Commit Graph

9 Commits

Author SHA1 Message Date
CIAgent 12b2300f6f fix(P07): final review — CORS PUT, WS origin gate, ingest leak+O(n²), symlink escape, retry leak, doc-reality gaps
---ci---
phase: 7
milestone: v0.3
status: review
lessons:
  - P0 CORS: allow_methods lacked PUT while the build surface writes files with PUT — every cross-origin Save failed preflight; pinned with tests/api/test_cors.py
  - P0 ingest leak: queue-overflow flood path returned without the disconnect sentinel, parking the drainer forever (one leaked task-set per flooded trace); sentinel now always enqueued, real-server regression test added
  - P1 perf: flood cap counted rows via len(get_trace(...)) — O(trace) per append, O(n²) per session; TraceStore.count() (COUNT(*)) added and wired
  - P0 security: file routes followed exec-planted symlinks out of the workspace bind; _resolve_in_workspace refuses escapes (422), read/write now 404 on unknown sandboxes (was 500)
  - P1 security: WS ingest accepted any browser Origin (CORS middleware does not cover WS); localhost dev origins + no-Origin (capture agent) allowed, others 1008
  - P1 correctness: use-sandbox-session leaked a created sandbox on any mid-start failure (per-learner cap 1 → all retries 429 forever); failed starts now destroy what they created
  - P2 testing: reconnect-flush test killed mid-burst (nondeterministic under load, reproduced on pre-change code); now waits for server-side observation of the pre-kill burst — the underlying one-line replay-margin/ACK gap is documented for v0.4
  - maintainability: grading-store/templates/grading.ts docstrings claimed grading is variant-blind (stale pre-P4 text) — updated; ARCHITECTURE.md referenced nonexistent voice/openai_audio.py; dead if TYPE_CHECKING: pass blocks removed
---/ci---
2026-09-12 20:02:10 +00:00
CIAgent 925ab096fb feat(P06): agent re-grounding on real engine inputs + corpus dormancy (Wave 1)
Tasks 6-1-01..04 (REQ-3-007): Lab consumes the LIVE trace digest (compute_digest over
TraceStore events; empty trace coaches the baseline); Assessor renders coaching FROM
the stored GradeRecord (it never invents scores — the grading engine owns that;
evaluate endpoint re-grounded: 404 without a grade); Proctor consumes digest +
DefenseStore long-pause signals + variant seed cross-check. Corpus telemetry/artifacts
DORMANT (headers + AST dormancy test: zero production importers; learner_context stays
active; retained as Phase-3 calibration history). lifespan now adopts a pre-set
provider (state-injection pattern).

v0.2 corpus-path endpoint tests updated honestly to the live contract (learner_id+task_id).
392 tests green; ruff clean.

---ci---
phase: 6
milestone: v0.3
status: execute
requirements: {covered: [REQ-3-007], partial: []}
---/ci---
2026-09-12 05:15:25 +00:00
CIAgent 04bdccf189 feat(P05): defense endpoints (Wave 3)
Task 5-3-01: api/defense.py — POST /v1/defense/start (DefenseRecord + first examiner
question persisted + voice descriptor + trace_complete disclosure — the defense does
NOT gate on completeness, the grader does per G-4), POST /{id}/answer ({text} or
multipart audio -> STT via VoiceProvider; follow-up question; per-turn latency
stt_ms/llm_ms/tts_ms), GET /{id}/audio/{turn_id} (streaming TTS WAV), POST /{id}/finish
(DefenseVerdict via D-020 + A-109 integrity signals: long pauses computed from turn
metadata at PAUSE_THRESHOLD_MS=15s), GET /{id} (ordered transcript + signals + status).
Lifespan wires DefenseStore + voice provider + ExaminerAgent. python-multipart dep for
audio parsing.

11 endpoint tests green (full loop mock voice + mock LLM; long-pause signal; 404s; 422
no-body; audio streaming). Suite 378 green; ruff clean.

---ci---
phase: 5
milestone: v0.3
status: execute
requirements: {covered: [REQ-3-006], partial: []}
---/ci---
2026-09-12 04:37:30 +00:00
CIAgent 6ab0ae2c0a fix(P04): ship variant anchors to the grader prompt (MH#4 second clause — verifier P1)
GradingEngine takes an optional VariantStore (constructor DI); when the graded
task_id joins to a stored variant: the template's difficulty anchors render into
the grader user turn ("Expected effort envelope" — same bar for every variant of
the template, a-5) and the variant seed is stamped on the GradeRecord (D-029).
Lifespan reordered: VariantStore builds before the engine and is passed in.
Anchors context carries only template id + anchor numbers — D-028 learner-anonymity
preserved (leak tests keep holding). Plain engine (no store) stays variant-blind;
non-variant tasks grade without the envelope.

3 new tests: variant task -> anchors + seed present in prompt/record;
non-variant task -> no envelope; plain engine -> variant_seed None.
Suite 327 green; ruff clean.

---ci---
phase: 4
milestone: v0.3
status: verify
requirements: {covered: [REQ-3-005], partial: []}
---/ci---
2026-09-12 03:51:25 +00:00
CIAgent 4acffac71e feat(P04): variants API + TS types (Wave 3)
Task 4-3-01: POST /v1/variants (template_id or competency_id resolution; cache-first
D-029; 404 unknown template/competency; 422 neither), GET /v1/variants/{task_id},
GET /v1/variants?learner_id=. SQLiteVariantStore + VariantGenerator wired into lifespan.
Task 4-3-02: packages/types/variants.ts (TaskVariant, VariantParams) + grading.ts
(RubricScore + GradeRecord, criteria-typed) — field-for-field Python parity,
scores typed as the documented rubric-or-gate union.

11 endpoint tests green (distinct learners -> distinct statements at API level; cache
hit -> zero LLM calls); suite 324 green; typecheck 7/7; ruff clean.

---ci---
phase: 4
milestone: v0.3
status: execute
requirements: {covered: [REQ-3-005], partial: []}
---/ci---
2026-09-12 03:21:11 +00:00
CIAgent 85028678c7 feat(P03): assessment grade endpoint (Wave 3)
Task 3-3-01: POST /v1/assessment/grade (engine over DI; GRADED -> 200 full record;
UNGRADABLE_* gate outcomes -> 200 gate records with missing_seqs/integrity_flag —
never 5xx, they are valid results; persistent D-020 failure -> 502, nothing persisted)
+ GET /v1/assessment/grade/{learner}/{task} (404 unknown). GradeStore wired into
lifespan alongside TraceStore (single db_path, per-connection WAL). Unknown task POST ->
200 UNGRADABLE_EMPTY_TRACE (engine cannot distinguish absent from empty; gate record
persisted so POST->GET round-trips).

11 endpoint tests green; suite 283 green; ruff clean.

---ci---
phase: 3
milestone: v0.3
status: execute
requirements: {covered: [REQ-3-004], partial: []}
---/ci---
2026-09-12 02:34:47 +00:00
CIAgent b6850fc036 feat(P02): in-sandbox capture agent + websocket ingest (Wave 2)
Task 2-2-01: sandbox-agent.py stdlib-only (D-031) — shell capture (command/file_diff/
run_result/test_result/stdin/stdout), per-task monotonic seq, JSONL fsync spool (at-least-once,
D-026), raw-socket RFC6455 client (no websockets in-namespace), exponential-backoff reconnect,
SIGKILL-safe. Loopback tests: ordered emission, spool-on-disconnect, reconnect flush order,
stdlib-only AST scan.

Task 2-2-02: WS /v1/telemetry/ingest (D-026) — query-param identity (extra=forbid frames),
server-side dedup on (learner,task,seq), gap detection + warnings, ping keepalive. G-3 flood
control: overflow or >50000 events/task -> 1008 close + trace marked INCOMPLETE_FLOODED
(terminal, Proctor signal); no silent drop. GET traces + gaps endpoints. TraceIntegrityMap
(process-local, D-019 precedent) exposes is_incomplete for the Phase 3 grader gate (G-4).

214/214 + ruff clean.

---ci---
phase: 2
milestone: v0.3
status: execute
requirements: {covered: [REQ-3-003], partial: []}
---/ci---
2026-09-12 00:47:45 +00:00
CIAgent b01de4be7d feat(P01): sandboxes lifecycle API + G-5 abuse control (Wave 3)
Task 1-3-01: /v1/sandboxes endpoints (create/list/get/snapshot/delete) over the manager
singleton via DI; lifespan boots the startup orphan reaper (a-1) + destroys all on shutdown.
Abuse control (G-5): learner allowlist (403 unknown id), per-learner active cap (429),
global create-rate cap (429). CORS gains DELETE. 174 full-suite tests green; manual probe
POST /v1/sandboxes -> 201 verified live; ruff clean.

---ci---
phase: 1
milestone: v0.3
status: execute
requirements: {covered: [REQ-3-001, REQ-3-002], partial: []}
---/ci---
2026-09-12 00:47:45 +00:00
CIAgent 88a1dab810 docs(milestone): complete v0.2-ai-tutor-architecture
---ci---
phase: 7
milestone: v0.2
status: complete
requirements:
  covered: [REQ-2-001, REQ-2-002, REQ-2-003, REQ-2-004, REQ-2-005, REQ-2-006, REQ-2-007, REQ-2-008, REQ-2-009, REQ-2-010, REQ-2-011, REQ-2-012]
  partial: []
---/ci---

Milestone v0.2 (ai-tutor-architecture) merged to main.

Escalation record (audit remediation, durable): P1 executor
delegation failed twice (empty subagent results, zero files
created); auto-resolved at full autonomy to inline execution with
identical plan fidelity (commit 3271373, reflog-only after phase
branch squash-delete).
2026-09-11 17:34:50 +00:00