Teleo evaluation pipeline infrastructure — Python async daemon for claim extraction, validation, evaluation, and merge
Find a file
m3taversal f43f8f923f fix: enrichment idempotency — three-layer dedup prevents duplicate evidence blocks
Layer 1: Insertion-time dedup in openrouter-extract-v2.py — skip if source_slug
already appears in claim content.
Layer 2: Insertion-time dedup in entity_batch.py — skip if PR number already
enriched this claim.
Layer 3: Post-rebase dedup in merge.py — scan rebased files for duplicate
evidence blocks (same source reference) and remove them before force-push.

Root cause: multiple enrichment branches modify the same claim at the same
insertion point. When rebased sequentially, evidence blocks are duplicated.
(Leo: PRs #1751, #1752)

lib/dedup.py: standalone module — parses evidence headers, deduplicates by
source key, preserves trailing content (Relevant Notes, Topics sections).
9 tests covering all patterns including the real PR #1751 duplication case.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-31 13:18:23 +01:00
.forgejo/workflows ganymede: add dev infrastructure — pyproject.toml, CI, deploy script 2026-03-13 14:24:27 +00:00
diagnostics feat: two-pass retrieval with sort order and graph expansion 2026-03-28 22:34:45 +00:00
lib fix: enrichment idempotency — three-layer dedup prevents duplicate evidence blocks 2026-03-31 13:18:23 +01:00
ops feat: atomic extract-and-connect + stale PR monitor + response audit 2026-03-28 22:34:20 +00:00
telegram feat: two-pass retrieval with sort order and graph expansion 2026-03-28 22:34:45 +00:00
tests fix: enrichment idempotency — three-layer dedup prevents duplicate evidence blocks 2026-03-31 13:18:23 +01:00
.gitignore ganymede: add dev infrastructure — pyproject.toml, CI, deploy script 2026-03-13 14:24:27 +00:00
ARCHITECTURE.md epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features 2026-03-20 20:17:27 +00:00
backfill-ci.py doc: label backfill as one-shot, not cron (Ganymede review) 2026-03-26 15:09:47 +00:00
backfill-domains.py feat: atomic extract-and-connect + stale PR monitor + response audit 2026-03-28 22:34:20 +00:00
backfill-source-authors.py feat: source author backfill — credits intellectual foundations of KB 2026-03-26 15:26:04 +00:00
backfill-sources.py epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features 2026-03-20 20:17:27 +00:00
batch-extract-50.sh fix: zombie retry loop + cost tracking 2026-03-28 11:29:58 +00:00
bootstrap-contributors.py epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features 2026-03-20 20:17:27 +00:00
deploy.sh ganymede: add dev infrastructure — pyproject.toml, CI, deploy script 2026-03-13 14:24:27 +00:00
DIAGNOSTICS-AGENT-SPEC.md epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features 2026-03-20 20:17:27 +00:00
embed-claims.py feat: atomic extract-and-connect + stale PR monitor + response audit 2026-03-28 22:34:20 +00:00
extract-decisions.py fix: delete existing branch before re-creating in decision extractor 2026-03-24 11:43:27 +00:00
INFRASTRUCTURE.md Initial commit: Pipeline v2 daemon + infrastructure docs 2026-03-12 14:11:18 +00:00
migrate-entity-schema.py epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features 2026-03-20 20:17:27 +00:00
migrate-source-archive.py epimetheus: source archive restructure — inbox/queue + inbox/archive/{domain} + inbox/null-result 2026-03-18 11:50:04 +00:00
openrouter-extract-v2.py fix: enrichment idempotency — three-layer dedup prevents duplicate evidence blocks 2026-03-31 13:18:23 +01:00
PIPELINE-AGENT-SPEC.md epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features 2026-03-20 20:17:27 +00:00
pyproject.toml ganymede: add dev infrastructure — pyproject.toml, CI, deploy script 2026-03-13 14:24:27 +00:00
reconcile-sources.py feat: atomic extract-and-connect + stale PR monitor + response audit 2026-03-28 22:34:20 +00:00
research-prompt-leo-synthesis.md epimetheus: source archive restructure — inbox/queue + inbox/archive/{domain} + inbox/null-result 2026-03-18 11:50:04 +00:00
research-prompt-v2.md epimetheus: source archive restructure — inbox/queue + inbox/archive/{domain} + inbox/null-result 2026-03-18 11:50:04 +00:00
reweave.py feat: atomic extract-and-connect + stale PR monitor + response audit 2026-03-28 22:34:20 +00:00
sync-mirror.sh epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features 2026-03-20 20:17:27 +00:00
teleo-pipeline.py epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features 2026-03-20 20:17:27 +00:00
teleo-pipeline.service Initial commit: Pipeline v2 daemon + infrastructure docs 2026-03-12 14:11:18 +00:00
tier0-gate.py epimetheus: sync VPS-deployed code to repo — Mar 18-20 reliability + features 2026-03-20 20:17:27 +00:00