woogi
d37ac8c1c7
feat: refocus on drawings — code/ADA gated off, drawing-integrity wave, Brain-directed clarification
...
Docker Release / build-and-push (push) Successful in 1m8s
Docker Release / release (push) Skipped
- 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).
2026-08-20 15:10:32 -05:00
woogi
fe09e4a66b
feat: coverage-driven extraction retry ladder (agent path)
Docker Release / build-and-push (push) Successful in 1m14s
Docker Release / release (push) Skipped
2026-08-18 13:38:30 -05:00
woogi
0d109fb5cd
feat: text-only structuring prompt for extraction retry ladder
2026-08-18 13:15:16 -05:00
woogi
570300324f
feat: text-layer grounding (extractor authority, guard rescue tier, verifier oracle + hi-DPI crops)
...
Docker Release / build-and-push (push) Successful in 1m25s
Docker Release / release (push) Skipped
- backend/text_layer.py: PyMuPDF text-layer extraction, fuzzy evidence
bbox matching, 300-DPI crop rendering, coverage-gap signal
- extractor (classic + agent): TEXT LAYER block appended at call sites;
grounding guard gains text-layer rescue tier (grounding=text_layer stamp)
- verifier: {text_layer} oracle excerpt + evidence-located hi-DPI crops
replacing full-page images (fallback preserved, I2 guard intact)
- coverage gaps: text-bearing pages with zero extraction -> failed-scope
gap findings (agent) / log-only (classic)
- config knobs: TEXT_LAYER_ENABLED/MIN_CHARS/MAX_CHARS, VERIFY_TEXT_MAX_CHARS,
VERIFY_HI_DPI_CROPS, VERIFY_CROP_DPI, VERIFY_CROP_MARGIN_PTS
- tests: 22 new (text_layer unit, grounding/render, runner-level flow)
Spec: docs/superpowers/specs/2026-08-12-text-layer-grounding-design.md
2026-08-12 14:27:00 -05:00
woogi
b174b531cd
fix: wave 5b review blockers - suppressed memory key, finalizer merge, zero-image guard
Docker Release / build-and-push (push) Successful in 59s
Docker Release / release (push) Skipped
2026-08-10 12:21:41 -05:00
woogi
3df359500c
feat: wave 5b evidence verification - vision fact-check of cited sheet text
2026-08-10 11:30:28 -05:00
woogi
c8af430143
fix: xref member-mark regex covers single-letter marks; recheck sheet diversity after cap
2026-08-10 11:23:06 -05:00
woogi
4a3f33a245
feat: cross-level xref link scopes via detail_reference and member tag
2026-08-10 11:10:43 -05:00
woogi
15297038a2
fix: annotate clusters and substitute {disputes} in classic pipeline path
2026-08-10 11:06:15 -05:00
woogi
8631a26006
feat: surface disputed extracted values to critic and specialist prompts
2026-08-10 10:47:34 -05:00
woogi
df4d15fd0c
feat: deterministic disputed-value detection for cluster assertions
2026-08-10 10:40:10 -05:00
woogi
3d7fce7bf9
Kill extract-wave truncation: 65k ceiling, hard thinking budget, reasoning-token telemetry
...
Docker Release / build-and-push (push) Successful in 57s
Docker Release / release (push) Skipped
Job 98194fa8d215 showed every extract call hitting the 32k cap with only
~20k chars visible despite reasoning effort=low - Gemini 2.5 Pro still
burned ~25k thinking tokens per sheet.
- EXTRACT_MAX_TOKENS default 32768 -> 65536 (model output ceiling)
- new EXTRACT_REASONING_MAX_TOKENS (default 2048): OpenRouter reasoning
max_tokens / Gemini thinking_budget; takes precedence over effort
- log per-call reasoning token counts (usage.completion_tokens_details)
and include thinking count in the finish_reason=length marker
2026-08-09 08:17:41 -05:00
woogi
76e0a52658
Fix sheet-extraction page loss: bare-list wrap, compact retry, reasoning cap
...
Docker Release / build-and-push (push) Successful in 1m1s
Docker Release / release (push) Skipped
- SheetExtractorAgent accepts top-level array responses as the objects
array instead of discarding them (recovered the failure mode behind
16/38 failed sheets on job 475a6f184dd1)
- Second-chance compact retry per page before declaring extraction failed
- call_json: reasoning_effort param (cloud-only extra_body), finish_reason
capture + explicit max_tokens log line, finish_reason in raw dumps,
cache key covers reasoning_effort
- EXTRACT_MAX_TOKENS default 16384 -> 32768 (Gemini thinking tokens count
against the cap); new EXTRACT_REASONING_EFFORT=low default for extract
- tests: 5 new fallback-ladder tests
2026-08-07 07:35:53 -05:00
John Wilganowski
1c1d2ff21b
Add required human review gate to the Agent pipeline.
...
Docker Release / build-and-push (push) Successful in 1m10s
Docker Release / release (push) Skipped
Agent web jobs now stop after Brain consolidation and enter needs_review
with a persisted review queue (blocking: high-severity, low-confidence,
sensitive-category findings; audit sample of clean clusters). Humans
decide confirm/reject/unsure/needs_clarification via new review API and
frontend queue; a finalizer applies decisions (rejections suppressed with
reason codes), performs bounded targeted reruns for clarifications,
drafts RFIs only for kept issues, and only then marks the job done and
sends the final email. Two-phase email (review-required, then final
report), per-decision feedback labels with redacted aggregate metrics,
restart recovery from job artifacts, and CLI --no-review bypass.
Classic pipeline unchanged. 65 non-LLM tests.
2026-07-28 19:23:57 +00:00
woogi
John Wilganowski