woogi/Conflict_Checker
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity
41 Commits 2 Branches 0 Tags
46db87115260f8eb10f0ce98b955c29f9dface46
Commit Graph
38 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
woogi 46db871152 docs: refresh pipeline overview + infographic for drawing-focus overhaul
Docker Release / build-and-push (push) Successful in 1m11s
Details
Docker Release / release (push) Skipped
Details 
- Specialists: Drawing Checker replaces Code Inspector as headline; code noted
  as off-by-default.
- Detectives now catch within-sheet contradictions.
- Add wave 6.5 Brain double-check step; mark shipped items in improvements.
- Regenerate infographic PNG.
 2026-08-20 15:13:26 -05:00
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
Details
Docker Release / release (push) Skipped
Details 
- 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 bae608a505 feat: deterministic sheet-list reconciliation (cover index vs identified sheets)
Docker Release / build-and-push (push) Successful in 1m19s
Details
Docker Release / release (push) Skipped
Details
2026-08-18 13:49:34 -05:00
woogi fe09e4a66b feat: coverage-driven extraction retry ladder (agent path)
Docker Release / build-and-push (push) Successful in 1m14s
Details
Docker Release / release (push) Skipped
Details
2026-08-18 13:38:30 -05:00
woogi 48fefa4007 feat: coverage ladder + vision-unverified stamping (classic path) 2026-08-18 13:35:21 -05:00
woogi 23f6d7fe89 feat: extraction coverage summary in report 2026-08-18 13:20:29 -05:00
woogi 06e108142e feat: deterministic text-layer coverage metric, merge, fallback + sheet-id recovery 2026-08-18 13:15:26 -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
Details
Docker Release / release (push) Skipped
Details 
- 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 349b357e5c docs: text-layer grounding design spec 2026-08-12 13:00:38 -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
Details
Docker Release / release (push) Skipped
Details
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 82952df307 fix: reasoning budget for conflict critic (wave-4 max_tokens truncation) 2026-08-10 11:29:03 -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 f21eb5d912 feat: config knobs and prompts for evidence verification wave 2026-08-10 11:14:27 -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 d431a026ce feat: treat disputed extracted values as unverified in constructability and critic prompts 2026-08-10 10:56:53 -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 0ea0b0e897 Add non-technical pipeline overview: infographic + flow explainer doc
Docker Release / build-and-push (push) Successful in 59s
Details
Docker Release / release (push) Skipped
Details
2026-08-10 08:21:57 -05:00
woogi 228e8bd031 Sync .env.example with new extract token defaults
Docker Release / build-and-push (push) Successful in 57s
Details
Docker Release / release (push) Skipped
Details
2026-08-09 08:21:31 -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
Details
Docker Release / release (push) Skipped
Details 
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
Details
Docker Release / release (push) Skipped
Details 
- 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
woogi 5c1fccfb35 Guard syncPipelineOptions when hybrid radio is removed.
Docker Release / build-and-push (push) Successful in 55s
Details
Docker Release / release (push) Skipped
Details
2026-08-05 16:07:34 -05:00
woogi 32544bc2af Add /models fetch timeout and health-derived default fallback for model dropdowns.
Docker Release / build-and-push (push) Successful in 57s
Details
Docker Release / release (push) Skipped
Details
2026-08-05 15:59:50 -05:00
woogi 4b3b62b3fa Add cache-busting meta tags and default build tag text.
Docker Release / build-and-push (push) Successful in 56s
Details
Docker Release / release (push) Skipped
Details
2026-08-05 15:50:35 -05:00
woogi 5305325d81 Fix model dropdown loading, cache models for 24h, and style build tag.
Docker Release / release (push) Skipped
Details
Docker Release / build-and-push (push) Successful in 1m1s
Details
2026-08-05 15:42:21 -05:00
woogi 6f10062b93 Agent-mode UI: remove hybrid compute option, add clickable sheet links in review queue.
Docker Release / build-and-push (push) Successful in 1m1s
Details
Docker Release / release (push) Skipped
Details
2026-08-05 15:28:09 -05:00
woogi 7488cf68c5 Verbose per-call LLM logging, raw request/response dumps, and end-of-log cost summary.
Docker Release / build-and-push (push) Successful in 1m13s
Details
Docker Release / release (push) Skipped
Details 
- [LLM] line per call: stage, model, prompt size, output size, cost, parsed item counts
- LLM_RAW_DUMP: full prompt/response JSON per call under outputs/<job>/llm_raw/
- Cost block at tail of job.log (per-stage, per-model, cached vs live)
- Agent mode: reset llm cost counters per job; review finalization now teed into job.log + dumps
 2026-08-05 15:17:17 -05:00
woogi f7e1b6bb7c Merge main: dual model dropdowns + richer job logs, adapted for agent-mode.
Docker Release / build-and-push (push) Successful in 1m0s
Details
Docker Release / release (push) Skipped
Details 
- llm.py: set_model_overrides(vision, text) replaces the single job override;
  UI picks still beat per-call agent model args, but never name the hybrid
  local model (avoids main's hybrid footgun); local->cloud fallback uses the
  text pick.
- jobs.py: timestamped line-split tee (job_log.py), in-memory log + log_tail
  polls, full log on terminal states (done/error/needs_review/finalization_error),
  log-only disk recovery, error email links to the run log, and failed runs now
  append the full traceback to job.log. Keeps pipeline_mode, job.json, and the
  review gate.
- models.py: vision/text split via architecture modalities, pricing kept;
  /models returns {vision, text, defaults}; /check takes vision_model/text_model
  (replacing model); /health adds text_model. models_catalog.py dropped.
- UI: two priced dropdowns (OpenRouter compute only) + live run-log panel.
- Tests updated for dual overrides and the /models shape; new coverage for
  traceback capture and local-model immunity.
 2026-08-02 09:55:09 -05:00
woogiandCursor bf508bfdf6 Expand session notes with API, job log, and model selection details.
Docker Release / build-and-push (push) Successful in 57s
Details
Docker Release / release (push) Skipped
Details 
Keep NOTES.md current for new sessions after the job-log and dual-model UI work.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-31 20:21:35 -05:00
woogiandCursor a6b0c8fdfa Add per-job run logs and separate vision/text model selection.
Docker Release / build-and-push (push) Successful in 1m27s
Details
Docker Release / release (push) Skipped
Details 
Capture pipeline stdout into job.log + API/UI so failed runs can be reviewed, and let users pick OpenRouter vision vs text models independently.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-31 14:56:48 -05:00
woogiandCursor ac328d34fd Build agent-mode branch image in CI under a branch tag.
Docker Release / build-and-push (push) Successful in 3m38s
Details
Docker Release / release (push) Has been skipped
Details 
Publish agent-mode pushes as :agent-mode (and :sha-<commit>) so the experimental fork is available from the registry without overwriting the Classic :latest image.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-18 14:42:13 +00:00
woogiandCursor 82a48d99cf Add scoped Agent-mode pipeline as experimental Classic fork. 
Wire specialist waves, Brain consolidation, and Classic-compatible reports so Agent mode can run end-to-end via OpenRouter without changing the default Classic path.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-18 14:31:13 +00:00
woogiandCursor e30522af9a Fix CI workflow to use github context variables.
Docker Release / build-and-push (push) Successful in 1m17s
Details
Docker Release / release (push) Has been skipped
Details 
The ChristopherHX runner only supports github.* expressions, not gitea.*.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-03 01:22:26 +00:00
woogiandCursor f85b2a1276 Add Docker packaging and Gitea Actions CI/CD pipeline.
Docker Release / build-and-push (push) Failing after 11s
Details
Docker Release / release (push) Has been skipped
Details 
Containerize the app for local and production deploys, and publish images
to the Gitea container registry on main pushes and version tags.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-03 01:09:52 +00:00
woogiandClaude Opus 4.8 1d248a8808 Initial commit: Conflict Checker 
Cross-discipline design-contradiction checker for construction drawing
sets. Standalone tool broken out from Iron_Bid; a pipeline stage may
later fold back into Iron_Bid.

Pipeline: PDF->images -> per-sheet assertion extraction -> deterministic
clustering by location -> per-cluster reasoning -> report.
Includes CLI (cli/run_check.py) and web UI (backend/main.py).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-07-03 00:22:02 +00:00