Read-only Q&A on the review screen, per finding and per run, answered from
the job's own artifacts (evidence, cluster, extraction, verification, Brain
merge, sheet index, cover reconciliation, job.log). It never mutates findings,
decisions, or the report.
Turns are logged job-locally (review/chat_log.jsonl, transcript at
/jobs/{id}/review-chat/log) and to a cross-job feedback store
(REVIEW_FEEDBACK_DIR), which now also receives review decisions with their
category/severity corrections.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0115gGtrSxXE9DKvS9XPFSoT
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
- [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
- 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.
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>
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>
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>
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>
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>
woogiandClaude Opus 5