dream: 2026-06-18 06:38, 4 change(s)

[MEMORY] Duplicate wiki sources (same URL as already-compiled source) should be detected and moved to `_hard/`
[MEMORY] Wiki uses graph layer with ontology.yaml
[MEMORY] Wiki graph regeneration: run `wiki_graph_lint.py` + `wiki_graph_extract.py` after each ingest batch that adds graph metadata
[SKILL] wiki-compile: idempotent wiki source compilation — check if pages already exist (skip if so), detect duplicate URLs → `_hard/`, handle ambiguous/conflicting sources → `_hard/` + log, move processed to `_done/`, run graph lint+extract after batch
This commit is contained in:
nanobot
2026-06-18 07:43:13 +02:00
parent d0e4d00a7a
commit 8a2af3091d
2 changed files with 3 additions and 1 deletions

View File

@@ -1 +1 @@
359 361

View File

@@ -87,7 +87,9 @@ This file stores important information that should persist across sessions.
- Wiki lint rule: lint is report-only, never make destructive edits to existing wiki pages without user confirmation - Wiki lint rule: lint is report-only, never make destructive edits to existing wiki pages without user confirmation
- Wiki compilation runs in isolated background sessions without user interaction (batch/hands-off mode) - Wiki compilation runs in isolated background sessions without user interaction (batch/hands-off mode)
- Wiki idempotency rule: if wiki pages already exist for a source, treat as done, move raw file to `_done/`, skip reconciliation - Wiki idempotency rule: if wiki pages already exist for a source, treat as done, move raw file to `_done/`, skip reconciliation
- Duplicate wiki sources (same URL as an already-compiled source) must be detected and moved to `_hard/`
- Every processed source must be moved out of `cml/raw/` to prevent cron reprocessing - Every processed source must be moved out of `cml/raw/` to prevent cron reprocessing
- Wiki graph regeneration: run `wiki_graph_lint.py` + `wiki_graph_extract.py` after each ingest batch that adds graph metadata
- Wiki source pages need explicit `slug` field (e.g. `slug: source-flash-attention`) and `graph.node_id` + `canonical: true` to avoid UNIQUE constraint collision with concept/entity pages sharing the same filename stem - Wiki source pages need explicit `slug` field (e.g. `slug: source-flash-attention`) and `graph.node_id` + `canonical: true` to avoid UNIQUE constraint collision with concept/entity pages sharing the same filename stem
- `wiki_graph_extract.py` patched: skip duplicate slugs (first wins) instead of crashing on `nodes.slug` UNIQUE constraint - `wiki_graph_extract.py` patched: skip duplicate slugs (first wins) instead of crashing on `nodes.slug` UNIQUE constraint