Ganymede review nit: if get_pr_diff returns an empty string (edge case —
Forgejo quirk, empty PR), the old `if diff is None` branch would miss it,
the `elif diff and ...` would evaluate False (empty string is falsy), and
control would fall to `else` — triggering auto-close on zero diff content.
Change `if diff is None` → `if not diff` so empty string ALSO falls through
to the conservative path. Matches the stated posture: skip auto-close when
in doubt.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Prevents Apr 22 runaway-damage pattern (44 open PRs manually bulk-closed)
where a source extracted 20+ times before the cooldown gate landed, each
leaving an orphan 'open' PR after eval correctly rejected as near-duplicate.
Gate fires in dispose_rejected_pr before attempt-count branches:
all_issues == ["near_duplicate"] (exact match — compound carries signal)
AND sibling PR exists with same source_path in status='merged'
AND diff contains "new file mode" (not enrichment-only)
→ close on Forgejo + DB with audit, post explanation comment.
Ganymede review — 5 must-fix/warnings applied + 1 must-add:
- Exact match on single-issue near_duplicate (compound rejections preserved)
- Enrichment guard via diff scan (eval_parse regex can flag enrichment prose)
- 10s timeout on get_pr_diff — conservative fallback on Forgejo wedge
- Forgejo comment with canned explanation (best-effort, try/except)
- Partial index idx_prs_source_path + migration v23
- Explicit p1.source_path IS NOT NULL in WHERE
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three targeted fixes from Ganymede's review of commit 469cb7f:
BUG #1 — Success path now updates sources.status='extracting' before PR
creation, so queue scan's DB-authoritative filter catches sources between
PR creation and merge. Previously the cooldown gate was load-bearing for
this window, not belt-and-suspenders as claimed.
BUG #2 — Second null-result path (line 573, triggered when enrichments
existed but all targets were missing in worktree) now updates DB. Without
this, that path created no PR, no DB mark, and would have re-entered the
runaway loop 4h later when the cooldown window expired.
NIT #6 — 4h cooldown moved to config.EXTRACTION_COOLDOWN_HOURS. Tunable
without code change. Log format now shows the configured hours.
Also backfilled 59 pre-existing zombie queue-path rows where the file
was already archived but DB status said 'unprocessed' — these would have
leaked past the DB filter once the 4h cooldown expired.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three changes reduce extraction cost and duplicate PR flood:
1. 4-hour cooldown gate — skip sources with ANY PR (merged/closed/open)
created in the last 4h. Prevents same source re-extracting every 60s
while archive step lags behind merge.
2. DB-authoritative status — sources.status is now updated in the pipeline DB
at each extraction terminal point (null_result, success). Queue scan checks
DB first so sources with failed archives (e.g., root-owned worktree files
blocking git pull --rebase) don't get re-extracted forever. Also moves
archival into the extraction branch so it goes through PR merge instead
of a fragile separate main-worktree push.
3. source_channel wiring — extract.py PR INSERT now sets source_channel from
classify_source_channel(branch). Previously daemon-created PRs had NULL
source_channel, breaking Argus dashboard filters. Combined with Ship's
in-branch archive refactor.
Root incident: blockworks-metadao-strategic-reset.md extracted 31 times in
12 hours. Nine other sources hit 10-22 extractions each. Near-duplicate
rejection rate jumped to 94%.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Forward link: claims get `sourced_from: {domain}/{filename}` at extraction time.
Reverse link: after merge, backlink_source_claims() updates source files with
`claims_extracted:` list. All disk writes happen under async_main_worktree_lock.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
config.py had extractor-heavy weights (0.40) from initial bootstrap.
Correct weights per approved architecture: challenger 0.35, synthesizer
0.25, reviewer 0.20, sourcer 0.15, extractor 0.05. backfill-ci.py
already had correct weights; this fixes the live computation in health.py.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The contributor attribution always recorded "extractor" regardless of
the PR's refined commit_type. Added COMMIT_TYPE_TO_ROLE mapping and
applied it in all three attribution paths (Pentagon-Agent trailer,
git author fallback, PR agent fallback).
Backfill script resets and re-derives role counts from prs.commit_type.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When a contributor merges main into their fork branch (standard GitHub
workflow), merge-base equals main SHA, triggering the 'already up to
date' early return. This closes the PR without cherry-picking the new
content. Cameron's PR #3377 hit this exact bug.
Fix: add a diff check before returning 'already up to date'. If the
branch has actual content changes vs main, proceed to cherry-pick
instead of short-circuiting.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
rejection_reason was always NULL in review_records — now populated with
comma-joined issue tags (near_duplicate, frontmatter_schema, etc.) at both
rejection call sites. Also fixes stale reviewer_model="gpt-4o" hardcoding
to use config.EVAL_DOMAIN_MODEL (currently Gemini Flash).
Ingestion branches (ingestion/futardio-*, ingestion/metadao-*) now resolve
to internet-finance domain instead of falling through to "general".
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Near-duplicate (159+ rejections):
- Add extract-time dedup gate: SequenceMatcher check before file write ($0)
- Strengthen extraction prompt: high-similarity matches (>=0.75) get explicit
"DO NOT extract, use enrichment instead" warning
- Strip [[wiki link]] brackets from related_claims field
Frontmatter schema (129+ rejections):
- Normalize LLM confidence aliases (high→likely, medium→experimental, etc.)
in both _build_claim_content and validate_schema
- Strip code fences (```markdown/```yaml) from entity content in extract.py
and from diff content in validate.py tier0.5 check
- Code fences were root cause of "no_frontmatter" failures: parser sees
```markdown as first line, not ---
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
A transient DB lock in breaker.record_failure() inside an except handler
killed the asyncio coroutine permanently — snapshot_cycle died Apr 18 and
never recovered. All three breaker call sites now have their own try/except.
Also includes HTML injection fix for github_feedback review_text.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Root cause of 84% reweave PR rejection rate: claim titles with colons
(e.g., "COAL: Meta-PoW: The ORE Treasury Protocol") written as bare
YAML list items, causing yaml.safe_load to fail during merge.
Three changes:
1. frontmatter.py: _yaml_quote() wraps colon-containing values in double quotes
2. reweave.py: _write_edge_regex uses _yaml_quote for new edges
3. merge.py: skip individual files with parse failures instead of aborting entire PR
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Ganymede review findings:
1. source_channel was missing from CREATE TABLE (fresh installs wouldn't have it)
2. Default fallback changed from 'telegram' to 'unknown' — unknown prefixes
are genuinely unknown, not telegram
3. Cross-reference comments added between BRANCH_PREFIX_MAP and _CHANNEL_MAP
Also wires classify_source_channel into merge.py PR discovery INSERT.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
github_feedback.py posts pipeline status to GitHub PRs at three touchpoints:
discovery ack, eval review result, and merge/close outcome. Only fires for
PRs with a github_pr link (set by sync-mirror.sh). All calls non-fatal.
contributor.py: expanded git author fallback to scan all non-merge commits
(was only checking last commit), added teleo-bot and github-actions[bot]
to bot filter list.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Enables GitHub↔Forgejo PR linking for the contributor pipeline.
Mirror script will store GitHub PR number when creating Forgejo PRs,
allowing back-sync of eval feedback and merge/close status.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
External contributors who run `git merge main` create merge commits that
cherry-pick can't handle without -m flag. --no-merges filters these out.
Added detection for branches with only merge commits but real content diff.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two changes to address the #1 rejection reason:
1. extraction_prompt.py: Explicitly tell LLM NOT to use [[wiki links]]
in body text — use connections/related_claims JSON fields instead.
Remove misleading "post-processor handles wiki links" language.
2. extract.py _get_kb_index(): Expand KB index to include entity stems
from entities/{domain}/ so the LLM knows what entities exist when
building connections. Previously only showed domain claims.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Both the "already merged" path and _handle_permanent_conflicts closed PRs on
Forgejo without checking the return value. On API failure, the DB update would
proceed anyway, creating ghost PRs (DB=closed/merged, Forgejo=open). Now both
paths check for None return and skip DB updates on failure — same pattern as
close_pr in pr_state.py.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
There were TWO `if not unprocessed: return 0, 0` gates. The previous
fix (c763c99) only addressed the second one. The first at line 746
fires before the re-extraction query even runs. Replace with a comment
explaining why we don't early-return there.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The re-extraction check was below an early return that fires when
unprocessed queue is empty. Sources in needs_reextraction state were
never picked up unless new sources happened to arrive simultaneously.
Move re-extraction query above the gate so both paths run independently.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Path(target).name strips directory components from LLM-generated
target filenames, preventing path traversal via ../. Same pattern
already applied to claim filenames (line 404) and entity filenames
(line 416). Ganymede-approved.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three changes:
1. Drop underscore prefixes in eval_parse.py — functions are now the public
API of the module (filter_diff, parse_verdict, classify_issues, etc.).
All 12 functions renamed, imports updated in evaluate.py and tests.
2. Extract eval_actions.py from evaluate.py — 3 async PR disposition functions:
- post_formal_approvals: submit Forgejo reviews from 2 agents
- terminate_pr: close PR, post rejection comment, requeue source
- dispose_rejected_pr: disposition logic for rejected PRs on attempt 2+
evaluate.py drops from ~1140 to 911 lines.
3. 14 new tests in test_eval_actions.py covering all three functions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Critical bug fix: close_pr now checks forgejo_api return value and
skips DB update on Forgejo failure, preventing ghost PRs (DB closed,
Forgejo open). Returns bool so callers can handle failures.
_terminate_pr checks return value — skips source requeue on failure.
stale_pr.py migrated from raw Forgejo+DB to close_pr (last raw close
transition eliminated).
eval_parse.py: 15 pure parsing functions extracted from evaluate.py
(~370 lines removed). Zero I/O, zero async, independently testable.
evaluate.py drops from ~1510 to ~1140 lines.
Tests: 295 passed (42 new eval_parse + 2 new close_pr), zero regressions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three fixes for conversation-sourced claim quality:
1. Trust hierarchy in extraction prompt: bot-generated numbers are
flagged as unverified context, not evidence. Directional claims
are extractable but specific figures require external verification.
Prevents laundering bot guesses into the KB as evidence.
2. Conversation-sourced claims tagged with verified: false and
source_type: conversation in frontmatter. Downstream consumers
(Leo, dashboard) can filter/flag these for verification.
3. GET /api/telegram-extractions endpoint for daily spot-checking.
Shows recent Telegram-sourced PRs with claim titles, status,
merge rate, and eval issues. Quick review surface.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fix 4 Forgejo ghost PR bugs flagged by Ganymede:
- fixer.py GC close: DB update ran outside try/except, closing DB even on Forgejo failure
- substantive_fixer.py droppable: NO Forgejo close at all
- substantive_fixer.py auto-enrichment: DB update before Forgejo (reversed order)
- substantive_fixer.py close_and_reextract: replace manual Forgejo+DB with close_pr()
Add start_fixing() and reset_for_reeval() to pr_state.py:
- start_fixing: atomic claim + fix_attempts increment in one statement
- reset_for_reeval: clears all eval state for re-evaluation after fix
Also fixes stale line number comment in merge.py (Ganymede nit).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two changes:
1. extract.py: Enrichments now modify existing claim files by appending
evidence sections. Previously enrichment-only extractions were
discarded as null-result even when they contained valuable challenges.
2. extraction_prompt.py: Corrections should produce BOTH a claim (the
corrected knowledge) AND an enrichment (linking to what it corrects).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace 38 hand-crafted UPDATE prs SET status calls across evaluate.py
and merge.py with 7 centralized functions that enforce invariants:
- close_pr: always syncs Forgejo (opt-out for reconciliation)
- approve_pr: raises ValueError on empty domain (prevents NULL bugs)
- mark_merged: always sets merged_at, clears last_error
- mark_conflict: always increments merge_failures, sets merge_cycled
- mark_conflict_permanent: terminal conflict state
- reopen_pr: handles all reopen scenarios (transient, rejection, reeval)
- start_review: atomic claim with bool return
This eliminates the class of bugs that produced 3 incidents:
1. Domain NULL on musings bypass (7 PRs stuck, 20h zero throughput)
2. Forgejo ghost PRs (70 PRs open on Forgejo but closed in DB)
3. Merge_cycled missing on various close paths
Also fixes: 3 close paths in merge.py had DB update before Forgejo call
(reversed order). close_pr does Forgejo first, then DB.
Only remaining raw status transition: _claim_next_pr (approved→merging)
which is an atomic subquery and doesn't have invariant requirements.
20 new tests, 264 total passing, 0 regressions. Net -101 lines in
evaluate.py + merge.py.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When source format is "conversation", inject specialized extraction
rules that prioritize human corrections/pushback as highest-value
content. Fixes null-result on short but high-signal correction
messages. Maps corrections to existing KB claims as challenges.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
db.py: migration v20 adds conflict_rebase_attempts, merge_failures,
merge_cycled columns (already exist on VPS via manual migration, missing
from code — any future DB rebuild would break retry mechanism).
merge.py: replace retry-with-backoff on config.lock with asyncio.Lock
(_bare_repo_lock) around all worktree add/remove calls. Prevents
contention instead of retrying it. Applied to both _cherry_pick_onto_main
and _merge_reweave_pr.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two code paths set status='closed' in the pipeline DB without calling
the Forgejo API to close the PR. This caused 50 ghost PRs to accumulate
on Forgejo (dashboard shows review backlog) while the pipeline considered
them done.
- evaluate.py: no-diff stale branch close now calls Forgejo PATCH
- merge.py: permanent conflict close now calls Forgejo PATCH
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Parallel domain merges race on the bare repo's config file. The single
retry only covered one of two worktree-add call sites and used fixed
delay. Now both sites retry up to 3 times with increasing jitter.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Ganymede review nit: substring match on "already" could false-positive
on future return strings. Pin to the two known values from cherry_pick().
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Musings bypass and batch both_approve set status='approved' without
domain or auto_merge. Merge gate requires domain IS NOT NULL and
prefix match OR auto_merge=1. Result: agent PRs deadlocked for 20+ hours.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two fixes for the 18-PR merge blockage:
1. When cherry-pick returns "already merged" (all commits empty because
content is already on main), close the PR directly instead of trying
to push the stale branch SHA to main. The branch ref points at old
commits that aren't descendants of current main, so the push would
always fail as non-fast-forward.
2. Retry worktree add once with jittered delay when config.lock
contention occurs from parallel domain merges.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Forgejo categorically blocks --force-with-lease on protected branches,
even for fast-forward pushes. The cherry-picked branch is already a
descendant of origin/main, so a regular push is a fast-forward by
definition. Non-ff is rejected by default — same safety guarantee.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three fixes from Ganymede's review of extract-time-connection:
1. Replace git add -A with explicit file staging in _reciprocal_edges
2. Push to origin/main immediately after commit (survive batch-extract reset)
3. RECIPROCAL_EDGE_MAP: challenges→challenged_by (not symmetric)
Added challenged_by to REWEAVE_EDGE_FIELDS, EDGE_FIELDS, EDGE_WEIGHTS
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The skip loop only matched `- ` (no indent) but YAML list items are
commonly written as ` - item` (2-space indent). This caused old list
items to persist alongside new ones, corrupting frontmatter on merge.
Fix: consume any line starting with space or dash as part of the current
field's value block.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Combined superset assertion and merge computation into single loop
(removed duplicate scalar-to-list normalization)
- Added worktree remove --force before worktree add to handle prior
crash leaving stale worktree (SIGKILL, OOM, power loss)
Two fixes from Ganymede review:
1. CRITICAL: blank line before closing --- compounded on repeat reweaves.
Body starts with \n---, so \n{body} created \n\n---. Fixed by checking
body prefix.
2. Replaced yaml.dump round-trip with _serialize_edge_fields() that splices
only edge arrays into raw frontmatter text. Non-edge fields (title,
confidence, type, quotes, flow styles) stay byte-identical to main HEAD.
_parse_yaml_frontmatter now returns 3-tuple: (dict, raw_fm_text, body).
_serialize_frontmatter takes (raw_fm_text, merged_edges_dict, body).
26 tests pass including idempotency (5x serialize), formatting preservation,
and no-blank-line regression test.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Reweave PRs modify existing files (appending YAML edges). Cherry-pick
fails ~75% when main moves between PR creation and merge.
_merge_reweave_pr() reads each changed file from both main HEAD and
branch HEAD, unions the edge arrays (order-preserving, main-first),
and writes the result. Eliminates merge conflicts structurally.
Key design decisions (Ganymede + Theseus approved):
- Order-preserving dedup: main's edges first, branch-new appended
- Superset assertion: logs warning if branch missing main edges
- Uses main's body text (reweave only touches frontmatter)
- Loud failure on parse errors (no cherry-pick fallback)
- Append-only contract: reweave adds edges, never removes
18 tests covering parse, union, serialize, superset, and full workflow.
_retry_conflict_prs called _rebase_and_push which was never defined,
causing NameError on every conflict retry. Now uses _cherry_pick_onto_main
consistent with the primary merge path.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
