coreci/nextcraft
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 24 Wiki Activity

docs(P00): clarify v0.3 ambiguities — auto-resolved (full autonomy)

Browse Source 
A-101 bwrap user-namespace sandbox isolation; A-102 coding-IDE-only scope (design/sim deferred);
A-103 xterm.js+WebSocket build UX; A-104 WebSocket+SQLite telemetry transport; A-105 SQLite trace store;
A-106 LLM trace grader w/ code-computed deterministic features; A-107 seeded LLM variant generation;
A-108 provider-agnostic mock-first voice (STT/TTS); A-109 Examiner agent reuses BaseAgent+SSE;
A-110 KYC/age-gating deferred per founder directive; A-111 extend ai-service (no new apps);
A-112 single-box 1-5 concurrent sandbox capacity target.

All resolutions confidence >= 0.60.

---ci---
phase: 0
milestone: v0.3
status: clarify
---/ci---
This commit is contained in:
CIAgent
2026-09-11 17:45:20 +00:00
parent 01286a02cb
commit da9320bf4e
1 changed files with 18 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.ciagent/PROJECT.md
+18 -1
View File
@@ -40,7 +40,24 @@ All 12 v0.2 requirements (REQ-2-001..012) are complete and shipped as v0.2.0. Se
All 28 v0.1 requirements (REQ-001..028) are complete and shipped as v0.1.0. See REQUIREMENTS.md traceability matrix.
## Clarified Assumptions (CLARIFY stage, full autonomy — auto-resolved)
## Clarified Assumptions (v0.3 CLARIFY stage, full autonomy — auto-resolved)
| # | Ambiguity | Resolution | Confidence |
|---|-----------|------------|-------------|
| A-101 | Sandbox isolation technology? | **Bubblewrap (bwrap) user-namespace subprocess isolation** per sandbox. No Docker-in-Docker, no VMs, no Firecracker. bwrap is setuid, preinstalled on the Gitea/Debian box, gives filesystem+PID+network namespaces with zero daemon. Solo-founder-appropriate. A `SandboxBackend` protocol keeps a future containerd swap possible. | 0.78 |
| A-102 | Sandbox scope in v0.3? | **Coding IDE only** (web terminal + file tree + run/test). The "design tool" and "simulation" environments specified in REQ-F-021 are deferred to v0.4 — a single real build environment is enough to prove the credential pipeline end-to-end (telemetry → trace → grade → defense). | 0.75 |
| A-103 | Live in-browser build UX? | **WebSocket xterm.js terminal** attached to the bwrap sandbox shell + HTTP file-tree/CRUD + run/test buttons. No full Monaco LSP in v0.3 — a code editor with syntax highlight (existing) + real shell is sufficient and far cheaper. | 0.72 |
| A-104 | Telemetry transport? | **WebSocket** from sandbox to a new ingestion endpoint on ai-service for live events; **SQLite-backed** ordered event log (`ai_service/telemetry/`) gives durability + at-least-once delivery + replay. Events carry monotonic `seq` per (learner,task) so gaps are detectable. | 0.8 |
| A-105 | Where do traces live? | **SQLite** (`ai_service` data dir), introducing the first real persistence. SQLModel/SQLAlchemy for typed access. Chosen over Postgres because solo-founder + single box + low write volume; the `TraceStore` protocol is Postgres-migration-ready like SessionStore was. | 0.75 |
| A-106 | Process-trace grading model? | **LLM-based grader**: structure the trace into a compact timeline digest (command categories, error/fix cycles, idle gaps, test passes) → Assessor-style rubric prompt → structured score via existing D-020 JSON defense. Deterministic features (test pass/fail, edit count) computed in code, not left to the LLM. | 0.7 |
| A-107 | Variant generation mechanism? | **Parameterized task templates + LLM instantiation**, seeded per learner. Generator fills typed parameter slots (scenario, constraints, data) from a template library; variant seed + parameters persisted to SQLite for grading fairness and proctoring cross-check. Difficulty normalized by template-level rubric anchors. | 0.72 |
| A-108 | Voice defense — STT/TTS providers? | **Provider-agnostic, mock-first like the LLM layer (D-014).** Real path: browser `MediaRecorder` → audio to ai-service → **OpenAI-compatible `/audio/transcriptions`** (Whisper STT) and **`/audio/speech`** (TTS) against ollama-cloud or a compatible endpoint; fallbacks: browser `SpeechRecognition`/`speechSynthesis` when no server keys. `VoiceProvider` protocol + deterministic mock (returns canned transcript) so tests never call a voice API. | 0.62 |
| A-109 | Defense dialogue shape? | Reuse BaseAgent: an `Examiner` agent (seventh agent) streams examiner questions over the existing SSE pipeline; integrity signals (long pauses, off-scope answers, reading-from-notes cadence) emitted alongside the transcript to Proctor. | 0.8 |
| A-110 | KYC / age-gating in v0.3? | **Deferred per founder directive.** No real identity backend. Age-gating stays the v0.1 visual flow mockup. Personas omit a security-engineer; security review via verifier + Phase 7 secrets-hygiene checklist. | 0.98 |
| A-111 | New services vs extend ai-service? | **Extend ai-service**, don't fork new Python apps. Telemetry ingestion, trace grading, variant generation, voice, and sandbox orchestration all live as new modules in `apps/ai-service` (they share the LLM provider pool + config + session infra). Only the in-sandbox capture agent is a separate tiny Python process shipped into the bwrap environment. | 0.82 |
| A-112 | Sandbox on a single dev/school box — capacity? | v0.3 targets **1–5 concurrent sandboxes** (founder + pilot learners). No horizontal scaling, no queue. Concurrency guard returns 503 when full. Scaling is post-MVP. | 0.8 |
## Clarified Assumptions (v0.2 CLARIFY stage, full autonomy — auto-resolved)
| # | Ambiguity | Resolution | Confidence |
|---|-----------|------------|-------------|