woogi
d37ac8c1c7
- ENABLE_CODE_REVIEW flag (default off): skips code/ADA/jurisdiction review path in both pipelines; nothing deleted, one env flag to restore. - Per-sheet Drawing Integrity QA wave (agent + classic, default on): dangling refs, on-sheet contradictions, dimension sanity, missing sheet essentials, tag hygiene. New DrawingIntegrityAgent + classic stage. - Broadened conflict critic: intra-sheet + same-discipline contradictions, not just cross-discipline. - Wave 6.5 Brain-directed clarification (bounded hub-and-spoke): Brain names uncertain findings, verify_evidence requests route through the wave-5b verifier; refuted findings suppressed. One planning call + capped verifies, single iteration. Shared _build_verify_scopes across 5b and 6.5. - Config knobs, .env.example, frontend copy, tests (182 passing).
61 lines
2.9 KiB
Markdown
61 lines
2.9 KiB
Markdown
# Plan: Brain-directed clarification pass (bounded hub-and-spoke)
|
|
|
|
Date: 2026-08-20
|
|
Branch: agent-mode
|
|
|
|
## Goal
|
|
Let the Brain actively chase weak/ambiguous findings instead of only judging
|
|
the finished pile once. Bounded, traceable, reuses the wave-5b verifier as the
|
|
"answer" channel. NOT a free agentic loop.
|
|
|
|
## Shape (agent pipeline)
|
|
Insert **wave 6.5: Brain-directed clarification** between the wave-6 Brain merge
|
|
and the review-gate / wave-7 branches, so BOTH paths benefit.
|
|
|
|
1. `BrainAgent.plan_clarifications(prioritized)` — one focused LLM call. Brain
|
|
names findings it is unsure about and emits TYPED requests:
|
|
`{issue_id, request_type, reason}`. v1 executes only `verify_evidence`;
|
|
the router accepts other types but logs them as "planned, not executed"
|
|
(extensible without a rewrite). Capped at `BRAIN_CLARIFY_MAX_REQUESTS`.
|
|
Brain is told which findings already carry `verification` (from 5b) so it
|
|
does not re-request them.
|
|
2. Route `verify_evidence` requests → build verify scopes for exactly those
|
|
findings (reuse the SAME scope builder as wave 5b: fresh page images +
|
|
hi-DPI evidence crops + text-layer oracle) → `EvidenceVerifierAgent` →
|
|
`apply_verdicts(prioritized, ...)`. Refuted findings are annotated,
|
|
demoted, removed from `prioritized`, and pushed into `memory["suppressed"]`
|
|
(existing key — no memory-registry crash). Clarify decisions recorded in
|
|
`memory["decisions"]`.
|
|
3. No second full Brain merge: Brain ASKED (step 1) and the verifier ANSWERED
|
|
(step 2); the answer prunes/annotates the list. This keeps issue_ids stable
|
|
for the review queue and adds at most 1 + N calls. One iteration only.
|
|
|
|
## Bounds / knobs (config.py, all env-overridable)
|
|
- `ENABLE_BRAIN_CLARIFY` (_flag, default true)
|
|
- `BRAIN_CLARIFY_MAX_REQUESTS` (default 8)
|
|
- reuse `AGENT_VERIFY_CONCURRENCY`, `VERIFY_MAX_TOKENS`,
|
|
`AGENT_VERIFY_REASONING_EFFORT`, `AGENT_CONFLICT_MAX_IMAGES`,
|
|
`VERIFY_HI_DPI_CROPS`.
|
|
|
|
## Reuse / refactor
|
|
- Extract the inline wave-5b verify-scope construction into
|
|
`_build_verify_scopes(findings, targets, sheet_to_page, page_to_b64,
|
|
page_to_text, page_words, pdf_path, prefix)` so wave 5b and wave 6.5 share
|
|
it. Preserve wave-5b behavior exactly (its tests guard this).
|
|
|
|
## Classic pipeline
|
|
Out of scope for v1 — the verifier/crops live only in the agent path. Classic
|
|
keeps its single dedup_validate. Documented as agent-only.
|
|
|
|
## Tests
|
|
- `plan_clarifications` parses/caps/skips-already-verified (stub call_json).
|
|
- Router executes verify_evidence, ignores unknown types.
|
|
- Runner smoke: a low-confidence finding Brain flags gets refuted → moves to
|
|
suppressed_issues; stub verifier.call_json (no live calls).
|
|
|
|
## Pitfalls to respect
|
|
- ProjectMemory keys are a closed registry — only use existing `suppressed` /
|
|
`decisions`. (Skill defect C1.)
|
|
- Stub `backend.agents.verifier.call_json` in runner tests or it hits the net.
|
|
- Extractor stub sheets need >= 2 assertions or no clusters form.
|