docs(fase2): /trekplan — adversarial-reviewed implementation plan [skip-docs]
14-step plan composing the four Fase 1 spikes into a src/ vertical slice (debate -> blocking validator -> two-layer HITL + provenance -> ExpeL learning), deterministic-core-first, on real chat clients in both profiles. Grounded in the 3 research briefs + installed-1.9.0-source introspection (7 exploration agents). Adversarial review: plan-critic REVISE (3 blockers/7 major/4 minor) -> all addressed; scope-guardian ALIGNED (0 creep, 9/9 criteria mapped, 6/6 Non-Goals honored). Key revisions: in-process retriever-as-tool MVP path (mcp dep conditional/GA-only); two-layer HITL capture + stable Verdict.id minting; extend_instructions retired by a REAL SessionContext test; TextSpan ownership + wave re-ordering; budget None-as-hard-fail with synthetic-usage test double; self_repair token-bound in the generate loop (validator.py frozen); global stop-on-failure rule. gemini-bridge Pass 2 unavailable (MCP SDK broke). plan-validator strict 0 errors. brief research_status pending to complete. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Fif1r1En5W542HbZV88yMH
This commit is contained in:
parent
c72730941e
commit
9973d9fe58
2 changed files with 687 additions and 1 deletions
|
|
@ -6,7 +6,7 @@ task: "Fase 2 MVP vertical slice — one synthetic project end-to-end on MAF 1.9
|
|||
slug: fase2-mvp-vertical-slice
|
||||
project_dir: .claude/projects/2026-06-24-fase2-mvp-vertical-slice/
|
||||
research_topics: 3
|
||||
research_status: pending
|
||||
research_status: complete
|
||||
auto_research: false
|
||||
interview_turns: 0
|
||||
source: interview
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue