01/72/4fd20ad520fb8da0157f95b27a7eb05a72790ef08138e7701ac972c342ea/pydantic_core-2.46.5-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:37ea7b83c935e5b0d68c9449b82651accf78a10828b2c02b2f2d9e9496446c21", size = 2202822, upload-time = "2026-08-28T09:59:24.277Z" },
+    { url = "https://files.pythonhosted.org/packages/31/b0/d16e0771206b29314f0d52198b720be21e8a99ab2bf11e3bc0d7c9cebdff/pydantic_core-2.46.5-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e64e88d5585bea9ce95861079de72006c7fa6d3df4e3a3b65ba31eb979c15c9f", size = 2262756, upload-time = "2026-08-28T09:59:26.608Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/9b/59634b7ac631c63b2a37760eb6943af3e29573d6b59a4abc5e7f019d4cee/pydantic_core-2.46.5-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:54d510bac3ee52247af28ed4bb18a1e799f040ac60fd2bf5ccd4c92f1fbe786f", size = 2068352, upload-time = "2026-08-28T09:59:29.044Z" },
+    { url = "https://files.pythonhosted.org/packages/08/7c/570abb1ad2155348dc754ea91be22e5aaa18eb6d69a6068f7c6f2679a6ed/pydantic_core-2.46.5-cp314-cp314-manylinux_2_31_riscv64.whl", hash = "sha256:a2a5e1d0ff29adddc9f6d6821a66302e4493f8ca898b715b6b1182c2c201ea0a", size = 2104777, upload-time = "2026-08-28T09:59:30.95Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/25/5bf74adc65a1ac5b7be3f6cb0bcb5433615c1598a801c19d830d84c98ded/pydantic_core-2.46.5-cp314-cp314-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:03b9666e41e35d8909852ba191a0607520f81b74eaf12ccf8737005dbb313821", size = 2156312, upload-time = "2026-08-28T09:59:32.604Z" },
+    { url = "https://files.pythonhosted.org/packages/90/6a/2ef38830675e050121040618135564ed56b860b45433b02d9b4ebece46f3/pydantic_core-2.46.5-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:a91c17edf6eea2402cb5457b4c89e99bc5ed1004aa34c4adf1d4258c1a5c22c2", size = 2150067, upload-time = "2026-08-28T09:59:34.453Z" },
+    { url = "https://files.pythonhosted.org/packages/90/ef/a7dbb03a14a64c2a4621f989c615ed9a892535a6cad938fc27079f919d80/pydantic_core-2.46.5-cp314-cp314-musllinux_1_1_armv7l.whl", hash = "sha256:b49924c73a235e969511bf2aabdff3beebf9820931f646c80274d5d780010c47", size = 2304516, upload-time = "2026-08-28T09:59:36.194Z" },
+    { url = "https://files.pythonhosted.org/packages/68/f8/6bb4c4b80e8a6fde1904c64a51c62a1d04fcdfa3ea521a66b2ddefa1d885/pydantic_core-2.46.5-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:2cbd9a5eff05e51c447c34dfa4632145b26b09120cf04bd0c871e44c1a5e1c9a", size = 2335223, upload-time = "2026-08-28T09:59:37.931Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/80/f46b8c681195190b2c1f1c7c0a81abce60663e987613e09ef64d433dd96b/pydantic_core-2.46.5-cp314-cp314-win32.whl", hash = "sha256:2d5d76654becf5efd62c9e51c3756c67b49498b0c9a40884934c40807adbd074", size = 1934827, upload-time = "2026-08-28T09:59:39.836Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/3c/60674207246bc0a4009d2391b7c7251c7159f279c8d2ab8aae8ef46f3dee/pydantic_core-2.46.5-cp314-cp314-win_amd64.whl", hash = "sha256:fa10ef4112775900e7a0661068635eb67b2ab824fbde764de6e0e21982a93db0", size = 2042648, upload-time = "2026-08-28T09:59:41.792Z" },
+    { url = "https://files.pythonhosted.org/packages/69/0c/117c562c7c1babdf44576b72a5e496906506c93690387ecfbca7c729ae2e/pydantic_core-2.46.5-cp314-cp314-win_arm64.whl", hash = "sha256:045ab3b6d308439e32b81cc173bba5b9018bc6ed896afd0c65b3b009b1699af5", size = 1989652, upload-time = "2026-08-28T09:59:43.702Z" },
+    { url = "https://files.pythonhosted.org/packages/e8/66/9336ae58f9eb68c41d121894e52c4c89eccb07eb8f602a04ee9c3f37736a/pydantic_core-2.46.5-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:8816f3d218beb4b787de5c9759c259b8fa61f9dec42dc7811f320a33771778b7", size = 2065829, upload-time = "2026-08-28T09:59:45.364Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/02/bc19b47a96c2d3109760711acf22369e56bd7e405ca52f7ade164d2ead57/pydantic_core-2.46.5-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:bce57638e08ac148e5778cce7feb968307a727d66f8e2274a543d0cf0c9ad6a3", size = 1905716, upload-time = "2026-08-28T09:59:47.18Z" },
+    { url = "https://files.pythonhosted.org/packages/52/a4/70b47c0509923dd98ccfed04fb3e32ea3849c82a0ff2205bb41009b43c00/pydantic_core-2.46.5-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:976e1128455aa595ea04c79ccfedff1aaeab96ee013fcc916bed120c4f0ad94f", size = 1934216, upload-time = "2026-08-28T09:59:49.241Z" },
+    { url = "https://files.pythonhosted.org/packages/52/ab/aa03b65f7bb198585edf806b906c3223ecf1795543e39e23aec4cce27ad2/pydantic_core-2.46.5-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e7b891faeedeafba41b2983e5001a81b6a915b69544c7e7570d1989ce1c36ac7", size = 2010635, upload-time = "2026-08-28T09:59:51.692Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/8b/0da06343f30b84ec549aafd309c6456223d5dc8bd36af504c573faad561d/pydantic_core-2.46.5-cp314-cp314t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5f194189415698233dd1114a093a9b56e61e2c57e11b469be3b0506f46f0771c", size = 2209369, upload-time = "2026-08-28T09:59:53.582Z" },
+    { url = "https://files.pythonhosted.org/packages/d6/5b/844c4defaa34a3df66eb9257087d121d70c201298b96abdf9f492fc2f1bf/pydantic_core-2.46.5-cp314-cp314t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:82a36973cf8a2ef5406f4fe2edbf8ed0c99629535d959e0b100c76a32535a111", size = 2253238, upload-time = "2026-08-28T09:59:55.484Z" },
+    { url = "https://files.pythonhosted.org/packages/f4/64/a4e536cb16d7f61a7fd3120b46c577fc7fa7325992f69c4f52bc786d77d8/pydantic_core-2.46.5-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cdbb78909f52b981d3b2d56b97328d71eb0b974c36bd77c920123a7ebb192829", size = 2065740, upload-time = "2026-08-28T09:59:58.038Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/75/aaa38c6bc2d085f6605b34eabdc6a8a4e0b2e61fc9c8e6e52b28e97b3125/pydantic_core-2.46.5-cp314-cp314t-manylinux_2_31_riscv64.whl", hash = "sha256:52e24eacdb536cade636aa90fb851835222becff8484b7001fdc78cb0290f2aa", size = 2087425, upload-time = "2026-08-28T09:59:59.898Z" },
+    { url = "https://files.pythonhosted.org/packages/55/ae/fcab4cfc39aba3689e1d20c8b5250ad280957022c09af2ed9cd585602a5e/pydantic_core-2.46.5-cp314-cp314t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:37ae34309d7bd8c0d61ab839668058f2a7962ea1fc51d105d2db228fe0618034", size = 2139306, upload-time = "2026-08-28T10:00:03.057Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/f4/f1d03a4bc9d9acbc62f4d742b8a319af52f71885079868b2ff8e48a651ee/pydantic_core-2.46.5-cp314-cp314t-musllinux_1_1_aarch64.whl", hash = "sha256:0cdbada856a1c69a7624a64d3d9aefe79300bd6ef827b43a4f265010b9b55184", size = 2144589, upload-time = "2026-08-28T10:00:05.645Z" },
+    { url = "https://files.pythonhosted.org/packages/83/f3/7a53bb1356de514a4cd295f25b6ac39237895620c0462d2592b76c16e114/pydantic_core-2.46.5-cp314-cp314t-musllinux_1_1_armv7l.whl", hash = "sha256:545f26c504b27c3758439a5e6d9349931f0a04f855668d5fe323c89e82300a38", size = 2288882, upload-time = "2026-08-28T10:00:07.931Z" },
+    { url = "https://files.pythonhosted.org/packages/cd/94/5a81583660c175c59d49ffb09f4b3a44debeaf86a19fca664ae1cdd9ee32/pydantic_core-2.46.5-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:ff218293c9c806138dca139765e3b067621be52bcd93cdc14c7711be7ddc90a9", size = 2335210, upload-time = "2026-08-28T10:00:10.177Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/9f/5d685c2693b972d1a59c998586e8823712b66603aeff47ee60a4bdaafd37/pydantic_core-2.46.5-cp314-cp314t-win32.whl", hash = "sha256:97cf3eb53a8cccacf9d46686a0926186c9bfb5574f2ed66d3639d5fe117cd3a9", size = 1921180, upload-time = "2026-08-28T10:00:12.35Z" },
+    { url = "https://files.pythonhosted.org/packages/70/12/5c94ee16d65a37a15f9e869f5e6256df111154491173801a4c5e800ab548/pydantic_core-2.46.5-cp314-cp314t-win_amd64.whl", hash = "sha256:d2f9fc07a8042a8f95925b35c4f04f469707c981fc33245b6ca187cf5d2dd290", size = 2020515, upload-time = "2026-08-28T10:00:14.774Z" },
+    { url = "https://files.pythonhosted.org/packages/63/19/67830dda664e6bdf9285ee2e40f355d0d7d6b92aa0c42e8d217bb8d33d36/pydantic_core-2.46.5-cp314-cp314t-win_arm64.whl", hash = "sha256:acf8a67ba51f4ca9ddbd0e6b3000a65ac51ab734661778b3e7ba64d99a710f2f", size = 1989276, upload-time = "2026-08-28T10:00:16.984Z" },
+    { url = "https://files.pythonhosted.org/packages/df/dd/053c2e4303f791f3b8f8a14ab0b22008e8eb21d868c0c90b4f9be705b76a/pydantic_core-2.46.5-graalpy312-graalpy250_312_native-macosx_10_12_x86_64.whl", hash = "sha256:013d6f3483d81e02e7c328831808f336c8596ee33b4bd4026b9ffb1e960b8942", size = 2062540, upload-time = "2026-08-28T10:01:00.318Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/dd/a18df751a5e37dd51bfad7f68e766999125bebe68c9e1d10a493ad01bd63/pydantic_core-2.46.5-graalpy312-graalpy250_312_native-macosx_11_0_arm64.whl", hash = "sha256:e9c134bb666dd54b778b9fc0d2b50cbb7f979b9e3716f26a88c9ab3b6fc1dd0f", size = 1902040, upload-time = "2026-08-28T10:01:02.529Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/13/01d40f9d07ce8a779fd6e0bd8ad4fba91309500dd67b869e2e219d261a6d/pydantic_core-2.46.5-graalpy312-graalpy250_312_native-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:347ec774390c87326a2e4929d58d3f7e8763a104d5d35f4cd595a4c952366433", size = 1967479, upload-time = "2026-08-28T10:01:05.004Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/04/c81d4841331c2178b6fb09ae225425e110ed72d990c9fe556c4ec03d1013/pydantic_core-2.46.5-graalpy312-graalpy250_312_native-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8e24d8f05fa2d28513d94e877e9c75ad66175376209b3977f916e240e623193c", size = 2111034, upload-time = "2026-08-28T10:01:07.345Z" },
+]
+
+[[package]]
+name = "pygments"
+version = "2.21.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/49/2e/ced460408999b33da6b31b0021b0f37d329e202d4169aeb164493778f25b/pygments-2.21.0.tar.gz", hash = "sha256:610ca751c9bc2492b38eb9a38a7fbc93edbbb2d7182edaf34e66ae493dee5c8c", size = 5005329, upload-time = "2026-08-17T08:02:48.824Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/71/46/17f022dd3e953bf20a04a028a21ec746d942f8d2af30fa0f124fa0e6a684/pygments-2.21.0-py3-none-any.whl", hash = "sha256:2363c69b61c4a97c838da3b130dcd6468f4848992b21a82f2a63ec34377137d9", size = 1250147, upload-time = "2026-08-17T08:02:44.912Z" },
+]
+
+[[package]]
+name = "pytest"
+version = "9.1.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "iniconfig" },
+    { name = "packaging" },
+    { name = "pluggy" },
+    { name = "pygments" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e4/47/b9efed96c114afcfa3c9d3fe98a76a1d14c74a9e266d397cf6eb64be5e01/pytest-9.1.1.tar.gz", hash = "sha256:1088fbde8f2b49d95a549a195707afa7a76a3ce9bcadc26b6d71f0ffda5fe313", size = 1636369, upload-time = "2026-06-19T10:58:32.857Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/24/25/1de2678b631f5a49215c6c96fff41ba892b0a34df68d6d80292b1b48aa7f/pytest-9.1.1-py3-none-any.whl", hash = "sha256:37a86b45efb9a47a61a36449063e8e18d0cab3161329fc099eb21783169c4f0c", size = 386536, upload-time = "2026-06-19T10:58:31.347Z" },
+]
+
+[[package]]
+name = "pytest-asyncio"
+version = "1.4.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pytest" },
+    { name = "typing-extensions", marker = "python_full_version < '3.13'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/43/7c/d36d04db312ecf4298932ef77e6e4a9e8ad017906e24e34f0b0c361a2473/pytest_asyncio-1.4.0.tar.gz", hash = "sha256:c6c0d2259945122819f171a32ecea2c349ead889ee28176caaf492143424be42", size = 58514, upload-time = "2026-05-26T09:56:04.083Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/03/e2/08a497ef684b88559c9cc5f4ad53a37e7b99e727094a86d6ea32536d5d3c/pytest_asyncio-1.4.0-py3-none-any.whl", hash = "sha256:933ca923a23075a87fb7070c0ec272a6848489824d887c85c812670932835aa1", size = 16930, upload-time = "2026-05-26T09:56:02.576Z" },
+]
+
+[[package]]
+name = "researchx"
+version = "0.2.0"
+source = { editable = "." }
+dependencies = [
+    { name = "fastapi" },
+    { name = "httpx" },
+    { name = "pydantic" },
+    { name = "sse-starlette" },
+    { name = "uvicorn" },
+]
+
+[package.dev-dependencies]
+dev = [
+    { name = "httpx" },
+    { name = "mypy" },
+    { name = "pytest" },
+    { name = "pytest-asyncio" },
+    { name = "ruff" },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "fastapi", specifier = ">=0.115,<0.116" },
+    { name = "httpx", specifier = ">=0.27,<1" },
+    { name = "pydantic", specifier = ">=2.8,<3" },
+    { name = "sse-starlette", specifier = ">=2.1,<3" },
+    { name = "uvicorn", specifier = ">=0.30,<1" },
+]
+
+[package.metadata.requires-dev]
+dev = [
+    { name = "httpx", specifier = ">=0.28.1" },
+    { name = "mypy", specifier = ">=1.11" },
+    { name = "pytest", specifier = ">=8" },
+    { name = "pytest-asyncio", specifier = ">=0.23" },
+    { name = "ruff", specifier = ">=0.6" },
+]
+
+[[package]]
+name = "ruff"
+version = "0.16.9"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/96/bf/c935ca98e73fe8ce65b87ef08a280c0c1e85295d569228c15e87d8fdfaf1/ruff-0.16.9.tar.gz", hash = "sha256:12b625c6cfba78d285d9f48eda5f053374f1e53cb10ef17342a383750db99161", size = 4948764, upload-time = "2026-09-24T20:37:49.416Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0d/26/df51322b52ee1ada7eff2d071ea09d11d5c2d1dcc9f02594f5785c4d1635/ruff-0.16.9-py3-none-linux_armv6l.whl", hash = "sha256:95e6f022090368ab3b824c36276839c53b2adf1a3f4c09fefc33dfc400f6da96", size = 10082922, upload-time = "2026-09-24T20:37:13.045Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/27/7bf51f5a7aa375e9f339280a303aab44ca75dc1525f1cdc5991761685b0f/ruff-0.16.9-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:a5f27be168556594a86d2f415db0cf43f5291917849318f873c7e2791f7a8c67", size = 10236360, upload-time = "2026-09-24T20:37:16.049Z" },
+    { url = "https://files.pythonhosted.org/packages/b6/63/09659283f92f02dff45809da194a70da2f688d87c55d8875c4fae3536072/ruff-0.16.9-py3-none-macosx_11_0_arm64.whl", hash = "sha256:1632eb1d6197f33bd00b1acbc5b71009e89a8895c158e2d2b03a834fac964ab6", size = 9892940, upload-time = "2026-09-24T20:37:17.957Z" },
+    { url = "https://files.pythonhosted.org/packages/24/58/98de1b72ec172f5f8f1731236fe21585b3998bf7dfe9fcc44ae9ba626012/ruff-0.16.9-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b3f951b14d865d5952c89d40a5ca07e87abe24fa5453299878411e127748fb1c", size = 10032114, upload-time = "2026-09-24T20:37:19.942Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/7d/f1e17c54ab59d4bad1dce8ee3e22a7a1d0ef4745240decacdcf3832b5bb2/ruff-0.16.9-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:447fc07e1573afff7cb02803462b12b6c8ece7cf10e2cd78565fa6d7a1c0bf8d", size = 9910227, upload-time = "2026-09-24T20:37:21.872Z" },
+    { url = "https://files.pythonhosted.org/packages/34/19/436f647a65075bbd3bab2668b3bdaa5120559b294694018cdcefabbbf30b/ruff-0.16.9-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8a3e039a6a40ed976c491722b60e0ae4a4aa1a86057f540ee7a37a5d19ae9120", size = 10547484, upload-time = "2026-09-24T20:37:24.229Z" },
+    { url = "https://files.pythonhosted.org/packages/03/59/38430a6bc2f6d8095447ac39625cf8b6e9344a47e6c26225c8ba1bff3ffb/ruff-0.16.9-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4684dded7db60aa57cb118fa158630f5feade4af5782903b6053484bdf9bd129", size = 11412367, upload-time = "2026-09-24T20:37:26.307Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/bd/bbb6d7fc7f208c8b8c50dd5dc8206e4cfdb1e7a8fb852606a3adf370c880/ruff-0.16.9-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d29c934357e45642fda2f34c0b1f4025b4a6c01e15e4bf0016879d60078a142c", size = 10869787, upload-time = "2026-09-24T20:37:28.35Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/b8/9c543074918061abbefc3bd139bee22de35abedb00dde0f2d27288838962/ruff-0.16.9-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a21713e629d3e5bdb2f5c2def1cc7f04f47fa8e1a7eb0571b4a28e1da64bc728", size = 10406494, upload-time = "2026-09-24T20:37:30.624Z" },
+    { url = "https://files.pythonhosted.org/packages/35/7a/5a8851bd146e7ccf8fd4b003f6c75c11f8fbdb0e60673b45097986b6bf41/ruff-0.16.9-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:7baa24ef5fc8e77aa93879e1d3f43754a01ae488e869f1ae30cf431afd4d2452", size = 10590083, upload-time = "2026-09-24T20:37:32.439Z" },
+    { url = "https://files.pythonhosted.org/packages/87/f0/4c3467188f23f806960b46fa76575a7cd0514c9ba90562650b71efc96980/ruff-0.16.9-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:a41aac6230aadfaa133bdfa1614488531ffa3e0837567ae04c0da2058a9c0f9e", size = 10119151, upload-time = "2026-09-24T20:37:34.581Z" },
+    { url = "https://files.pythonhosted.org/packages/15/34/5a4def5adea572ce6aea0bb64f21f928ee317b80e0db747d7979b01d7261/ruff-0.16.9-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:c2529fb5896d49115b0e9aa8f887490b34bbe76baf879ec2264ac59406869ce7", size = 9911544, upload-time = "2026-09-24T20:37:36.796Z" },
+    { url = "https://files.pythonhosted.org/packages/62/5d/d15ebea7499eef9373318c0ee6ca127832927c6529731f6d48e18dce7ca9/ruff-0.16.9-py3-none-musllinux_1_2_i686.whl", hash = "sha256:41e3870277694177429b56406d65dfbdb2c2802c52b715edaf6a0b829c69d4ee", size = 10269884, upload-time = "2026-09-24T20:37:38.857Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/56/c5d3cd119ded7a3c7aba0e961b69cb3df701c91662c98ad694467d060ce1/ruff-0.16.9-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:8adbe4e58af167f767d7b2ba5e83c42e878350796cf78c2f5e14ab9903a92588", size = 10749366, upload-time = "2026-09-24T20:37:41.042Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/fe/734ec7527029ac757ecf821f143c9f3fcf69149c21f53a044a899b430f5a/ruff-0.16.9-py3-none-win32.whl", hash = "sha256:0e1dbc2073624dee6618d41d0098690a7244654af746704b64759e12b6b6b385", size = 10152355, upload-time = "2026-09-24T20:37:43.025Z" },
+    { url = "https://files.pythonhosted.org/packages/14/21/26e4643629b3ebb44f0a06f9c9a53058d63d989415f63a9a3c28e2ee7f22/ruff-0.16.9-py3-none-win_amd64.whl", hash = "sha256:6bd40fec8cd4c8a3d4dd589bd8ad4e6320c13c29234159bfd959a40d529d597b", size = 10592965, upload-time = "2026-09-24T20:37:44.944Z" },
+    { url = "https://files.pythonhosted.org/packages/51/60/5fb1a39dbb5ae314d5f59bc7348a63c1d5c20f3cd83914c4b5cb0be31d2d/ruff-0.16.9-py3-none-win_arm64.whl", hash = "sha256:ed1a252039200f57a59eebc063b54beabea67bfbaaca0eeaa7f54b5fbcda2284", size = 10458649, upload-time = "2026-09-24T20:37:46.882Z" },
+]
+
+[[package]]
+name = "sse-starlette"
+version = "2.4.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/07/3e/eae74d8d33e3262bae0a7e023bb43d8bdd27980aa3557333f4632611151f/sse_starlette-2.4.1.tar.gz", hash = "sha256:7c8a800a1ca343e9165fc06bbda45c78e4c6166320707ae30b416c42da070926", size = 18635, upload-time = "2025-07-06T09:41:33.631Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e4/f1/6c7eaa8187ba789a6dd6d74430307478d2a91c23a5452ab339b6fbe15a08/sse_starlette-2.4.1-py3-none-any.whl", hash = "sha256:08b77ea898ab1a13a428b2b6f73cfe6d0e607a7b4e15b9bb23e4a37b087fd39a", size = 10824, upload-time = "2025-07-06T09:41:32.321Z" },
+]
+
+[[package]]
+name = "starlette"
+version = "0.46.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ce/20/08dfcd9c983f6a6f4a1000d934b9e6d626cff8d2eeb77a89a68eef20a2b7/starlette-0.46.2.tar.gz", hash = "sha256:7f7361f34eed179294600af672f565727419830b54b7b084efe44bb82d2fccd5", size = 2580846, upload-time = "2025-04-13T13:56:17.942Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8b/0c/9d30a4ebeb6db2b25a841afbb80f6ef9a854fc3b41be131d249a977b4959/starlette-0.46.2-py3-none-any.whl", hash = "sha256:595633ce89f8ffa71a015caed34a5b2dc1c0cdb3f0f1fbd1e69339cf2abeec35", size = 72037, upload-time = "2025-04-13T13:56:16.21Z" },
+]
+
+[[package]]
+name = "typing-extensions"
+version = "4.16.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f6/cc/6253133b5bb138fc3306cebfbda2c520f545d36b5be2c7255cc528bb45d6/typing_extensions-4.16.0.tar.gz", hash = "sha256:dc983d19a509c94dba722ee6abd33940f7c05a89e243c47e907eb4db6f1a43e5", size = 113555, upload-time = "2026-07-02T08:40:05.92Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/49/d3/b8441a820a491ddfc024b0b0cf0393375b75ea13866d9c66727e54c2fc80/typing_extensions-4.16.0-py3-none-any.whl", hash = "sha256:481caa481374e813c1b176ada14e97f1f67a4539ce9cfeb3f350d78d6370c2e8", size = 45571, upload-time = "2026-07-02T08:40:04.659Z" },
+]
+
+[[package]]
+name = "typing-inspection"
+version = "0.4.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a3/26/b09b8010994eccc3c09092e6b34058f36a460eea2d4c3e8b910c695975a0/typing_inspection-0.4.4.tar.gz", hash = "sha256:547274fa6b0a561ccf549cc9524b999a578e737d015d8709d021f9d0d13bea47", size = 76928, upload-time = "2026-08-12T12:37:25.997Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/67/81/4add07e5172b7ac40d8ed5ff580409a7801a4fe26d529bdd915401dabfbe/typing_inspection-0.4.4-py3-none-any.whl", hash = "sha256:65b8397ba37ccbce054456aaccddfc91e6e3083c92824df348d96ca832f3f147", size = 14750, upload-time = "2026-08-12T12:37:24.648Z" },
+]
+
+[[package]]
+name = "uvicorn"
+version = "0.54.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "click" },
+    { name = "h11" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/da/34/30e9280707135d2cfc589dfff3cb796bd07a3aeb1a3e415ba09dd89d7bb4/uvicorn-0.54.0.tar.gz", hash = "sha256:a2e33cbfaa0306f8e6b0c13e0cb89d7d7a2da3e62b90c66e18c33d9807b28620", size = 112283, upload-time = "2026-09-25T06:52:37.601Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/38/0c/b54a4fdd7f90a3af8b02ebc9ce6712c2c208b7926a2f7bad95c33ebbe943/uvicorn-0.54.0-py3-none-any.whl", hash = "sha256:505bdb0f318731d45f1f712071fc781a8981f6847a31c902c9f5e652d4f67faf", size = 87427, upload-time = "2026-09-25T06:52:35.829Z" },
+]

frontend/README.md

@@ -1,5 +1,12 @@
 # ResearchX Frontend
 
+**TL;DR** — This is the ResearchX web interface: ask a question, choose a research method, approve the plan, watch the live trace, read the cited report. The prototype runs entirely on scripted sample data — no API keys, no backend, no network — so the full product journey is tryable today.
+
+- **What** — A Next.js app (ask, choose, run, report, library, settings) rendering mock data through one typed client interface.
+- **Why** — The journey is checkable end-to-end before live inference exists.
+- **Action** — no action — FYI. Developers: Quickstart below (Node 20+, pnpm).
+- **Details** — Root `README.md`: backend engine, live mode, architecture.
+
 The prototype frontend for ResearchX — methodology-driven deep research
 with a trust loop. This milestone (v0.1) runs **entirely on mock data**:
 no API keys, no env vars, no network calls beyond static assets.

frontend/openapi.json

@@ -0,0 +1,652 @@
+{
+  "openapi": "3.1.0",
+  "info": {
+    "title": "ResearchX API",
+    "version": "0.2.0"
+  },
+  "paths": {
+    "/api/config": {
+      "get": {
+        "summary": "Config Status",
+        "operationId": "config_status_api_config_get",
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ConfigStatus"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/methodologies": {
+      "get": {
+        "summary": "Methodologies",
+        "operationId": "methodologies_api_methodologies_get",
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "items": {
+                    "$ref": "#/components/schemas/MethodologyCard"
+                  },
+                  "type": "array",
+                  "title": "Response Methodologies Api Methodologies Get"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/runs": {
+      "post": {
+        "summary": "Create Run",
+        "operationId": "create_run_api_runs_post",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CreateRunBody"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "201": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunSummary"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/runs/{run_id}": {
+      "get": {
+        "summary": "Get Run",
+        "operationId": "get_run_api_runs__run_id__get",
+        "parameters": [
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "title": "Run Id"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunSummary"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/runs/{run_id}/approve": {
+      "post": {
+        "summary": "Approve Run",
+        "operationId": "approve_run_api_runs__run_id__approve_post",
+        "parameters": [
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "title": "Run Id"
+            }
+          }
+        ],
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "anyOf": [
+                  {
+                    "$ref": "#/components/schemas/ApproveBody"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ],
+                "title": "Body"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunSummary"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/runs/{run_id}/pause": {
+      "post": {
+        "summary": "Pause Run",
+        "operationId": "pause_run_api_runs__run_id__pause_post",
+        "parameters": [
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "title": "Run Id"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunSummary"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/runs/{run_id}/resume": {
+      "post": {
+        "summary": "Resume Run",
+        "operationId": "resume_run_api_runs__run_id__resume_post",
+        "parameters": [
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "title": "Run Id"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunSummary"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/runs/{run_id}/cancel": {
+      "post": {
+        "summary": "Cancel Run",
+        "operationId": "cancel_run_api_runs__run_id__cancel_post",
+        "parameters": [
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "title": "Run Id"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/RunSummary"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/runs/{run_id}/events": {
+      "get": {
+        "summary": "Run Events",
+        "operationId": "run_events_api_runs__run_id__events_get",
+        "parameters": [
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "title": "Run Id"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {}
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/runs/{run_id}/report": {
+      "get": {
+        "summary": "Run Report",
+        "operationId": "run_report_api_runs__run_id__report_get",
+        "parameters": [
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "title": "Run Id"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "additionalProperties": true,
+                  "title": "Response Run Report Api Runs  Run Id  Report Get"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "/api/runs/{run_id}/ledger": {
+      "get": {
+        "summary": "Run Ledger",
+        "operationId": "run_ledger_api_runs__run_id__ledger_get",
+        "parameters": [
+          {
+            "name": "run_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "string",
+              "title": "Run Id"
+            }
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "additionalProperties": true,
+                  "title": "Response Run Ledger Api Runs  Run Id  Ledger Get"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  },
+  "components": {
+    "schemas": {
+      "ApproveBody": {
+        "properties": {
+          "plan": {
+            "anyOf": [
+              {
+                "additionalProperties": true,
+                "type": "object"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "title": "Plan"
+          }
+        },
+        "type": "object",
+        "title": "ApproveBody"
+      },
+      "ConfigStatus": {
+        "properties": {
+          "model_adapter": {
+            "type": "string",
+            "title": "Model Adapter"
+          },
+          "search_adapter": {
+            "type": "string",
+            "title": "Search Adapter"
+          },
+          "storage_dir": {
+            "type": "string",
+            "title": "Storage Dir"
+          },
+          "probe": {
+            "anyOf": [
+              {
+                "additionalProperties": true,
+                "type": "object"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "title": "Probe"
+          },
+          "cost_counters": {
+            "additionalProperties": {
+              "type": "integer"
+            },
+            "type": "object",
+            "title": "Cost Counters"
+          }
+        },
+        "type": "object",
+        "required": [
+          "model_adapter",
+          "search_adapter",
+          "storage_dir",
+          "cost_counters"
+        ],
+        "title": "ConfigStatus"
+      },
+      "CreateRunBody": {
+        "properties": {
+          "question": {
+            "type": "string",
+            "minLength": 1,
+            "title": "Question"
+          },
+          "context": {
+            "type": "string",
+            "title": "Context",
+            "default": ""
+          },
+          "methodology": {
+            "type": "string",
+            "title": "Methodology"
+          },
+          "dial_overrides": {
+            "additionalProperties": true,
+            "type": "object",
+            "title": "Dial Overrides"
+          }
+        },
+        "type": "object",
+        "required": [
+          "question",
+          "methodology"
+        ],
+        "title": "CreateRunBody"
+      },
+      "HTTPValidationError": {
+        "properties": {
+          "detail": {
+            "items": {
+              "$ref": "#/components/schemas/ValidationError"
+            },
+            "type": "array",
+            "title": "Detail"
+          }
+        },
+        "type": "object",
+        "title": "HTTPValidationError"
+      },
+      "MethodologyCard": {
+        "properties": {
+          "slug": {
+            "type": "string",
+            "title": "Slug"
+          },
+          "name": {
+            "type": "string",
+            "title": "Name"
+          },
+          "description": {
+            "type": "string",
+            "title": "Description"
+          },
+          "eta_minutes": {
+            "type": "integer",
+            "title": "Eta Minutes"
+          },
+          "cost_estimate": {
+            "type": "string",
+            "title": "Cost Estimate"
+          },
+          "why_recommended": {
+            "type": "string",
+            "title": "Why Recommended"
+          },
+          "output_shape": {
+            "type": "string",
+            "title": "Output Shape"
+          },
+          "dials": {
+            "additionalProperties": true,
+            "type": "object",
+            "title": "Dials"
+          }
+        },
+        "type": "object",
+        "required": [
+          "slug",
+          "name",
+          "description",
+          "eta_minutes",
+          "cost_estimate",
+          "why_recommended",
+          "output_shape",
+          "dials"
+        ],
+        "title": "MethodologyCard"
+      },
+      "RunSummary": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "title": "Id"
+          },
+          "status": {
+            "type": "string",
+            "title": "Status"
+          },
+          "question": {
+            "type": "string",
+            "title": "Question"
+          },
+          "methodology": {
+            "type": "string",
+            "title": "Methodology"
+          },
+          "plan": {
+            "anyOf": [
+              {
+                "additionalProperties": true,
+                "type": "object"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "title": "Plan"
+          },
+          "started_at": {
+            "type": "string",
+            "title": "Started At"
+          }
+        },
+        "type": "object",
+        "required": [
+          "id",
+          "status",
+          "question",
+          "methodology",
+          "started_at"
+        ],
+        "title": "RunSummary"
+      },
+      "ValidationError": {
+        "properties": {
+          "loc": {
+            "items": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "integer"
+                }
+              ]
+            },
+            "type": "array",
+            "title": "Location"
+          },
+          "msg": {
+            "type": "string",
+            "title": "Message"
+          },
+          "type": {
+            "type": "string",
+            "title": "Error Type"
+          }
+        },
+        "type": "object",
+        "required": [
+          "loc",
+          "msg",
+          "type"
+        ],
+        "title": "ValidationError"
+      }
+    }
+  }
+}

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@researchx/frontend",
-  "version": "0.1.0",
+  "version": "0.2.5",
   "private": true,
   "packageManager": "pnpm@12.6.0",
   "scripts": {
@@ -30,8 +30,11 @@
     "@vitejs/plugin-react": "4.7.0",
     "eslint": "^9.39.5",
     "eslint-config-next": "15.5.6",
+    "eventsource": "^5.1.2",
     "globals": "^17.0.0",
     "jsdom": "26.1.0",
+    "openapi-fetch": "^0.13.8",
+    "openapi-typescript": "^7.13.0",
     "tailwindcss": "4.1.18",
     "typescript": "^5.9.3",
     "typescript-eslint": "^8.70.1",

frontend/pnpm-lock.yaml

@@ -168,7 +168,7 @@ importers:
     dependencies:
       next:
         specifier: 15.5.6
-        version: 15.5.6(@babel/core@7.29.7(supports-color@7.2.0))(react-dom@19.2.8(react@19.2.8))(react@19.2.8)
+        version: 15.5.6(@babel/core@7.29.7(supports-color@10.2.2))(react-dom@19.2.8(react@19.2.8))(react@19.2.8)
       react:
         specifier: 19.2.8
         version: 19.2.8
@@ -178,7 +178,7 @@ importers:
     devDependencies:
       '@eslint/eslintrc':
         specifier: ^3.3.7
-        version: 3.3.7(supports-color@7.2.0)
+        version: 3.3.7(supports-color@10.2.2)
       '@tailwindcss/postcss':
         specifier: 4.1.18
         version: 4.1.18
@@ -205,19 +205,28 @@ importers:
         version: 19.2.3(@types/react@19.2.5)
       '@vitejs/plugin-react':
         specifier: 4.7.0
-        version: 4.7.0(supports-color@7.2.0)(vite@7.3.6(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2))
+        version: 4.7.0(supports-color@10.2.2)(vite@7.3.6(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2))
       eslint:
         specifier: ^9.39.5
-        version: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+        version: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       eslint-config-next:
         specifier: 15.5.6
-        version: 15.5.6(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
+        version: 15.5.6(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
+      eventsource:
+        specifier: ^5.1.2
+        version: 5.1.2
       globals:
         specifier: ^17.0.0
         version: 17.12.0
       jsdom:
         specifier: 26.1.0
-        version: 26.1.0(supports-color@7.2.0)
+        version: 26.1.0(supports-color@10.2.2)
+      openapi-fetch:
+        specifier: ^0.13.8
+        version: 0.13.8
+      openapi-typescript:
+        specifier: ^7.13.0
+        version: 7.13.0(typescript@5.9.3)
       tailwindcss:
         specifier: 4.1.18
         version: 4.1.18
@@ -226,10 +235,10 @@ importers:
         version: 5.9.3
       typescript-eslint:
         specifier: ^8.70.1
-        version: 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
+        version: 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
       vitest:
         specifier: 3.2.7
-        version: 3.2.7(@types/node@24.3.1)(jiti@2.7.0)(jsdom@26.1.0(supports-color@7.2.0))(lightningcss@1.30.2)(supports-color@7.2.0)
+        version: 3.2.7(@types/node@24.3.1)(jiti@2.7.0)(jsdom@26.1.0(supports-color@10.2.2))(lightningcss@1.30.2)(supports-color@10.2.2)
 
 packages:
 
@@ -841,6 +850,16 @@ packages:
     resolution: {integrity: sha512-nn5ozdjYQpUCZlWGuxcJY/KpxkWQs4DcbMCmKojjyrYDEAGy4Ce19NN4v5MduafTwJlbKc99UA8YhSVqq9yPZA==}
     engines: {node: '>=12.4.0'}
 
+  '@redocly/ajv@8.11.2':
+    resolution: {integrity: sha512-io1JpnwtIcvojV7QKDUSIuMN/ikdOUd1ReEnUnMKGfDVridQZ31J0MmIuqwuRjWDZfmvr+Q0MqCcfHM2gTivOg==}
+
+  '@redocly/config@0.22.0':
+    resolution: {integrity: sha512-gAy93Ddo01Z3bHuVdPWfCwzgfaYgMdaZPcfL7JZ7hWJoK9V0lXDbigTWkhiPFAaLWzbOJ+kbUQG1+XwIm0KRGQ==}
+
+  '@redocly/openapi-core@1.34.20':
+    resolution: {integrity: sha512-ypeBZ/6BKXR9+7/TtbKhbl4UgD7raHhPS12oknlKno2A8+lnFkxIwiE/Aklu6L2cd/ioH+fCWuMxi9/p3EyAPw==}
+    engines: {node: '>=18.17.0', npm: '>=9.5.0'}
+
   '@rolldown/pluginutils@1.0.0-beta.27':
     resolution: {integrity: sha512-+d0F4MKMCbeVUJwG96uQ4SgAznZNSq93I3V+9NHA4OpvqG8mRCpGdKmK8l/dl02h2CCDHwW2FqilnTyDcAnqjA==}
 
@@ -1390,6 +1409,10 @@ packages:
   ajv@6.15.0:
     resolution: {integrity: sha512-fgFx7Hfoq60ytK2c7DhnF8jIvzYgOMxfugjLOSMHjLIPgenqa7S7oaagATUq99mV6IYvN2tRmC0wnTYX6iPbMw==}
 
+  ansi-colors@4.1.3:
+    resolution: {integrity: sha512-/6w/C21Pm1A7aZitlI5Ni/2J6FFQN8i1Cvz3kHABAAbw93v/NlvKdVOqz7CCWz/3iv/JplRSEEZ83XION15ovw==}
+    engines: {node: '>=6'}
+
   ansi-regex@5.0.1:
     resolution: {integrity: sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==}
     engines: {node: '>=8'}
@@ -1482,6 +1505,9 @@ packages:
   brace-expansion@1.1.21:
     resolution: {integrity: sha512-9zeA+KLZNNzglF2TPKRQEDyx6Yby7daAkuy8MiPzpXPsYDWi/DRM8jmwUDxokQjYqBpv5DgPiwD4h4ZZSy1Ujw==}
 
+  brace-expansion@2.1.7:
+    resolution: {integrity: sha512-uZbew1NqdmPDTMJ8ah1y+b+9QEJrfkXFk3RcTQw3X0jW/xRUvFKsg1CfQdSYGdTbXZWExtU3J3ccxtnfw1Fi0g==}
+
   brace-expansion@5.0.12:
     resolution: {integrity: sha512-YovQ3rzhaLMIrDjNDMkNS01tea93qhEhG5xy8f6+R0l+dw3Ki+5sCoIoI942iuLZTHWogWktgwVDhU09iNEimQ==}
     engines: {node: 20 || >=22}
@@ -1526,6 +1552,9 @@ packages:
     resolution: {integrity: sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==}
     engines: {node: '>=10'}
 
+  change-case@5.4.4:
+    resolution: {integrity: sha512-HRQyTk2/YPEkt9TnUPbOpr64Uw3KOicFWPVBb+xiHvd6eBx/qPr9xqfBFDT8P2vWsvvz4jbEkfDe71W3VyNu2w==}
+
   check-error@2.1.3:
     resolution: {integrity: sha512-PAJdDJusoxnwm1VwW07VWwUN1sl7smmC3OKggvndJFadxxDRyFJBX/ggnu/KE4kQAB7a3Dp8f/YXC1FlUprWmA==}
     engines: {node: '>= 16'}
@@ -1540,6 +1569,9 @@ packages:
   color-name@1.1.4:
     resolution: {integrity: sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==}
 
+  colorette@1.4.0:
+    resolution: {integrity: sha512-Y2oEozpomLn7Q3HFP7dpww7AtMJplbM9lGZP6RDfHqmbeRjiwRg4n6VM6j4KLmRke85uWEI7JqF17f3pqdRA0g==}
+
   concat-map@0.0.1:
     resolution: {integrity: sha512-/Srv4dswyQNBfohGpz9o6Yb3Gz3SrUDqBH5rTuhGR7ahtlbYKnVxw2bCFMRljaA7EXHaXZ8wsHdodFvbkhKmqg==}
 
@@ -1826,6 +1858,14 @@ packages:
     resolution: {integrity: sha512-kVscqXk4OCp68SZ0dkgEKVi6/8ij300KBWTJq32P/dYeWTSwK41WyTxalN1eRmA5Z9UU/LX9D7FWSmV9SAYx6g==}
     engines: {node: '>=0.10.0'}
 
+  eventsource-parser@4.1.1:
+    resolution: {integrity: sha512-zaWNqeSLeyzEAAt2Q6aDBRDRk/VnPmsKqvToyGvv6aahvLv71A4Jw7jG93Hckf11zXurbqgsffvpSgKPoeU1Qw==}
+    engines: {node: '>=22.12'}
+
+  eventsource@5.1.2:
+    resolution: {integrity: sha512-VJnwqqp+fOT3WDkjnUy49Zuyh48+kH0JdJApZkslrRQyx35zIZJeJYJl0+a+LrTzh5TFv6MdmXnBDv71UXFyWQ==}
+    engines: {node: '>=22.12.0'}
+
   expect-type@1.4.0:
     resolution: {integrity: sha512-KfYbmpRm0VbLjEvVa9yGwCi9GI34xvi7A/HXYWQO65CSD2u3MczUJSuwXKFIxlGsgBQizV9q5J9NHj4VG0n+pA==}
     engines: {node: '>=12.0.0'}
@@ -2006,6 +2046,10 @@ packages:
     resolution: {integrity: sha512-EdDDZu4A2OyIK7Lr/2zG+w5jmbuk1DVBnEwREQvBzspBJkCEbRa8GxU1lghYcaGJCnRWibjDXlq779X1/y5xwg==}
     engines: {node: '>=8'}
 
+  index-to-position@1.2.0:
+    resolution: {integrity: sha512-Yg7+ztRkqslMAS2iFaU+Oa4KTSidr63OsFGlOrJoW981kIYO3CGCS3wA95P1mUi/IVSJkn0D479KTJpVpvFNuw==}
+    engines: {node: '>=18'}
+
   internal-slot@1.1.0:
     resolution: {integrity: sha512-4gd7VpWNQNB4UKKCFFVcp1AVv+FMOgs9NKzjHKusc8jTMhd5eL1NqQqOpE0KzMds804/yHlglp3uxgluOqAPLw==}
     engines: {node: '>= 0.4'}
@@ -2134,6 +2178,10 @@ packages:
     resolution: {integrity: sha512-AC/7JofJvZGrrneWNaEnJeOLUx+JlGt7tNa0wZiRPT4MY1wmfKjt2+6O2p2uz2+skll8OZZmJMNqeke7kKbNgQ==}
     hasBin: true
 
+  js-levenshtein@1.1.6:
+    resolution: {integrity: sha512-X2BB11YZtrRqY4EnQcLX5Rh373zbK4alC1FW7D7MBhL2gtcC17cTnr6DmfHZeS0s2rTHjUTMMHfG7gO8SSdw+g==}
+    engines: {node: '>=0.10.0'}
+
   js-tokens@4.0.0:
     resolution: {integrity: sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ==}
 
@@ -2164,6 +2212,9 @@ packages:
   json-schema-traverse@0.4.1:
     resolution: {integrity: sha512-xbbCH5dCYU5T8LcEhhuh7HJ88HXuW3qsI3Y0zOZFKfZEHcpWiHU/Jxzk629Brsab/mMiHQti9wMP+845RPe3Vg==}
 
+  json-schema-traverse@1.0.0:
+    resolution: {integrity: sha512-NM8/P9n3XjXhIZn1lLhkFaACTOURQXjWhV4BA/RnOv8xvgqtqpAX9IO4mRQxSx1Rlo4tqzeqb0sOlruaOy3dug==}
+
   json-stable-stringify-without-jsonify@1.0.1:
     resolution: {integrity: sha512-Bdboy+l7tA3OGW6FjyFHWkP5LuByj1Tk33Ljyq0axyzdk9//JSi2u3fP1QSmd1KNwq6VOKYGlAu87CisVir6Pw==}
 
@@ -2318,6 +2369,10 @@ packages:
   minimatch@3.1.5:
     resolution: {integrity: sha512-VgjWUsnnT6n+NUk6eZq77zeFdpW2LWDzP6zFGrCbHXiYNul5Dzqk2HHQ5uFH2DNW5Xbp8+jVzaeNt94ssEEl4w==}
 
+  minimatch@5.1.9:
+    resolution: {integrity: sha512-7o1wEA2RyMP7Iu7GNba9vc0RWWGACJOCZBJX2GJWip0ikV+wcOsgVuY9uE8CPiyQhkGFSlhuSkZPavN7u1c2Fw==}
+    engines: {node: '>=10'}
+
   minimist@1.2.8:
     resolution: {integrity: sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==}
 
@@ -2402,6 +2457,18 @@ packages:
     resolution: {integrity: sha512-gXah6aZrcUxjWg2zR2MwouP2eHlCBzdV4pygudehaKXSGW4v2AsRQUK+lwwXhii6KFZcunEnmSUoYp5CXibxtA==}
     engines: {node: '>= 0.4'}
 
+  openapi-fetch@0.13.8:
+    resolution: {integrity: sha512-yJ4QKRyNxE44baQ9mY5+r/kAzZ8yXMemtNAOFwOzRXJscdjSxxzWSNlyBAr+o5JjkUw9Lc3W7OIoca0cY3PYnQ==}
+
+  openapi-typescript-helpers@0.0.15:
+    resolution: {integrity: sha512-opyTPaunsklCBpTK8JGef6mfPhLSnyy5a0IN9vKtx3+4aExf+KxEqYwIy3hqkedXIB97u357uLMJsOnm3GVjsw==}
+
+  openapi-typescript@7.13.0:
+    resolution: {integrity: sha512-EFP392gcqXS7ntPvbhBzbF8TyBA+baIYEm791Hy5YkjDYKTnk/Tn5OQeKm5BIZvJihpp8Zzr4hzx0Irde1LNGQ==}
+    hasBin: true
+    peerDependencies:
+      typescript: ^5.x
+
   optionator@0.9.4:
     resolution: {integrity: sha512-6IpQ7mKUxRcZNLIObR0hz7lxsapSSIYNZJwXPGeF0mTVqGKFIXj1DQcMoT22S3ROcLyY/rz0PWaWZ9ayWmad9g==}
     engines: {node: '>= 0.8.0'}
@@ -2422,6 +2489,10 @@ packages:
     resolution: {integrity: sha512-GQ2EWRpQV8/o+Aw8YqtfZZPfNRWZYkbidE9k5rpl/hC3vtHHBfGm2Ifi6qWV+coDGkrUKZAxE3Lot5kcsRlh+g==}
     engines: {node: '>=6'}
 
+  parse-json@8.3.0:
+    resolution: {integrity: sha512-ybiGyvspI+fAoRQbIPRddCcSTV9/LsJbf0e/S85VLowVGzRmokfneg2kwVW/KU5rOXrPSbF1qAKPMgNTqqROQQ==}
+    engines: {node: '>=18'}
+
   parse5@7.3.0:
     resolution: {integrity: sha512-IInvU7fabl34qmi9gY8XOVxhYyMyuH2xUNpb2q8/Y+7552KlejkRvqvD19nMoUW/uQGGbqNpA6Tufu5FL5BZgw==}
 
@@ -2454,6 +2525,10 @@ packages:
     resolution: {integrity: sha512-qcJu88Q2IWqJsDD529JKMdwGm/dvInW4HvQnRwiH9JtihJvzGOscDtHE3x1pBKeUOTysQ8kVmLnJ2kJu7yhcGA==}
     engines: {node: '>=12'}
 
+  pluralize@8.0.0:
+    resolution: {integrity: sha512-Nc3IT5yHzflTfbjgqWcCPpo7DaKy4FnpB0l/zCAW0Tc7jxAiuqSxHasntB3D7887LSrA93kDJ9IXovxJYxyLCA==}
+    engines: {node: '>=4'}
+
   possible-typed-array-names@1.1.0:
     resolution: {integrity: sha512-/+5VFTchJDoVj3bhoqi6UeymcD00DAwb1nJwamzPvHEszJ4FpF6SNNbUbOS8yI56qHzdV8eK0qEfOSiodkTdxg==}
     engines: {node: '>= 0.4'}
@@ -2515,6 +2590,10 @@ packages:
     resolution: {integrity: sha512-dYqgNSZbDwkaJ2ceRd9ojCGjBq+mOm9LmtXnAnEGyHhN/5R7iDW2TRw3h+o/jCFxus3P2LfWIIiwowAjANm7IA==}
     engines: {node: '>= 0.4'}
 
+  require-from-string@2.0.2:
+    resolution: {integrity: sha512-Xf0nWe6RseziFMu+Ap9biiUbmplq6S9/p+7w7YXP/JBHhrUDDUhwa+vANyubuqfZWTveU//DYVGsDG7RKL/vEw==}
+    engines: {node: '>=0.10.0'}
+
   resolve-from@4.0.0:
     resolution: {integrity: sha512-pb/MYmXstAkysRFx8piNI1tGFNQIFA3vkE3Gq4EuA1dF6gHp/+vgZqsCGJapvy8N3Q+4o7FwvquPJcnZ7RYy4g==}
     engines: {node: '>=4'}
@@ -2684,6 +2763,10 @@ packages:
       babel-plugin-macros:
         optional: true
 
+  supports-color@10.2.2:
+    resolution: {integrity: sha512-SS+jx45GF1QjgEXQx4NJZV9ImqmO2NPz5FNsIHrsDjh2YsHnawpan7SNQ1o8NuhrbHZy9AZhIoCUiCeaW/C80g==}
+    engines: {node: '>=18'}
+
   supports-color@7.2.0:
     resolution: {integrity: sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw==}
     engines: {node: '>=8'}
@@ -2759,6 +2842,10 @@ packages:
     resolution: {integrity: sha512-XleUoc9uwGXqjWwXaUTZAmzMcFZ5858QA2vvx1Ur5xIcixXIP+8LnFDgRplU30us6teqdlskFfu+ae4K79Ooew==}
     engines: {node: '>= 0.8.0'}
 
+  type-fest@4.41.0:
+    resolution: {integrity: sha512-TeTSQ6H5YHvpqVwBRcnLDCBnDOHWYu7IvGbHT6N8AOymcr9PJGjc1GTtiWZTYg0NCgYwvnYWEkVChQAr9bjfwA==}
+    engines: {node: '>=16'}
+
   typed-array-buffer@1.0.3:
     resolution: {integrity: sha512-nAYYwfY3qnzX30IkA6AQZjVbtK6duGontcQm1WSG1MD94YLqK0515GNApXkoxKOWMusVssAHWLh9SeaoefYFGw==}
     engines: {node: '>= 0.4'}
@@ -2803,6 +2890,9 @@ packages:
     peerDependencies:
       browserslist: '>= 4.21.0'
 
+  uri-js-replace@1.0.1:
+    resolution: {integrity: sha512-W+C9NWNLFOoBI2QWDp4UT9pv65r2w5Cx+3sTYFvtMdDBxkKt1syCqsUdSFAChbEe1uK5TfS04wt/nGwmaeIQ0g==}
+
   uri-js@4.4.1:
     resolution: {integrity: sha512-7rKUyy33Q1yc98pQ1DAmLtwX109F7TIfWlW1Ydo8Wl1ii1SeHieeh0HHfPeL2fMXK6z0s8ecKs9frCuLJvndBg==}
 
@@ -2952,6 +3042,13 @@ packages:
   yallist@3.1.1:
     resolution: {integrity: sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g==}
 
+  yaml-ast-parser@0.0.43:
+    resolution: {integrity: sha512-2PTINUwsRqSd+s8XxKaJWQlUuEMHJQyEuh2edBbW8KNJz0SJPwUSD2zRWqezFEdN7IzAgeuYHFUCF7o8zRdZ0A==}
+
+  yargs-parser@21.1.1:
+    resolution: {integrity: sha512-tVpsJW7DdjecAiFpbIB1e3qxIQsE6NoPc5/eTdrbbIC4h0LVsWhnoa3g+m2HclBIujHzsxZ4VJVA+GUuc2/LBw==}
+    engines: {node: '>=12'}
+
   yocto-queue@0.1.0:
     resolution: {integrity: sha512-rVksvsnNCdJ/ohGc6xgPwyN8eheCxsiLM8mxuE/t/mOVqJewPuO1miLpTHQiRgTKCLexL4MeAFVagts7HmNZ2Q==}
     engines: {node: '>=10'}
@@ -2978,20 +3075,20 @@ snapshots:
 
   '@babel/compat-data@7.29.7': {}
 
-  '@babel/core@7.29.7(supports-color@7.2.0)':
+  '@babel/core@7.29.7(supports-color@10.2.2)':
     dependencies:
       '@babel/code-frame': 7.29.7
       '@babel/generator': 7.29.8
       '@babel/helper-compilation-targets': 7.29.7
-      '@babel/helper-module-transforms': 7.29.7(@babel/core@7.29.7(supports-color@7.2.0))(supports-color@7.2.0)
+      '@babel/helper-module-transforms': 7.29.7(@babel/core@7.29.7(supports-color@10.2.2))(supports-color@10.2.2)
       '@babel/helpers': 7.29.7
       '@babel/parser': 7.29.9
       '@babel/template': 7.29.7
-      '@babel/traverse': 7.29.8(supports-color@7.2.0)
+      '@babel/traverse': 7.29.8(supports-color@10.2.2)
       '@babel/types': 7.29.8
       '@jridgewell/remapping': 2.3.5
       convert-source-map: 2.0.0
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
       gensync: 1.0.0-beta.2
       json5: 2.2.3
       semver: 6.3.1
@@ -3016,19 +3113,19 @@ snapshots:
 
   '@babel/helper-globals@7.29.7': {}
 
-  '@babel/helper-module-imports@7.29.7(supports-color@7.2.0)':
+  '@babel/helper-module-imports@7.29.7(supports-color@10.2.2)':
     dependencies:
-      '@babel/traverse': 7.29.8(supports-color@7.2.0)
+      '@babel/traverse': 7.29.8(supports-color@10.2.2)
       '@babel/types': 7.29.8
     transitivePeerDependencies:
       - supports-color
 
-  '@babel/helper-module-transforms@7.29.7(@babel/core@7.29.7(supports-color@7.2.0))(supports-color@7.2.0)':
+  '@babel/helper-module-transforms@7.29.7(@babel/core@7.29.7(supports-color@10.2.2))(supports-color@10.2.2)':
     dependencies:
-      '@babel/core': 7.29.7(supports-color@7.2.0)
-      '@babel/helper-module-imports': 7.29.7(supports-color@7.2.0)
+      '@babel/core': 7.29.7(supports-color@10.2.2)
+      '@babel/helper-module-imports': 7.29.7(supports-color@10.2.2)
       '@babel/helper-validator-identifier': 7.29.7
-      '@babel/traverse': 7.29.8(supports-color@7.2.0)
+      '@babel/traverse': 7.29.8(supports-color@10.2.2)
     transitivePeerDependencies:
       - supports-color
 
@@ -3049,14 +3146,14 @@ snapshots:
     dependencies:
       '@babel/types': 7.29.8
 
-  '@babel/plugin-transform-react-jsx-self@7.29.7(@babel/core@7.29.7(supports-color@7.2.0))':
+  '@babel/plugin-transform-react-jsx-self@7.29.7(@babel/core@7.29.7(supports-color@10.2.2))':
     dependencies:
-      '@babel/core': 7.29.7(supports-color@7.2.0)
+      '@babel/core': 7.29.7(supports-color@10.2.2)
       '@babel/helper-plugin-utils': 7.29.7
 
-  '@babel/plugin-transform-react-jsx-source@7.29.7(@babel/core@7.29.7(supports-color@7.2.0))':
+  '@babel/plugin-transform-react-jsx-source@7.29.7(@babel/core@7.29.7(supports-color@10.2.2))':
     dependencies:
-      '@babel/core': 7.29.7(supports-color@7.2.0)
+      '@babel/core': 7.29.7(supports-color@10.2.2)
       '@babel/helper-plugin-utils': 7.29.7
 
   '@babel/runtime@7.29.7': {}
@@ -3067,7 +3164,7 @@ snapshots:
       '@babel/parser': 7.29.9
       '@babel/types': 7.29.8
 
-  '@babel/traverse@7.29.8(supports-color@7.2.0)':
+  '@babel/traverse@7.29.8(supports-color@10.2.2)':
     dependencies:
       '@babel/code-frame': 7.29.7
       '@babel/generator': 7.29.8
@@ -3075,7 +3172,7 @@ snapshots:
       '@babel/parser': 7.29.9
       '@babel/template': 7.29.7
       '@babel/types': 7.29.8
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
     transitivePeerDependencies:
       - supports-color
 
@@ -3203,17 +3300,17 @@ snapshots:
   '@esbuild/win32-x64@0.28.2':
     optional: true
 
-  '@eslint-community/eslint-utils@4.10.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))':
+  '@eslint-community/eslint-utils@4.10.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))':
     dependencies:
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       eslint-visitor-keys: 3.4.3
 
   '@eslint-community/regexpp@4.12.2': {}
 
-  '@eslint/config-array@0.21.2(supports-color@7.2.0)':
+  '@eslint/config-array@0.21.2(supports-color@10.2.2)':
     dependencies:
       '@eslint/object-schema': 2.1.7
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
       minimatch: 3.1.5
     transitivePeerDependencies:
       - supports-color
@@ -3226,10 +3323,10 @@ snapshots:
     dependencies:
       '@types/json-schema': 7.0.15
 
-  '@eslint/eslintrc@3.3.7(supports-color@7.2.0)':
+  '@eslint/eslintrc@3.3.7(supports-color@10.2.2)':
     dependencies:
       ajv: 6.15.0
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
       espree: 10.4.0
       globals: 14.0.0
       ignore: 5.3.2
@@ -3435,6 +3532,29 @@ snapshots:
 
   '@nolyfill/is-core-module@1.0.39': {}
 
+  '@redocly/ajv@8.11.2':
+    dependencies:
+      fast-deep-equal: 3.1.3
+      json-schema-traverse: 1.0.0
+      require-from-string: 2.0.2
+      uri-js-replace: 1.0.1
+
+  '@redocly/config@0.22.0': {}
+
+  '@redocly/openapi-core@1.34.20(supports-color@10.2.2)':
+    dependencies:
+      '@redocly/ajv': 8.11.2
+      '@redocly/config': 0.22.0
+      colorette: 1.4.0
+      https-proxy-agent: 7.0.6(supports-color@10.2.2)
+      js-levenshtein: 1.1.6
+      js-yaml: 4.3.2
+      minimatch: 5.1.9
+      pluralize: 8.0.0
+      yaml-ast-parser: 0.0.43
+    transitivePeerDependencies:
+      - supports-color
+
   '@rolldown/pluginutils@1.0.0-beta.27': {}
 
   '@rollup/rollup-android-arm-eabi@4.63.5':
@@ -3677,15 +3797,15 @@ snapshots:
     dependencies:
       csstype: 3.2.3
 
-  '@typescript-eslint/eslint-plugin@8.70.1(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3))(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)':
+  '@typescript-eslint/eslint-plugin@8.70.1(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3))(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)':
     dependencies:
       '@eslint-community/regexpp': 4.12.2
-      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
+      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
       '@typescript-eslint/scope-manager': 8.70.1
-      '@typescript-eslint/type-utils': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
-      '@typescript-eslint/utils': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
+      '@typescript-eslint/type-utils': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
+      '@typescript-eslint/utils': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
       '@typescript-eslint/visitor-keys': 8.70.1
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       ignore: 7.0.10
       natural-compare: 1.4.0
       ts-api-utils: 2.5.0(typescript@5.9.3)
@@ -3693,23 +3813,23 @@ snapshots:
     transitivePeerDependencies:
       - supports-color
 
-  '@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)':
+  '@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)':
     dependencies:
       '@typescript-eslint/scope-manager': 8.70.1
       '@typescript-eslint/types': 8.70.1
-      '@typescript-eslint/typescript-estree': 8.70.1(supports-color@7.2.0)(typescript@5.9.3)
+      '@typescript-eslint/typescript-estree': 8.70.1(supports-color@10.2.2)(typescript@5.9.3)
       '@typescript-eslint/visitor-keys': 8.70.1
-      debug: 4.4.3(supports-color@7.2.0)
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       typescript: 5.9.3
     transitivePeerDependencies:
       - supports-color
 
-  '@typescript-eslint/project-service@8.70.1(supports-color@7.2.0)(typescript@5.9.3)':
+  '@typescript-eslint/project-service@8.70.1(supports-color@10.2.2)(typescript@5.9.3)':
     dependencies:
       '@typescript-eslint/tsconfig-utils': 8.70.1(typescript@5.9.3)
       '@typescript-eslint/types': 8.70.1
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
       typescript: 5.9.3
     transitivePeerDependencies:
       - supports-color
@@ -3723,13 +3843,13 @@ snapshots:
     dependencies:
       typescript: 5.9.3
 
-  '@typescript-eslint/type-utils@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)':
+  '@typescript-eslint/type-utils@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)':
     dependencies:
       '@typescript-eslint/types': 8.70.1
-      '@typescript-eslint/typescript-estree': 8.70.1(supports-color@7.2.0)(typescript@5.9.3)
-      '@typescript-eslint/utils': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
-      debug: 4.4.3(supports-color@7.2.0)
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      '@typescript-eslint/typescript-estree': 8.70.1(supports-color@10.2.2)(typescript@5.9.3)
+      '@typescript-eslint/utils': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
+      debug: 4.4.3(supports-color@10.2.2)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       ts-api-utils: 2.5.0(typescript@5.9.3)
       typescript: 5.9.3
     transitivePeerDependencies:
@@ -3737,13 +3857,13 @@ snapshots:
 
   '@typescript-eslint/types@8.70.1': {}
 
-  '@typescript-eslint/typescript-estree@8.70.1(supports-color@7.2.0)(typescript@5.9.3)':
+  '@typescript-eslint/typescript-estree@8.70.1(supports-color@10.2.2)(typescript@5.9.3)':
     dependencies:
-      '@typescript-eslint/project-service': 8.70.1(supports-color@7.2.0)(typescript@5.9.3)
+      '@typescript-eslint/project-service': 8.70.1(supports-color@10.2.2)(typescript@5.9.3)
       '@typescript-eslint/tsconfig-utils': 8.70.1(typescript@5.9.3)
       '@typescript-eslint/types': 8.70.1
       '@typescript-eslint/visitor-keys': 8.70.1
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
       minimatch: 10.2.6
       semver: 7.8.5
       tinyglobby: 0.2.17
@@ -3752,13 +3872,13 @@ snapshots:
     transitivePeerDependencies:
       - supports-color
 
-  '@typescript-eslint/utils@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)':
+  '@typescript-eslint/utils@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)':
     dependencies:
-      '@eslint-community/eslint-utils': 4.10.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))
+      '@eslint-community/eslint-utils': 4.10.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))
       '@typescript-eslint/scope-manager': 8.70.1
       '@typescript-eslint/types': 8.70.1
-      '@typescript-eslint/typescript-estree': 8.70.1(supports-color@7.2.0)(typescript@5.9.3)
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      '@typescript-eslint/typescript-estree': 8.70.1(supports-color@10.2.2)(typescript@5.9.3)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       typescript: 5.9.3
     transitivePeerDependencies:
       - supports-color
@@ -3838,11 +3958,11 @@ snapshots:
   '@unrs/resolver-binding-win32-x64-msvc@1.12.2':
     optional: true
 
-  '@vitejs/plugin-react@4.7.0(supports-color@7.2.0)(vite@7.3.6(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2))':
+  '@vitejs/plugin-react@4.7.0(supports-color@10.2.2)(vite@7.3.6(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2))':
     dependencies:
-      '@babel/core': 7.29.7(supports-color@7.2.0)
-      '@babel/plugin-transform-react-jsx-self': 7.29.7(@babel/core@7.29.7(supports-color@7.2.0))
-      '@babel/plugin-transform-react-jsx-source': 7.29.7(@babel/core@7.29.7(supports-color@7.2.0))
+      '@babel/core': 7.29.7(supports-color@10.2.2)
+      '@babel/plugin-transform-react-jsx-self': 7.29.7(@babel/core@7.29.7(supports-color@10.2.2))
+      '@babel/plugin-transform-react-jsx-source': 7.29.7(@babel/core@7.29.7(supports-color@10.2.2))
       '@rolldown/pluginutils': 1.0.0-beta.27
       '@types/babel__core': 7.20.5
       react-refresh: 0.17.0
@@ -3907,6 +4027,8 @@ snapshots:
       json-schema-traverse: 0.4.1
       uri-js: 4.4.1
 
+  ansi-colors@4.1.3: {}
+
   ansi-regex@5.0.1: {}
 
   ansi-styles@4.3.0:
@@ -4015,6 +4137,10 @@ snapshots:
       balanced-match: 1.0.2
       concat-map: 0.0.1
 
+  brace-expansion@2.1.7:
+    dependencies:
+      balanced-match: 1.0.2
+
   brace-expansion@5.0.12:
     dependencies:
       balanced-match: 4.0.4
@@ -4067,6 +4193,8 @@ snapshots:
       ansi-styles: 4.3.0
       supports-color: 7.2.0
 
+  change-case@5.4.4: {}
+
   check-error@2.1.3: {}
 
   client-only@0.0.1: {}
@@ -4077,6 +4205,8 @@ snapshots:
 
   color-name@1.1.4: {}
 
+  colorette@1.4.0: {}
+
   concat-map@0.0.1: {}
 
   convert-source-map@2.0.0: {}
@@ -4121,17 +4251,17 @@ snapshots:
       es-errors: 1.3.0
       is-data-view: 1.0.2
 
-  debug@3.2.7(supports-color@7.2.0):
+  debug@3.2.7(supports-color@10.2.2):
     dependencies:
       ms: 2.1.3
     optionalDependencies:
-      supports-color: 7.2.0
+      supports-color: 10.2.2
 
-  debug@4.4.3(supports-color@7.2.0):
+  debug@4.4.3(supports-color@10.2.2):
     dependencies:
       ms: 2.1.3
     optionalDependencies:
-      supports-color: 7.2.0
+      supports-color: 10.2.2
 
   decimal.js@10.6.0: {}
 
@@ -4326,19 +4456,19 @@ snapshots:
 
   escape-string-regexp@4.0.0: {}
 
-  eslint-config-next@15.5.6(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3):
+  eslint-config-next@15.5.6(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3):
     dependencies:
       '@next/eslint-plugin-next': 15.5.6
       '@rushstack/eslint-patch': 1.16.1
-      '@typescript-eslint/eslint-plugin': 8.70.1(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3))(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
-      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
-      eslint-import-resolver-node: 0.3.10(supports-color@7.2.0)
-      eslint-import-resolver-typescript: 3.10.1(eslint-plugin-import@2.32.0)(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)
-      eslint-plugin-import: 2.32.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)
-      eslint-plugin-jsx-a11y: 6.10.2(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))
-      eslint-plugin-react: 7.37.5(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))
-      eslint-plugin-react-hooks: 5.2.0(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))
+      '@typescript-eslint/eslint-plugin': 8.70.1(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3))(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
+      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
+      eslint-import-resolver-node: 0.3.10(supports-color@10.2.2)
+      eslint-import-resolver-typescript: 3.10.1(eslint-plugin-import@2.32.0)(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)
+      eslint-plugin-import: 2.32.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)
+      eslint-plugin-jsx-a11y: 6.10.2(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))
+      eslint-plugin-react: 7.37.5(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))
+      eslint-plugin-react-hooks: 5.2.0(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))
     optionalDependencies:
       typescript: 5.9.3
     transitivePeerDependencies:
@@ -4346,52 +4476,52 @@ snapshots:
       - eslint-plugin-import-x
       - supports-color
 
-  eslint-import-resolver-node@0.3.10(supports-color@7.2.0):
+  eslint-import-resolver-node@0.3.10(supports-color@10.2.2):
     dependencies:
-      debug: 3.2.7(supports-color@7.2.0)
+      debug: 3.2.7(supports-color@10.2.2)
       is-core-module: 2.17.0
       resolve: 2.0.0-next.7
     transitivePeerDependencies:
       - supports-color
 
-  eslint-import-resolver-typescript@3.10.1(eslint-plugin-import@2.32.0)(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0):
+  eslint-import-resolver-typescript@3.10.1(eslint-plugin-import@2.32.0)(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2):
     dependencies:
       '@nolyfill/is-core-module': 1.0.39
-      debug: 4.4.3(supports-color@7.2.0)
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       get-tsconfig: 4.14.3
       is-bun-module: 2.0.0
       stable-hash: 0.0.5
       tinyglobby: 0.2.17
       unrs-resolver: 1.12.2
     optionalDependencies:
-      eslint-plugin-import: 2.32.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)
+      eslint-plugin-import: 2.32.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)
     transitivePeerDependencies:
       - supports-color
 
-  eslint-module-utils@2.14.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3))(eslint-import-resolver-node@0.3.10(supports-color@7.2.0))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0):
+  eslint-module-utils@2.14.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3))(eslint-import-resolver-node@0.3.10(supports-color@10.2.2))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2):
     dependencies:
-      debug: 3.2.7(supports-color@7.2.0)
+      debug: 3.2.7(supports-color@10.2.2)
     optionalDependencies:
-      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
-      eslint-import-resolver-node: 0.3.10(supports-color@7.2.0)
-      eslint-import-resolver-typescript: 3.10.1(eslint-plugin-import@2.32.0)(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)
+      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
+      eslint-import-resolver-node: 0.3.10(supports-color@10.2.2)
+      eslint-import-resolver-typescript: 3.10.1(eslint-plugin-import@2.32.0)(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)
     transitivePeerDependencies:
       - supports-color
 
-  eslint-plugin-import@2.32.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0):
+  eslint-plugin-import@2.32.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2):
     dependencies:
       '@rtsao/scc': 1.1.0
       array-includes: 3.2.0
       array.prototype.findlastindex: 1.2.6
       array.prototype.flat: 1.3.3
       array.prototype.flatmap: 1.3.3
-      debug: 3.2.7(supports-color@7.2.0)
+      debug: 3.2.7(supports-color@10.2.2)
       doctrine: 2.1.0
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
-      eslint-import-resolver-node: 0.3.10(supports-color@7.2.0)
-      eslint-module-utils: 2.14.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3))(eslint-import-resolver-node@0.3.10(supports-color@7.2.0))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
+      eslint-import-resolver-node: 0.3.10(supports-color@10.2.2)
+      eslint-module-utils: 2.14.0(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3))(eslint-import-resolver-node@0.3.10(supports-color@10.2.2))(eslint-import-resolver-typescript@3.10.1)(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)
       hasown: 2.0.4
       is-core-module: 2.17.0
       is-glob: 4.0.3
@@ -4403,13 +4533,13 @@ snapshots:
       string.prototype.trimend: 1.0.10
       tsconfig-paths: 3.15.0
     optionalDependencies:
-      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
+      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
     transitivePeerDependencies:
       - eslint-import-resolver-typescript
       - eslint-import-resolver-webpack
       - supports-color
 
-  eslint-plugin-jsx-a11y@6.10.2(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0)):
+  eslint-plugin-jsx-a11y@6.10.2(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2)):
     dependencies:
       aria-query: 5.3.2
       array-includes: 3.2.0
@@ -4419,7 +4549,7 @@ snapshots:
       axobject-query: 4.1.0
       damerau-levenshtein: 1.0.8
       emoji-regex: 9.2.2
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       hasown: 2.0.4
       jsx-ast-utils: 3.3.5
       language-tags: 1.0.9
@@ -4428,11 +4558,11 @@ snapshots:
       safe-regex-test: 1.1.0
       string.prototype.includes: 2.0.1
 
-  eslint-plugin-react-hooks@5.2.0(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0)):
+  eslint-plugin-react-hooks@5.2.0(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2)):
     dependencies:
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
 
-  eslint-plugin-react@7.37.5(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0)):
+  eslint-plugin-react@7.37.5(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2)):
     dependencies:
       array-includes: 3.2.0
       array.prototype.findlast: 1.2.5
@@ -4440,7 +4570,7 @@ snapshots:
       array.prototype.tosorted: 1.1.4
       doctrine: 2.1.0
       es-iterator-helpers: 1.4.0
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       estraverse: 5.3.0
       hasown: 2.0.4
       jsx-ast-utils: 3.3.5
@@ -4465,14 +4595,14 @@ snapshots:
 
   eslint-visitor-keys@5.0.1: {}
 
-  eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0):
+  eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2):
     dependencies:
-      '@eslint-community/eslint-utils': 4.10.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))
+      '@eslint-community/eslint-utils': 4.10.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))
       '@eslint-community/regexpp': 4.12.2
-      '@eslint/config-array': 0.21.2(supports-color@7.2.0)
+      '@eslint/config-array': 0.21.2(supports-color@10.2.2)
       '@eslint/config-helpers': 0.4.2
       '@eslint/core': 0.17.0
-      '@eslint/eslintrc': 3.3.7(supports-color@7.2.0)
+      '@eslint/eslintrc': 3.3.7(supports-color@10.2.2)
       '@eslint/js': 9.39.5
       '@eslint/plugin-kit': 0.4.1
       '@humanfs/node': 0.16.8
@@ -4482,7 +4612,7 @@ snapshots:
       ajv: 6.15.0
       chalk: 4.1.2
       cross-spawn: 7.0.6
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
       escape-string-regexp: 4.0.0
       eslint-scope: 8.4.0
       eslint-visitor-keys: 4.2.1
@@ -4528,6 +4658,12 @@ snapshots:
 
   esutils@2.0.3: {}
 
+  eventsource-parser@4.1.1: {}
+
+  eventsource@5.1.2:
+    dependencies:
+      eventsource-parser: 4.1.1
+
   expect-type@1.4.0: {}
 
   fast-deep-equal@3.1.3: {}
@@ -4674,17 +4810,17 @@ snapshots:
     dependencies:
       whatwg-encoding: 3.1.1
 
-  http-proxy-agent@7.0.2(supports-color@7.2.0):
+  http-proxy-agent@7.0.2(supports-color@10.2.2):
     dependencies:
       agent-base: 7.1.4
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
     transitivePeerDependencies:
       - supports-color
 
-  https-proxy-agent@7.0.6(supports-color@7.2.0):
+  https-proxy-agent@7.0.6(supports-color@10.2.2):
     dependencies:
       agent-base: 7.1.4
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
     transitivePeerDependencies:
       - supports-color
 
@@ -4705,6 +4841,8 @@ snapshots:
 
   indent-string@4.0.0: {}
 
+  index-to-position@1.2.0: {}
+
   internal-slot@1.1.0:
     dependencies:
       es-errors: 1.3.0
@@ -4844,6 +4982,8 @@ snapshots:
 
   jiti@2.7.0: {}
 
+  js-levenshtein@1.1.6: {}
+
   js-tokens@4.0.0: {}
 
   js-tokens@9.0.1: {}
@@ -4852,14 +4992,14 @@ snapshots:
     dependencies:
       argparse: 2.0.1
 
-  jsdom@26.1.0(supports-color@7.2.0):
+  jsdom@26.1.0(supports-color@10.2.2):
     dependencies:
       cssstyle: 4.6.0
       data-urls: 5.0.0
       decimal.js: 10.6.0
       html-encoding-sniffer: 4.0.0
-      http-proxy-agent: 7.0.2(supports-color@7.2.0)
-      https-proxy-agent: 7.0.6(supports-color@7.2.0)
+      http-proxy-agent: 7.0.2(supports-color@10.2.2)
+      https-proxy-agent: 7.0.6(supports-color@10.2.2)
       is-potential-custom-element-name: 1.0.1
       nwsapi: 2.2.28
       parse5: 7.3.0
@@ -4885,6 +5025,8 @@ snapshots:
 
   json-schema-traverse@0.4.1: {}
 
+  json-schema-traverse@1.0.0: {}
+
   json-stable-stringify-without-jsonify@1.0.1: {}
 
   json5@1.0.2:
@@ -5007,6 +5149,10 @@ snapshots:
     dependencies:
       brace-expansion: 1.1.21
 
+  minimatch@5.1.9:
+    dependencies:
+      brace-expansion: 2.1.7
+
   minimist@1.2.8: {}
 
   ms@2.1.3: {}
@@ -5017,7 +5163,7 @@ snapshots:
 
   natural-compare@1.4.0: {}
 
-  next@15.5.6(@babel/core@7.29.7(supports-color@7.2.0))(react-dom@19.2.8(react@19.2.8))(react@19.2.8):
+  next@15.5.6(@babel/core@7.29.7(supports-color@10.2.2))(react-dom@19.2.8(react@19.2.8))(react@19.2.8):
     dependencies:
       '@next/env': 15.5.6
       '@swc/helpers': 0.5.15
@@ -5025,7 +5171,7 @@ snapshots:
       postcss: 8.4.31
       react: 19.2.8
       react-dom: 19.2.8(react@19.2.8)
-      styled-jsx: 5.1.6(@babel/core@7.29.7(supports-color@7.2.0))(react@19.2.8)
+      styled-jsx: 5.1.6(@babel/core@7.29.7(supports-color@10.2.2))(react@19.2.8)
     optionalDependencies:
       '@next/swc-darwin-arm64': 15.5.6
       '@next/swc-darwin-x64': 15.5.6
@@ -5093,6 +5239,22 @@ snapshots:
       define-properties: 1.2.1
       es-object-atoms: 1.1.2
 
+  openapi-fetch@0.13.8:
+    dependencies:
+      openapi-typescript-helpers: 0.0.15
+
+  openapi-typescript-helpers@0.0.15: {}
+
+  openapi-typescript@7.13.0(typescript@5.9.3):
+    dependencies:
+      '@redocly/openapi-core': 1.34.20(supports-color@10.2.2)
+      ansi-colors: 4.1.3
+      change-case: 5.4.4
+      parse-json: 8.3.0
+      supports-color: 10.2.2
+      typescript: 5.9.3
+      yargs-parser: 21.1.1
+
   optionator@0.9.4:
     dependencies:
       deep-is: 0.1.4
@@ -5121,6 +5283,12 @@ snapshots:
     dependencies:
       callsites: 3.1.0
 
+  parse-json@8.3.0:
+    dependencies:
+      '@babel/code-frame': 7.29.7
+      index-to-position: 1.2.0
+      type-fest: 4.41.0
+
   parse5@7.3.0:
     dependencies:
       entities: 6.0.1
@@ -5141,6 +5309,8 @@ snapshots:
 
   picomatch@4.0.7: {}
 
+  pluralize@8.0.0: {}
+
   possible-typed-array-names@1.1.0: {}
 
   postcss@8.4.31:
@@ -5211,6 +5381,8 @@ snapshots:
       gopd: 1.2.0
       set-function-name: 2.0.2
 
+  require-from-string@2.0.2: {}
+
   resolve-from@4.0.0: {}
 
   resolve-pkg-maps@1.0.0: {}
@@ -5461,12 +5633,14 @@ snapshots:
     dependencies:
       js-tokens: 9.0.1
 
-  styled-jsx@5.1.6(@babel/core@7.29.7(supports-color@7.2.0))(react@19.2.8):
+  styled-jsx@5.1.6(@babel/core@7.29.7(supports-color@10.2.2))(react@19.2.8):
     dependencies:
       client-only: 0.0.1
       react: 19.2.8
     optionalDependencies:
-      '@babel/core': 7.29.7(supports-color@7.2.0)
+      '@babel/core': 7.29.7(supports-color@10.2.2)
+
+  supports-color@10.2.2: {}
 
   supports-color@7.2.0:
     dependencies:
@@ -5530,6 +5704,8 @@ snapshots:
     dependencies:
       prelude-ls: 1.2.1
 
+  type-fest@4.41.0: {}
+
   typed-array-buffer@1.0.3:
     dependencies:
       call-bound: 1.0.4
@@ -5562,13 +5738,13 @@ snapshots:
       possible-typed-array-names: 1.1.0
       reflect.getprototypeof: 1.0.10
 
-  typescript-eslint@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3):
+  typescript-eslint@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3):
     dependencies:
-      '@typescript-eslint/eslint-plugin': 8.70.1(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3))(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
-      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
-      '@typescript-eslint/typescript-estree': 8.70.1(supports-color@7.2.0)(typescript@5.9.3)
-      '@typescript-eslint/utils': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@7.2.0))(supports-color@7.2.0)(typescript@5.9.3)
-      eslint: 9.39.5(jiti@2.7.0)(supports-color@7.2.0)
+      '@typescript-eslint/eslint-plugin': 8.70.1(@typescript-eslint/parser@8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3))(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
+      '@typescript-eslint/parser': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
+      '@typescript-eslint/typescript-estree': 8.70.1(supports-color@10.2.2)(typescript@5.9.3)
+      '@typescript-eslint/utils': 8.70.1(eslint@9.39.5(jiti@2.7.0)(supports-color@10.2.2))(supports-color@10.2.2)(typescript@5.9.3)
+      eslint: 9.39.5(jiti@2.7.0)(supports-color@10.2.2)
       typescript: 5.9.3
     transitivePeerDependencies:
       - supports-color
@@ -5617,14 +5793,16 @@ snapshots:
       escalade: 3.2.0
       picocolors: 1.1.1
 
+  uri-js-replace@1.0.1: {}
+
   uri-js@4.4.1:
     dependencies:
       punycode: 2.3.1
 
-  vite-node@3.2.4(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2)(supports-color@7.2.0):
+  vite-node@3.2.4(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2)(supports-color@10.2.2):
     dependencies:
       cac: 6.7.14
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
       es-module-lexer: 1.7.0
       pathe: 2.0.3
       vite: 7.3.6(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2)
@@ -5656,7 +5834,7 @@ snapshots:
       jiti: 2.7.0
       lightningcss: 1.30.2
 
-  vitest@3.2.7(@types/node@24.3.1)(jiti@2.7.0)(jsdom@26.1.0(supports-color@7.2.0))(lightningcss@1.30.2)(supports-color@7.2.0):
+  vitest@3.2.7(@types/node@24.3.1)(jiti@2.7.0)(jsdom@26.1.0(supports-color@10.2.2))(lightningcss@1.30.2)(supports-color@10.2.2):
     dependencies:
       '@types/chai': 5.2.3
       '@vitest/expect': 3.2.7
@@ -5667,7 +5845,7 @@ snapshots:
       '@vitest/spy': 3.2.7
       '@vitest/utils': 3.2.7
       chai: 5.3.3
-      debug: 4.4.3(supports-color@7.2.0)
+      debug: 4.4.3(supports-color@10.2.2)
       expect-type: 1.4.0
       magic-string: 0.30.21
       pathe: 2.0.3
@@ -5679,11 +5857,11 @@ snapshots:
       tinypool: 1.1.1
       tinyrainbow: 2.0.0
       vite: 7.3.6(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2)
-      vite-node: 3.2.4(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2)(supports-color@7.2.0)
+      vite-node: 3.2.4(@types/node@24.3.1)(jiti@2.7.0)(lightningcss@1.30.2)(supports-color@10.2.2)
       why-is-node-running: 2.3.0
     optionalDependencies:
       '@types/node': 24.3.1
-      jsdom: 26.1.0(supports-color@7.2.0)
+      jsdom: 26.1.0(supports-color@10.2.2)
     transitivePeerDependencies:
       - jiti
       - less
@@ -5775,4 +5953,8 @@ snapshots:
 
   yallist@3.1.1: {}
 
+  yaml-ast-parser@0.0.43: {}
+
+  yargs-parser@21.1.1: {}
+
   yocto-queue@0.1.0: {}

frontend/src/components/ask-view.test.tsx

@@ -6,14 +6,16 @@
  *   fills the question box (editable, NO auto-submit)
  * - Refine: disabled without a draft; the exchange completes and
  *   "Use this" fills question + context; "Keep original"/Escape leaves
- *   the draft untouched; Enter advances the exchange without
- *   submitting the outer form; focus returns to the trigger on close
+ *   the draft untouched; Enter advances the exchange exactly once and
+ *   never submits the outer form; Enter on drawer buttons activates
+ *   them normally; focus returns to the trigger on close
  */
 
 import { cleanup, render, screen, waitFor } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
 import { AskView } from "@/components/ask-view";
+import { api } from "@/lib/api/client";
 import { clearAskState, getAskState } from "@/lib/ask-store";
 
 const pushMock = vi.hoisted(() => vi.fn());
@@ -261,4 +263,57 @@ describe("AskView", () => {
     // The keyboard user is not stranded on <body>.
     expect(refine).toHaveFocus();
   });
+
+  it("refine: Enter finishing the exchange composes exactly once", async () => {
+    // Regression (P8 review): the section-level Enter guard re-fired
+    // submitAnswer on the same bubbled event (stale stage closure) —
+    // the composer ran twice, a doubled paid POST once v0.2 wires the
+    // model. The input guard alone must own the Enter path.
+    const composeSpy = vi.spyOn(api, "composeRefinedQuestion");
+    const user = userEvent.setup();
+    render(<AskView />);
+
+    await user.type(
+      screen.getByLabelText(/what do you want to know\?/i),
+      "What are the latest advances in solid-state batteries",
+    );
+    await user.click(screen.getByRole("button", { name: /Refine question/i }));
+    await screen.findByRole("region", { name: /Refine your question/i });
+
+    const answer = await screen.findByLabelText(
+      /What specific part of this topic matters most to you\?/i,
+    );
+    await user.type(answer, "automotive applications");
+    await user.keyboard("{Enter}");
+    await user.click(await screen.findByRole("button", { name: "Skip" }));
+    await user.click(await screen.findByRole("button", { name: "Compose question" }));
+
+    await screen.findByText(/Refined question/i);
+    expect(composeSpy).toHaveBeenCalledTimes(1);
+    composeSpy.mockRestore();
+  });
+
+  it("refine: Enter on a drawer button activates it (Keep original closes)", async () => {
+    // Regression (P8 review): the section-level Enter guard swallowed
+    // the focused button's own activation during the questions stage —
+    // keyboard "Keep original" did nothing.
+    const user = userEvent.setup();
+    render(<AskView />);
+
+    await user.type(
+      screen.getByLabelText(/what do you want to know\?/i),
+      "How good are solid-state batteries",
+    );
+    await user.click(screen.getByRole("button", { name: /Refine question/i }));
+    await screen.findByRole("region", { name: /Refine your question/i });
+
+    screen.getByRole("button", { name: "Keep original" }).focus();
+    await user.keyboard("{Enter}");
+    expect(
+      screen.queryByRole("region", { name: /Refine your question/i }),
+    ).toBeNull();
+    expect(screen.getByLabelText(/what do you want to know\?/i)).toHaveValue(
+      "How good are solid-state batteries",
+    );
+  });
 });

frontend/src/components/refine-question.tsx

@@ -8,10 +8,11 @@
  * one clarifying question at a time, then the composed refined
  * question + suggested context. "Use this" applies the composition to
  * the form; "Keep original" discards it; the draft is never modified
- * until the user accepts. Enter advances the exchange (never the outer
- * form), and focus returns to the trigger when the drawer closes.
- * Scripted in the prototype — honest caption says the model-driven
- * version lands in v0.2.
+ * until the user accepts. The answer input's Enter guard advances the
+ * exchange (never the outer form — the input is the only Enter path,
+ * and all drawer buttons are type="button"); focus returns to the
+ * trigger when the drawer closes. Scripted in the prototype — honest
+ * caption says the model-driven version lands in v0.2.
  */
 
 import { useEffect, useRef, useState } from "react";
@@ -157,12 +158,6 @@ function RefineDrawer({
     <section
       aria-label="Refine your question"
       className="mt-3 rounded-card border border-hairline bg-accent-wash px-5 py-5"
-      onKeyDown={(event) => {
-        if (event.key === "Enter" && exchange?.stage === "questions") {
-          event.preventDefault();
-          submitAnswer();
-        }
-      }}
     >
       <div className="flex items-baseline justify-between gap-2">
         <h3 className="text-small font-semibold uppercase tracking-wide text-accent-ink">
@@ -185,6 +180,17 @@ function RefineDrawer({
           Refine is unavailable right now — try again.
         </p>
       )}
+      {error && (
+        <div className="mt-3">
+          <button
+            type="button"
+            onClick={onClose}
+            className="rounded-pill border border-hairline px-4 py-1.5 text-caption font-medium text-ink-soft transition-colors hover:text-ink"
+          >
+            Keep original
+          </button>
+        </div>
+      )}
 
       {exchange === null && !error && (
         <p className="mt-3 text-caption text-ink-faint">Preparing questions…</p>

frontend/src/components/settings-view.test.tsx

@@ -107,6 +107,6 @@ describe("SettingsView (REQ-65)", () => {
     expect(screen.getByText("preview", { exact: true })).toBeInTheDocument();
 
     expect(screen.getByText(/About & version|About and version/i)).toBeInTheDocument();
-    expect(screen.getByText(/v0\.1\.6 · prototype/i)).toBeInTheDocument();
+    expect(screen.getByText(/v0\.2\.5 · MVP release candidate/i)).toBeInTheDocument();
   });
-});
+});

frontend/src/components/settings-view.tsx

@@ -244,8 +244,9 @@ export function SettingsView() {
             visited-only citations, three clicks to a trustworthy report.
           </p>
           <p className="mt-2 text-caption text-ink-faint">
-            v0.1.6 · prototype — runs on scripted mock data; the engine,
-            adapters, and trust loop arrive in v0.2.
+            v0.2.5 · MVP release candidate — mock-backed by default; the
+            engine, adapters, and trust loop ship with v0.2 (live mode:
+            NEXT_PUBLIC_RESEARCHX_API_MODE=live).
           </p>
         </section>
 

frontend/src/lib/api/client.ts

@@ -26,6 +26,7 @@ import type {
   UserProfile,
 } from "@/lib/types";
 import { MockApiClient } from "@/lib/api/mock/mock-client";
+import { GeneratedApiClient } from "@/lib/api/live-client";
 
 export type { Report, ReportSection } from "@/lib/types";
 export type {
@@ -66,7 +67,8 @@ export interface CreateRunInput {
 
 /**
  * Subscription handle for the live trace stream (EventSource-shaped).
- * v0.2 backs this with SSE; pause/resume stay client-side concerns.
+ * v0.2: backed by SSE in live mode; client-side pause/resume kept
+ * (server-side pause/resume added via the P3 extension below).
  */
 export interface RunEventSubscription {
   /** Stop the stream and release its timers (idempotent). */
@@ -77,6 +79,18 @@ export interface RunEventSubscription {
   resume(): void;
 }
 
+/**
+ * v0.2 P3 extension (grill G-003 — the single planned interface
+ * addition): server-side pause/resume of a running engine across
+ * restarts. Mock mode ignores it; live mode hits the backend.
+ */
+export interface RunLifecycle {
+  /** Pause the engine server-side (durable across restarts). */
+  pauseRun(id: string): Promise<ResearchRun>;
+  /** Resume a server-side-paused run. */
+  resumeRun(id: string): Promise<ResearchRun>;
+}
+
 /**
  * The backend-swappable contract. Every screen talks to this — never
  * to a concrete client, never to the database, never to the network.
@@ -181,7 +195,29 @@ export interface ApiClient {
 
 /**
  * The app-wide singleton. v0.1: MockApiClient (fixture data + scripted
- * event replay, zero API keys). v0.2 P3: rebind to the OpenAPI-generated
- * client — this line is the only thing that changes.
+ * event replay, zero API keys). v0.2 P3 (REQ-26/REQ-54): the binding
+ * switches to the OpenAPI-generated client in live mode — selected by
+ * NEXT_PUBLIC_RESEARCHX_API_MODE=live (mock stays the default). Live mode covers
+ * the core research loop only (G-002); other surfaces stay mock-backed.
  */
-export const api: ApiClient = new MockApiClient();
+class MockApiClientWithLifecycle extends MockApiClient implements RunLifecycle {
+  async pauseRun(id: string): Promise<ResearchRun> {
+    return this.getRun(id);
+  }
+  async resumeRun(id: string): Promise<ResearchRun> {
+    return this.getRun(id);
+  }
+}
+
+function resolveBinding(): ApiClient & RunLifecycle {
+  const mode =
+    process.env.NEXT_PUBLIC_RESEARCHX_API_MODE ??
+    process.env.RESEARCHX_API_MODE ??
+    "mock";
+  if (mode === "live") {
+    return new GeneratedApiClient() as unknown as ApiClient & RunLifecycle;
+  }
+  return new MockApiClientWithLifecycle();
+}
+
+export const api: ApiClient & RunLifecycle = resolveBinding();

frontend/src/lib/api/e2e-real-stack.test.ts

@@ -0,0 +1,215 @@
+/**
+ * @vitest-environment node
+ *
+ * E2E happy path on the REAL stack (REQ-17): new user → research
+ * running in ≤3 clicks using defaults only.
+ *
+ * The live ApiClient binding talks to a real FastAPI app (engine +
+ * fakes) through httpx's ASGI transport wired in as fetch. This is
+ * the full boundary → API → engine → trust-loop loop — no mocks in
+ * the data path. Click budget: submit question (1), pick methodology
+ * (2), approve plan (3).
+ */
+import { afterAll, beforeAll, describe, expect, it } from "vitest";
+
+import { EventSource as EventSourcePolyfill } from "eventsource";
+
+const g = globalThis as unknown as { EventSource?: unknown };
+if (!g.EventSource) {
+  g.EventSource = EventSourcePolyfill;
+}
+
+import { GeneratedApiClient } from "@/lib/api/live-client";
+
+type Lifecycle = { pauseRun(id: string): Promise<unknown> };
+
+let client: GeneratedApiClient & Lifecycle;
+let server: {
+  ready: Promise<void>;
+  close: () => Promise<void>;
+  app: unknown;
+};
+
+beforeAll(async () => {
+  const { spawn } = await import("node:child_process");
+  const { resolve } = await import("node:path");
+
+  const backendDir = resolve(process.cwd(), "..", "backend");
+  const child = spawn(
+    "/bin/bash",
+    ["-lc", "uv run python -m researchx.api.dev_bridge"],
+    {
+      cwd: backendDir,
+      stdio: ["pipe", "pipe", "inherit"],
+    },
+  );
+
+  const ready = new Promise<void>((resolve, reject) => {
+    const timer = setTimeout(() => reject(new Error("bridge not ready in 60s")), 60_000);
+    let buf = "";
+    child.stdout!.on("data", (chunk: Buffer) => {
+      buf += chunk.toString();
+      if (buf.includes("READY")) {
+        clearTimeout(timer);
+        resolve();
+      }
+    });
+    child.on("error", (err) => {
+      clearTimeout(timer);
+      reject(err);
+    });
+  });
+
+  server = {
+    app: child,
+    ready,
+    close: async () => {
+      child.kill("SIGTERM");
+    },
+  };
+  await ready;
+
+  const waitForPort = async (): Promise<void> => {
+    const deadline = Date.now() + 30_000;
+    while (Date.now() < deadline) {
+      try {
+        const probe = await fetch("http://127.0.0.1:8000/api/config");
+        if (probe.ok) {
+          return;
+        }
+      } catch {
+        // not listening yet
+      }
+      await new Promise((r) => setTimeout(r, 250));
+    }
+    throw new Error("backend bridge never listened on 8000");
+  };
+  await waitForPort();
+
+  const fetchImpl = (async (input: RequestInfo | URL, init?: RequestInit) => {
+    const req = input instanceof Request ? input : new Request(input, init);
+    const body = req.body ? await new Response(req.body).text() : undefined;
+    const headers: Record<string, string> = {};
+    req.headers.forEach((v, k) => {
+      headers[k] = v;
+    });
+    const response = await fetch("http://127.0.0.1:8000" + new URL(req.url).pathname, {
+      method: req.method,
+      headers,
+      ...(body ? { body } : {}),
+    });
+    return response;
+  }) as typeof globalThis.fetch;
+
+  client = new GeneratedApiClient(fetchImpl) as GeneratedApiClient & Lifecycle;
+}, 90_000);
+
+afterAll(async () => {
+  await server?.close?.();
+});
+
+describe("E2E happy path — real stack, defaults only (REQ-17)", () => {
+  it("runs research in ≤3 user actions", async () => {
+    // Action budget: 1) submit question on Ask, 2) pick methodology on
+    // Choose (defaults preselected — the plan requires zero dial fiddling),
+    // 3) approve plan on Plan & Run.
+    let userActions = 0;
+
+    const methodologies = await client.getMethodologies(); // catalog load — not a click
+    expect(methodologies.length).toBeGreaterThanOrEqual(2);
+
+    const question = "How do verification pipelines keep citations honest?";
+    userActions += 1; // Ask: submit question
+    const run = await client.createRun({
+      question,
+      methodologySlug: "rapid-answer",
+    });
+    expect(run.status).toBeOneOf(["planning", "awaiting_approval"]);
+
+    userActions += 2; // Choose: pick methodology + Plan & Run: approve
+    let current = await client.getRun(run.id);
+    const deadline = Date.now() + 30_000;
+    while (current.status === "planning" && Date.now() < deadline) {
+      current = await client.getRun(run.id);
+    }
+    expect(current.plan.subQuestions.length).toBeGreaterThanOrEqual(1);
+
+    const approved = await client.approvePlan(run.id);
+    expect(approved.status).not.toBe("planning");
+
+    let done = false;
+    const events: string[] = [];
+    await new Promise<void>((resolve, reject) => {
+      const timer = setTimeout(() => reject(new Error("run timed out")), 60_000);
+      const subscription = client.getRunEvents(
+        run.id,
+        (event) => {
+          events.push(event.type);
+        },
+        () => {
+          done = true;
+          clearTimeout(timer);
+          resolve();
+        },
+      );
+      // Safety valve — cancel the subscription if the run hangs.
+      setTimeout(() => {
+        if (!done) {
+          subscription.cancel();
+          clearTimeout(timer);
+          reject(new Error("no run_done within window"));
+        }
+      }, 55_000);
+    });
+    expect(done).toBe(true);
+    expect(events).toContain("status");
+
+    const final = await client.getRun(run.id);
+    expect(final.status).toBe("done");
+    expect(userActions).toBeLessThanOrEqual(3);
+  }, 90_000);
+
+  it("exports round-trip: markdown carries citation links, JSON validates (REQ-34)", async () => {
+    const run = await client.createRun({
+      question: "Export round-trip proof",
+      methodologySlug: "rapid-answer",
+    });
+    const deadline = Date.now() + 30_000;
+    let current = await client.getRun(run.id);
+    while (current.status === "planning" && Date.now() < deadline) {
+      current = await client.getRun(run.id);
+    }
+    await client.approvePlan(run.id);
+    const doneDeadline = Date.now() + 60_000;
+    while (current.status !== "done" && Date.now() < doneDeadline) {
+      current = await client.getRun(run.id);
+    }
+    expect(current.status).toBe("done");
+
+    const markdown = await client.exportReport(run.id, "markdown");
+    expect(markdown.filename.endsWith(".md")).toBe(true);
+    expect(markdown.content).toContain("[p-");
+    const linkRe = /\[https?:\/\/[^\]]+\]\(https?:\/\/[^)]+\)/;
+    expect(markdown.content).toMatch(linkRe);
+
+    const json = await client.exportReport(run.id, "json");
+    expect(json.filename.endsWith(".json")).toBe(true);
+    const parsed = JSON.parse(json.content) as {
+      run_id: string;
+      entries: Array<{
+        url: string;
+        visited_at: string;
+        passages: string[];
+        health: string;
+        authority_tier: string | number;
+      }>;
+    };
+    expect(parsed.run_id).toBe(run.id);
+    expect(parsed.entries.length).toBeGreaterThanOrEqual(1);
+    for (const entry of parsed.entries) {
+      expect(entry.url).toMatch(/^https?:\/\//);
+      expect(entry.health).toBeOneOf(["live", "stale", "dead"]);
+      expect(Array.isArray(entry.passages)).toBe(true);
+    }
+  }, 90_000);
+});

frontend/src/lib/api/generated/schema.d.ts

@@ -0,0 +1,628 @@
+/**
+ * This file was auto-generated by openapi-typescript.
+ * Do not make direct changes to the file.
+ */
+
+export interface paths {
+    "/api/config": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        /** Config Status */
+        get: operations["config_status_api_config_get"];
+        put?: never;
+        post?: never;
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/methodologies": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        /** Methodologies */
+        get: operations["methodologies_api_methodologies_get"];
+        put?: never;
+        post?: never;
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/runs": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        get?: never;
+        put?: never;
+        /** Create Run */
+        post: operations["create_run_api_runs_post"];
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/runs/{run_id}": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        /** Get Run */
+        get: operations["get_run_api_runs__run_id__get"];
+        put?: never;
+        post?: never;
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/runs/{run_id}/approve": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        get?: never;
+        put?: never;
+        /** Approve Run */
+        post: operations["approve_run_api_runs__run_id__approve_post"];
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/runs/{run_id}/pause": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        get?: never;
+        put?: never;
+        /** Pause Run */
+        post: operations["pause_run_api_runs__run_id__pause_post"];
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/runs/{run_id}/resume": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        get?: never;
+        put?: never;
+        /** Resume Run */
+        post: operations["resume_run_api_runs__run_id__resume_post"];
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/runs/{run_id}/cancel": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        get?: never;
+        put?: never;
+        /** Cancel Run */
+        post: operations["cancel_run_api_runs__run_id__cancel_post"];
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/runs/{run_id}/events": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        /** Run Events */
+        get: operations["run_events_api_runs__run_id__events_get"];
+        put?: never;
+        post?: never;
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/runs/{run_id}/report": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        /** Run Report */
+        get: operations["run_report_api_runs__run_id__report_get"];
+        put?: never;
+        post?: never;
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/api/runs/{run_id}/ledger": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        /** Run Ledger */
+        get: operations["run_ledger_api_runs__run_id__ledger_get"];
+        put?: never;
+        post?: never;
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+}
+export type webhooks = Record<string, never>;
+export interface components {
+    schemas: {
+        /** ApproveBody */
+        ApproveBody: {
+            /** Plan */
+            plan?: {
+                [key: string]: unknown;
+            } | null;
+        };
+        /** ConfigStatus */
+        ConfigStatus: {
+            /** Model Adapter */
+            model_adapter: string;
+            /** Search Adapter */
+            search_adapter: string;
+            /** Storage Dir */
+            storage_dir: string;
+            /** Probe */
+            probe?: {
+                [key: string]: unknown;
+            } | null;
+            /** Cost Counters */
+            cost_counters: {
+                [key: string]: number;
+            };
+        };
+        /** CreateRunBody */
+        CreateRunBody: {
+            /** Question */
+            question: string;
+            /**
+             * Context
+             * @default
+             */
+            context: string;
+            /** Methodology */
+            methodology: string;
+            /** Dial Overrides */
+            dial_overrides?: {
+                [key: string]: unknown;
+            };
+        };
+        /** HTTPValidationError */
+        HTTPValidationError: {
+            /** Detail */
+            detail?: components["schemas"]["ValidationError"][];
+        };
+        /** MethodologyCard */
+        MethodologyCard: {
+            /** Slug */
+            slug: string;
+            /** Name */
+            name: string;
+            /** Description */
+            description: string;
+            /** Eta Minutes */
+            eta_minutes: number;
+            /** Cost Estimate */
+            cost_estimate: string;
+            /** Why Recommended */
+            why_recommended: string;
+            /** Output Shape */
+            output_shape: string;
+            /** Dials */
+            dials: {
+                [key: string]: unknown;
+            };
+        };
+        /** RunSummary */
+        RunSummary: {
+            /** Id */
+            id: string;
+            /** Status */
+            status: string;
+            /** Question */
+            question: string;
+            /** Methodology */
+            methodology: string;
+            /** Plan */
+            plan?: {
+                [key: string]: unknown;
+            } | null;
+            /** Started At */
+            started_at: string;
+        };
+        /** ValidationError */
+        ValidationError: {
+            /** Location */
+            loc: (string | number)[];
+            /** Message */
+            msg: string;
+            /** Error Type */
+            type: string;
+        };
+    };
+    responses: never;
+    parameters: never;
+    requestBodies: never;
+    headers: never;
+    pathItems: never;
+}
+export type $defs = Record<string, never>;
+export interface operations {
+    config_status_api_config_get: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["ConfigStatus"];
+                };
+            };
+        };
+    };
+    methodologies_api_methodologies_get: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["MethodologyCard"][];
+                };
+            };
+        };
+    };
+    create_run_api_runs_post: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        requestBody: {
+            content: {
+                "application/json": components["schemas"]["CreateRunBody"];
+            };
+        };
+        responses: {
+            /** @description Successful Response */
+            201: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["RunSummary"];
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+    get_run_api_runs__run_id__get: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path: {
+                run_id: string;
+            };
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["RunSummary"];
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+    approve_run_api_runs__run_id__approve_post: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path: {
+                run_id: string;
+            };
+            cookie?: never;
+        };
+        requestBody?: {
+            content: {
+                "application/json": components["schemas"]["ApproveBody"] | null;
+            };
+        };
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["RunSummary"];
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+    pause_run_api_runs__run_id__pause_post: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path: {
+                run_id: string;
+            };
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["RunSummary"];
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+    resume_run_api_runs__run_id__resume_post: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path: {
+                run_id: string;
+            };
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["RunSummary"];
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+    cancel_run_api_runs__run_id__cancel_post: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path: {
+                run_id: string;
+            };
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["RunSummary"];
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+    run_events_api_runs__run_id__events_get: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path: {
+                run_id: string;
+            };
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": unknown;
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+    run_report_api_runs__run_id__report_get: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path: {
+                run_id: string;
+            };
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": {
+                        [key: string]: unknown;
+                    };
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+    run_ledger_api_runs__run_id__ledger_get: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path: {
+                run_id: string;
+            };
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": {
+                        [key: string]: unknown;
+                    };
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+}

frontend/src/lib/api/live-client.test.ts

@@ -0,0 +1,157 @@
+/**
+ * Boundary tests for the v0.2 P3 client swap (REQ-26, G-003).
+ *
+ * Live mode is contract-tested against a stubbed global fetch — no
+ * network, no keys. Mock mode stays pinned by the existing suite.
+ */
+import { describe, expect, it } from "vitest";
+
+import { GeneratedApiClient } from "@/lib/api/live-client";
+import type { BackendRun } from "@/lib/api/test-helpers";
+
+type RouteHandler = (url: string, init?: RequestInit) => { status: number; body: unknown };
+
+function stubRoutes(routes: Record<string, RouteHandler>): typeof globalThis.fetch {
+  return (async (input: RequestInfo | URL, init?: RequestInit) => {
+    const url = input instanceof Request ? input.url : String(input);
+    for (const [prefix, handler] of Object.entries(routes)) {
+      if (url.startsWith(prefix)) {
+        const { status, body } = handler(url, init);
+        return new Response(JSON.stringify(body), {
+          status,
+          headers: { "Content-Type": "application/json" },
+        });
+      }
+    }
+    return new Response(JSON.stringify({ detail: "not found" }), { status: 404 });
+  }) as typeof globalThis.fetch;
+}
+
+const backendRun: BackendRun = {
+  id: "abcd2345",
+  status: "awaiting_approval",
+  question: "How do engines run?",
+  methodology: "rapid-answer",
+  plan: {
+    sub_questions: ["verification passes"],
+    source_universe: ["web"],
+    outline: ["intro"],
+  },
+  started_at: "2026-09-27T12:00:00Z",
+};
+
+describe("GeneratedApiClient (live binding)", () => {
+  it("maps backend methodology cards to the frontend Methodology shape", async () => {
+    const routes = {
+      "http://127.0.0.1:8000/api/methodologies": (): { status: number; body: unknown } => ({
+        status: 200,
+        body: [
+          {
+            slug: "rapid-answer",
+            name: "Rapid Answer",
+            description: "One pass, one memo. Fastest path.",
+            eta_minutes: 2,
+            cost_estimate: "~5k tokens (estimate)",
+            why_recommended: "Fastest path to a confident cited answer.",
+            output_shape: "memo",
+            dials: { depth: 1, breadth: 1 },
+          },
+        ],
+      }),
+    };
+    const client = new GeneratedApiClient(stubRoutes(routes));
+    const cards = await client.getMethodologies();
+    expect(cards).toHaveLength(1);
+    expect(cards[0]?.slug).toBe("rapid-answer");
+    expect(cards[0]?.etaMinutes).toBe(2);
+    expect(cards[0]?.costEstimate).toContain("estimate");
+    expect(cards[0]?.defaultDials).toEqual({ depth: 1, breadth: 1 });
+  });
+
+  it("creates runs through the backend contract", async () => {
+    const routes = {
+      "http://127.0.0.1:8000/api/runs": (url: string, init?: RequestInit) => {
+        const method =
+          init?.method ?? (url.endsWith("/api/runs") ? "POST" : undefined);
+        return {
+          status: 201,
+          body: method === "POST" ? backendRun : { detail: "wrong method" },
+        };
+      },
+    };
+    const client = new GeneratedApiClient(stubRoutes(routes));
+    const run = await client.createRun({
+      question: "How do engines run?",
+      methodologySlug: "rapid-answer",
+    });
+    expect(run.id).toBe("abcd2345");
+    expect(run.status).toBe("awaiting_approval");
+    expect(run.plan.subQuestions).toEqual(["verification passes"]);
+    expect(run.plan.methodologySlug).toBe("rapid-answer");
+  });
+
+  it("approves, cancels, pauses, resumes via lifecycle routes", async () => {
+    const routes = {
+      "http://127.0.0.1:8000/api/runs/abcd2345/approve": () => ({
+        status: 200,
+        body: { ...backendRun, status: "searching" },
+      }),
+      "http://127.0.0.1:8000/api/runs/abcd2345/cancel": () => ({
+        status: 200,
+        body: { ...backendRun, status: "cancelled" },
+      }),
+      "http://127.0.0.1:8000/api/runs/abcd2345/pause": () => ({
+        status: 200,
+        body: { ...backendRun, status: "searching" },
+      }),
+      "http://127.0.0.1:8000/api/runs/abcd2345/resume": () => ({
+        status: 200,
+        body: { ...backendRun, status: "verifying" },
+      }),
+    };
+    const client = new GeneratedApiClient(stubRoutes(routes));
+    expect((await client.approvePlan("abcd2345")).status).toBe("searching");
+    expect((await client.cancelRun("abcd2345")).status).toBe("cancelled");
+    expect((await client.pauseRun("abcd2345")).status).toBe("searching");
+    expect((await client.resumeRun("abcd2345")).status).toBe("verifying");
+  });
+
+  it("maps the ledger to frontend citations with health + tier", async () => {
+    const routes = {
+      "http://127.0.0.1:8000/api/runs/abcd2345/ledger": () => ({
+        status: 200,
+        body: {
+          run_id: "abcd2345",
+          generated_at: "2026-09-27T12:01:00Z",
+          entries: [
+            {
+              url: "https://example.org/a",
+              visited_at: "2026-09-27T12:00:00Z",
+              passages: ["p-1", "p-2"],
+              claims_supported: 2,
+              health: "live",
+              authority_tier: "official",
+            },
+          ],
+        },
+      }),
+    };
+    const client = new GeneratedApiClient(stubRoutes(routes));
+    const ledger = await client.getLedger("abcd2345");
+    expect(ledger.runId).toBe("abcd2345");
+    expect(ledger.citations[0]?.verification).toBe("live");
+    expect(ledger.citations[0]?.authorityTier).toBe(1);
+  });
+
+  it("fetches the report markdown", async () => {
+    const routes = {
+      "http://127.0.0.1:8000/api/runs/abcd2345/report": () => ({
+        status: 200,
+        body: { run_id: "abcd2345", markdown: "# Report\n\nClaim [p-1]." },
+      }),
+    };
+    const client = new GeneratedApiClient(stubRoutes(routes));
+    const report = await client.getReport("abcd2345");
+    expect(report.sections[0]?.body).toContain("[p-1]");
+  });
+});

frontend/src/lib/api/live-client.ts

@@ -0,0 +1,390 @@
+/**
+ * GeneratedApiClient — the live-mode ApiClient binding (v0.2 P3, REQ-26/REQ-54).
+ *
+ * Core research loop methods (methodologies, runs, events, report,
+ * ledger, export) hit the FastAPI backend through openapi-fetch,
+ * typed by the generated schema. Per G-002, the remaining prototype
+ * surfaces (library, settings, suggestions, refine, graph, inbox,
+ * profile) stay mock-backed until v0.3+ — this class delegates those
+ * to the MockApiClient rather than reimplementing them.
+ *
+ * Components never import this class — only client.ts (the boundary)
+ * does, selected by RESEARCHX_API_MODE=live (mock is the default).
+ */
+
+import createClient from "openapi-fetch";
+
+import type { paths } from "@/lib/api/generated/schema";
+import type {
+  CitationLedger,
+  Methodology,
+  Report,
+  ResearchRun,
+  TraceEvent,
+} from "@/lib/types";
+import type {
+  CreateRunInput,
+  RunEventSubscription,
+} from "@/lib/api/client";
+import { MockApiClient } from "@/lib/api/mock/mock-client";
+
+function baseUrl(): string {
+  return (
+    process.env.NEXT_PUBLIC_API_BASE_URL ?? "http://127.0.0.1:8000"
+  );
+}
+
+type BackendRun = {
+  id: string;
+  status: string;
+  question: string;
+  methodology: string;
+  plan: {
+    sub_questions: string[];
+    source_universe: string[];
+    outline: string[];
+  } | null;
+  started_at: string;
+};
+
+type BackendCard = {
+  slug: string;
+  name: string;
+  description: string;
+  eta_minutes: number;
+  cost_estimate: string;
+  why_recommended: string;
+  output_shape: string;
+  dials: Record<string, unknown>;
+};
+
+export class GeneratedApiClient extends MockApiClient {
+  #client: ReturnType<typeof createClient<paths>>;
+
+  constructor(fetchImpl?: typeof globalThis.fetch) {
+    super();
+    this.#client = createClient<paths>({
+      baseUrl: baseUrl(),
+      ...(fetchImpl ? { fetch: fetchImpl } : {}),
+    });
+  }
+
+  override async getMethodologies(): Promise<Methodology[]> {
+    const { data, error } = await this.#client.GET("/api/methodologies");
+    if (error || !data) {
+      throw new Error("live: failed to load methodologies");
+    }
+    return (data as BackendCard[]).map((card, index) => ({
+      slug: card.slug,
+      name: card.name,
+      tagline: card.description.split(".")[0] ?? card.description,
+      description: card.description,
+      etaMinutes: card.eta_minutes,
+      costEstimate: card.cost_estimate,
+      whyRecommended: card.why_recommended,
+      recommended: index === 0,
+      verification: card.slug === "deep-report" ? "full" : "standard",
+      dialSummary: Object.entries(card.dials).map(
+        ([dial, value]) => `${dial}: ${String(value)}`,
+      ),
+      defaultDials: card.dials as unknown as Methodology["defaultDials"],
+      badge: card.slug === "rapid-answer" ? "Fastest" : undefined,
+    }));
+  }
+
+  #toRun(run: BackendRun): ResearchRun {
+    const plan = run.plan;
+    return {
+      id: run.id,
+      status: run.status as ResearchRun["status"],
+      plan: {
+        id: run.id,
+        question: run.question,
+        methodologySlug: run.methodology,
+        subQuestions: plan?.sub_questions ?? [],
+        sourceUniverse: plan?.source_universe ?? [],
+        outline: plan?.outline ?? [],
+      },
+      startedAt: run.started_at,
+    };
+  }
+
+  override async createRun(input: CreateRunInput): Promise<ResearchRun> {
+    const overrides: Record<string, unknown> = {};
+    for (const [key, value] of Object.entries(input.dialOverrides ?? {})) {
+      const snake = key.replace(/[A-Z]/g, (m) => `_${m.toLowerCase()}`);
+      overrides[snake] = value;
+    }
+    const { data, error } = await this.#client.POST("/api/runs", {
+      body: {
+        question: input.question,
+        context: input.context ?? "",
+        methodology: input.methodologySlug,
+        dial_overrides: overrides,
+      },
+    });
+    if (error || !data) {
+      throw new Error("live: failed to create run");
+    }
+    return this.#toRun(data as BackendRun);
+  }
+
+  override async getRun(id: string): Promise<ResearchRun> {
+    const { data, error } = await this.#client.GET("/api/runs/{run_id}", {
+      params: { path: { run_id: id } },
+    });
+    if (error || !data) {
+      throw new Error(`live: failed to load run ${id}`);
+    }
+    return this.#toRun(data as BackendRun);
+  }
+
+  override async approvePlan(id: string): Promise<ResearchRun> {
+    const { data, error } = await this.#client.POST(
+      "/api/runs/{run_id}/approve",
+      { params: { path: { run_id: id } }, body: {} },
+    );
+    if (error || !data) {
+      throw new Error(`live: failed to approve run ${id}`);
+    }
+    return this.#toRun(data as BackendRun);
+  }
+
+  override async cancelRun(id: string): Promise<ResearchRun> {
+    const { data, error } = await this.#client.POST(
+      "/api/runs/{run_id}/cancel",
+      { params: { path: { run_id: id } } },
+    );
+    if (error || !data) {
+      throw new Error(`live: failed to cancel run ${id}`);
+    }
+    return this.#toRun(data as BackendRun);
+  }
+
+  async pauseRun(id: string): Promise<ResearchRun> {
+    const { data, error } = await this.#client.POST(
+      "/api/runs/{run_id}/pause",
+      { params: { path: { run_id: id } } },
+    );
+    if (error || !data) {
+      throw new Error(`live: failed to pause run ${id}`);
+    }
+    return this.#toRun(data as BackendRun);
+  }
+
+  async resumeRun(id: string): Promise<ResearchRun> {
+    const { data, error } = await this.#client.POST(
+      "/api/runs/{run_id}/resume",
+      { params: { path: { run_id: id } } },
+    );
+    if (error || !data) {
+      throw new Error(`live: failed to resume run ${id}`);
+    }
+    return this.#toRun(data as BackendRun);
+  }
+
+  override getRunEvents(
+    id: string,
+    onEvent: (event: TraceEvent) => void,
+    onDone?: () => void,
+  ): RunEventSubscription {
+    const source = new EventSource(
+      `${baseUrl()}/api/runs/${encodeURIComponent(id)}/events`,
+    );
+    let paused = false;
+    let buffer: TraceEvent[] = [];
+    let counter = 0;
+
+    const deliver = (event: TraceEvent) => {
+      if (paused) {
+        buffer.push(event);
+      } else {
+        onEvent(event);
+      }
+    };
+
+    const mapType = (type: string): TraceEvent["type"] => {
+      if (type === "query_fired") return "query";
+      if (type === "source_visited") return "source_visited";
+      if (type === "passage_extracted") return "passage_extracted";
+      if (type === "state_changed") return "status";
+      if (type === "run_done" || type === "run_started") return "status";
+      if (type === "run_error") return "status";
+      return "status";
+    };
+
+    const handle = (backendEvent: { type: string; data: unknown }) => {
+      let detail = "";
+      let message = backendEvent.type;
+      if (typeof backendEvent.data === "string") {
+        try {
+          const parsed = JSON.parse(backendEvent.data) as {
+            type: string;
+            data: Record<string, string>;
+          };
+          message =
+            parsed.data?.message ??
+            parsed.data?.query ??
+            parsed.data?.url ??
+            parsed.data?.state ??
+            backendEvent.type;
+          detail = JSON.stringify(parsed.data);
+        } catch {
+          detail = backendEvent.data;
+        }
+      }
+      counter += 1;
+      deliver({
+        id: `live-${counter}`,
+        ts: new Date().toISOString(),
+        type: mapType(backendEvent.type),
+        message,
+        detail,
+      });
+      if (backendEvent.type === "run_done" || backendEvent.type === "run_error") {
+        source.close();
+        onDone?.();
+      }
+    };
+
+    source.onmessage = (raw) => {
+      handle({ type: "message", data: raw.data });
+    };
+    for (const type of [
+      "run_started",
+      "query_fired",
+      "source_found",
+      "source_visited",
+      "passage_extracted",
+      "source_refused",
+      "state_changed",
+      "probe_attached",
+      "run_done",
+      "run_error",
+    ]) {
+      source.addEventListener(type, (raw) => {
+        handle({ type, data: (raw as MessageEvent).data });
+      });
+    }
+
+    return {
+      cancel() {
+        source.close();
+      },
+      pause() {
+        paused = true;
+      },
+      resume() {
+        paused = false;
+        const pending = buffer;
+        buffer = [];
+        for (const event of pending) {
+          onEvent(event);
+        }
+      },
+    };
+  }
+
+  override async getReport(id: string): Promise<Report> {
+    const { data, error } = await this.#client.GET(
+      "/api/runs/{run_id}/report",
+      { params: { path: { run_id: id } } },
+    );
+    if (error || !data) {
+      throw new Error(`live: report not ready for run ${id}`);
+    }
+    const markdown = (data as { run_id: string; markdown: string }).markdown;
+    return {
+      id,
+      runId: id,
+      title: "Research Report",
+      sections: [{ heading: "Report", body: markdown }],
+      citations: [],
+    };
+  }
+
+  override async getLedger(id: string): Promise<CitationLedger> {
+    const { data, error } = await this.#client.GET(
+      "/api/runs/{run_id}/ledger",
+      { params: { path: { run_id: id } } },
+    );
+    if (error || !data) {
+      throw new Error(`live: ledger not ready for run ${id}`);
+    }
+    const backend = data as {
+      run_id: string;
+      generated_at: string;
+      entries: Array<{
+        url: string;
+        visited_at: string;
+        passages: string[];
+        claims_supported: number;
+        health: string;
+        authority_tier: string;
+      }>;
+    };
+    return {
+      runId: backend.run_id,
+      generatedAt: backend.generated_at,
+      citations: backend.entries.map((entry, index) => ({
+        id: `c-${index + 1}`,
+        url: entry.url,
+        title: entry.url,
+        site: entry.url,
+        passageId: entry.passages[0] ?? "",
+        quote: "",
+        verification: (entry.health === "live"
+          ? "live"
+          : entry.health === "stale"
+            ? "stale"
+            : "dead") as CitationLedger["citations"][number]["verification"],
+        authorityTier: (entry.authority_tier === "official"
+          ? 1
+          : entry.authority_tier === "reference"
+            ? 2
+            : 3) as CitationLedger["citations"][number]["authorityTier"],
+      })),
+    };
+  }
+
+  override async exportReport(
+    id: string,
+    format: "markdown" | "json",
+  ): Promise<{ filename: string; content: string }> {
+    const [report, ledger] = await Promise.all([this.getReport(id), this.getLedger(id)]);
+    if (format === "markdown") {
+      const body = report.sections.map((s) => `## ${s.heading}\n\n${s.body}`).join("\n\n");
+      const citationsBlock = ledger.citations
+        .map(
+          (c, i) =>
+            `${i + 1}. [${c.url}](${c.url}) — health: ${c.verification}, tier: ${c.authorityTier}`,
+        )
+        .join("\n");
+      return {
+        filename: `researchx-${id}.md`,
+        content:
+          `# Research Report\n\n${body}\n\n## Citations\n\n${citationsBlock || "(no citations)"}\n`,
+      };
+    }
+    const payload = {
+      run_id: id,
+      generated_at: ledger.generatedAt,
+      entries: ledger.citations.map((c) => ({
+        url: c.url,
+        visited_at: ledger.generatedAt,
+        passages: c.passageId ? [c.passageId] : [],
+        claims_supported: 1,
+        health: c.verification,
+        authority_tier: c.authorityTier === 1 ? "official" : c.authorityTier === 2 ? "reference" : "general",
+      })),
+      checklist: {
+        run_id: id,
+        citations_checked: ledger.citations.length,
+      },
+    };
+    return {
+      filename: `researchx-${id}.json`,
+      content: JSON.stringify(payload, null, 2),
+    };
+  }
+}

frontend/src/lib/api/test-helpers.ts

@@ -0,0 +1,14 @@
+/** Shared test fixtures for live-binding contract tests. */
+
+export interface BackendRun {
+  id: string;
+  status: string;
+  question: string;
+  methodology: string;
+  plan: {
+    sub_questions: string[];
+    source_universe: string[];
+    outline: string[];
+  } | null;
+  started_at: string;
+}