fix(skills): --update must prune files a new ignore rule excluded (#2773)

graphify/skills/agents/references/update.md

@@ -17,11 +17,17 @@ new_total = result.get('new_total', 0)
 print(json.dumps(result, indent=2, ensure_ascii=False))
 Path('graphify-out/.graphify_incremental.json').write_text(json.dumps(result, ensure_ascii=False), encoding=\"utf-8\")
 deleted = list(result.get('deleted_files', []))
-if new_total == 0 and not deleted:
+# Newly ignored/excluded files are stale in exactly the same way as deleted ones
+# (#2773). They must count here too, or adding a .graphifyignore rule with nothing
+# else changed exits 'Nothing to update' and never reaches the prune below.
+excluded = list(result.get('excluded_files', []))
+if new_total == 0 and not deleted and not excluded:
     print('No files changed since last run. Nothing to update.')
     raise SystemExit(0)
 if deleted:
     print(f'{len(deleted)} deleted file(s) to prune.')
+if excluded:
+    print(f'{len(excluded)} newly excluded file(s) to prune.')
 if new_total > 0:
     print(f'{new_total} new/changed file(s) to re-extract.')
 "
@@ -66,11 +72,11 @@ If `code_only` is True: print `[graphify update] Code-only changes detected - sk
 If `code_only` is False (any changed file is a doc/paper/image/video): **first, if any changed file is in `new_files['video']`, run `references/transcribe.md` (Step 2.5) on those files, then rewrite `.graphify_detect.json` to move the resulting transcript paths into `files['document']` and drop `files['video']`** — otherwise raw `.mp4/.mp3` paths are fed to semantic subagents as unreadable media (#1392). Then run the full Steps 3A–3C pipeline as normal.
 
 
-If no new files exist (only deletions), create an empty extraction so the merge step can prune:
+If no new files exist (only deletions or newly excluded files), create an empty extraction so the merge step can prune:
 
 ```bash
 if [ ! -f graphify-out/.graphify_extract.json ]; then
-    echo '[graphify update] Only deletions -- creating empty extraction for merge.'
+    echo '[graphify update] Nothing to re-extract -- creating empty extraction so the merge can prune.'
     $(cat graphify-out/.graphify_python) -c "
 import json
 from pathlib import Path
@@ -93,13 +99,21 @@ from graphify.detect import save_manifest
 new_extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
 incremental = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\"))
 deleted = list(incremental.get('deleted_files', []))
-# prune_sources is ONLY for genuinely DELETED files. Changed/re-extracted files are
-# handled by build_merge's replace-on-re-extract (#1344): every source_file in
+# Files that left the corpus because an ignore rule or --exclude changed. These are
+# NOT deletions — detect_incremental splits them out precisely so they are not
+# reported as such (#1908) — but their nodes are just as stale, and graphify's own
+# library path prunes both (cli.py: `list(excluded_files) + graph_stale_sources`).
+# Without this an added .graphifyignore rule never removes what it excluded, and the
+# leak is permanent: save_manifest below drops the excluded row, so on the next run
+# the file is neither deleted nor excluded and nothing can prune it again (#2773).
+excluded = list(incremental.get('excluded_files', []))
+# prune_sources is for genuinely DELETED and newly EXCLUDED files. Changed/re-extracted
+# files are handled by build_merge's replace-on-re-extract (#1344): every source_file in
 # new_chunks is dropped from the base before merge, so old/stale nodes don't survive.
 # Do NOT add `changed` here: with root= passed, prune_set relativizes to the same base
 # as the freshly merged nodes and would DELETE the re-extracted content (#1178 is moot
 # now that replace — not the dedup pass — reconciles changed files).
-prune = list(deleted) or None
+prune = (list(deleted) + excluded) or None
 
 # Use build_merge() — reads graph.json directly without NetworkX round-trip
 # so edge direction (calls, implements, imports) is always preserved (#801).

graphify/skills/amp/references/update.md

@@ -17,11 +17,17 @@ new_total = result.get('new_total', 0)
 print(json.dumps(result, indent=2, ensure_ascii=False))
 Path('graphify-out/.graphify_incremental.json').write_text(json.dumps(result, ensure_ascii=False), encoding=\"utf-8\")
 deleted = list(result.get('deleted_files', []))
-if new_total == 0 and not deleted:
+# Newly ignored/excluded files are stale in exactly the same way as deleted ones
+# (#2773). They must count here too, or adding a .graphifyignore rule with nothing
+# else changed exits 'Nothing to update' and never reaches the prune below.
+excluded = list(result.get('excluded_files', []))
+if new_total == 0 and not deleted and not excluded:
     print('No files changed since last run. Nothing to update.')
     raise SystemExit(0)
 if deleted:
     print(f'{len(deleted)} deleted file(s) to prune.')
+if excluded:
+    print(f'{len(excluded)} newly excluded file(s) to prune.')
 if new_total > 0:
     print(f'{new_total} new/changed file(s) to re-extract.')
 "
@@ -66,11 +72,11 @@ If `code_only` is True: print `[graphify update] Code-only changes detected - sk
 If `code_only` is False (any changed file is a doc/paper/image/video): **first, if any changed file is in `new_files['video']`, run `references/transcribe.md` (Step 2.5) on those files, then rewrite `.graphify_detect.json` to move the resulting transcript paths into `files['document']` and drop `files['video']`** — otherwise raw `.mp4/.mp3` paths are fed to semantic subagents as unreadable media (#1392). Then run the full Steps 3A–3C pipeline as normal.
 
 
-If no new files exist (only deletions), create an empty extraction so the merge step can prune:
+If no new files exist (only deletions or newly excluded files), create an empty extraction so the merge step can prune:
 
 ```bash
 if [ ! -f graphify-out/.graphify_extract.json ]; then
-    echo '[graphify update] Only deletions -- creating empty extraction for merge.'
+    echo '[graphify update] Nothing to re-extract -- creating empty extraction so the merge can prune.'
     $(cat graphify-out/.graphify_python) -c "
 import json
 from pathlib import Path
@@ -93,13 +99,21 @@ from graphify.detect import save_manifest
 new_extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
 incremental = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\"))
 deleted = list(incremental.get('deleted_files', []))
-# prune_sources is ONLY for genuinely DELETED files. Changed/re-extracted files are
-# handled by build_merge's replace-on-re-extract (#1344): every source_file in
+# Files that left the corpus because an ignore rule or --exclude changed. These are
+# NOT deletions — detect_incremental splits them out precisely so they are not
+# reported as such (#1908) — but their nodes are just as stale, and graphify's own
+# library path prunes both (cli.py: `list(excluded_files) + graph_stale_sources`).
+# Without this an added .graphifyignore rule never removes what it excluded, and the
+# leak is permanent: save_manifest below drops the excluded row, so on the next run
+# the file is neither deleted nor excluded and nothing can prune it again (#2773).
+excluded = list(incremental.get('excluded_files', []))
+# prune_sources is for genuinely DELETED and newly EXCLUDED files. Changed/re-extracted
+# files are handled by build_merge's replace-on-re-extract (#1344): every source_file in
 # new_chunks is dropped from the base before merge, so old/stale nodes don't survive.
 # Do NOT add `changed` here: with root= passed, prune_set relativizes to the same base
 # as the freshly merged nodes and would DELETE the re-extracted content (#1178 is moot
 # now that replace — not the dedup pass — reconciles changed files).
-prune = list(deleted) or None
+prune = (list(deleted) + excluded) or None
 
 # Use build_merge() — reads graph.json directly without NetworkX round-trip
 # so edge direction (calls, implements, imports) is always preserved (#801).

graphify/skills/claude/references/update.md

@@ -17,11 +17,17 @@ new_total = result.get('new_total', 0)
 print(json.dumps(result, indent=2, ensure_ascii=False))
 Path('graphify-out/.graphify_incremental.json').write_text(json.dumps(result, ensure_ascii=False), encoding=\"utf-8\")
 deleted = list(result.get('deleted_files', []))
-if new_total == 0 and not deleted:
+# Newly ignored/excluded files are stale in exactly the same way as deleted ones
+# (#2773). They must count here too, or adding a .graphifyignore rule with nothing
+# else changed exits 'Nothing to update' and never reaches the prune below.
+excluded = list(result.get('excluded_files', []))
+if new_total == 0 and not deleted and not excluded:
     print('No files changed since last run. Nothing to update.')
     raise SystemExit(0)
 if deleted:
     print(f'{len(deleted)} deleted file(s) to prune.')
+if excluded:
+    print(f'{len(excluded)} newly excluded file(s) to prune.')
 if new_total > 0:
     print(f'{new_total} new/changed file(s) to re-extract.')
 "
@@ -66,11 +72,11 @@ If `code_only` is True: print `[graphify update] Code-only changes detected - sk
 If `code_only` is False (any changed file is a doc/paper/image/video): **first, if any changed file is in `new_files['video']`, run `references/transcribe.md` (Step 2.5) on those files, then rewrite `.graphify_detect.json` to move the resulting transcript paths into `files['document']` and drop `files['video']`** — otherwise raw `.mp4/.mp3` paths are fed to semantic subagents as unreadable media (#1392). Then run the full Steps 3A–3C pipeline as normal.
 
 
-If no new files exist (only deletions), create an empty extraction so the merge step can prune:
+If no new files exist (only deletions or newly excluded files), create an empty extraction so the merge step can prune:
 
 ```bash
 if [ ! -f graphify-out/.graphify_extract.json ]; then
-    echo '[graphify update] Only deletions -- creating empty extraction for merge.'
+    echo '[graphify update] Nothing to re-extract -- creating empty extraction so the merge can prune.'
     $(cat graphify-out/.graphify_python) -c "
 import json
 from pathlib import Path
@@ -93,13 +99,21 @@ from graphify.detect import save_manifest
 new_extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
 incremental = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\"))
 deleted = list(incremental.get('deleted_files', []))
-# prune_sources is ONLY for genuinely DELETED files. Changed/re-extracted files are
-# handled by build_merge's replace-on-re-extract (#1344): every source_file in
+# Files that left the corpus because an ignore rule or --exclude changed. These are
+# NOT deletions — detect_incremental splits them out precisely so they are not
+# reported as such (#1908) — but their nodes are just as stale, and graphify's own
+# library path prunes both (cli.py: `list(excluded_files) + graph_stale_sources`).
+# Without this an added .graphifyignore rule never removes what it excluded, and the
+# leak is permanent: save_manifest below drops the excluded row, so on the next run
+# the file is neither deleted nor excluded and nothing can prune it again (#2773).
+excluded = list(incremental.get('excluded_files', []))
+# prune_sources is for genuinely DELETED and newly EXCLUDED files. Changed/re-extracted
+# files are handled by build_merge's replace-on-re-extract (#1344): every source_file in
 # new_chunks is dropped from the base before merge, so old/stale nodes don't survive.
 # Do NOT add `changed` here: with root= passed, prune_set relativizes to the same base
 # as the freshly merged nodes and would DELETE the re-extracted content (#1178 is moot
 # now that replace — not the dedup pass — reconciles changed files).
-prune = list(deleted) or None
+prune = (list(deleted) + excluded) or None
 
 # Use build_merge() — reads graph.json directly without NetworkX round-trip
 # so edge direction (calls, implements, imports) is always preserved (#801).

graphify/skills/claw/references/update.md

@@ -17,11 +17,17 @@ new_total = result.get('new_total', 0)
 print(json.dumps(result, indent=2, ensure_ascii=False))
 Path('graphify-out/.graphify_incremental.json').write_text(json.dumps(result, ensure_ascii=False), encoding=\"utf-8\")
 deleted = list(result.get('deleted_files', []))
-if new_total == 0 and not deleted:
+# Newly ignored/excluded files are stale in exactly the same way as deleted ones
+# (#2773). They must count here too, or adding a .graphifyignore rule with nothing
+# else changed exits 'Nothing to update' and never reaches the prune below.
+excluded = list(result.get('excluded_files', []))
+if new_total == 0 and not deleted and not excluded:
     print('No files changed since last run. Nothing to update.')
     raise SystemExit(0)
 if deleted:
     print(f'{len(deleted)} deleted file(s) to prune.')
+if excluded:
+    print(f'{len(excluded)} newly excluded file(s) to prune.')
 if new_total > 0:
     print(f'{new_total} new/changed file(s) to re-extract.')
 "
@@ -66,11 +72,11 @@ If `code_only` is True: print `[graphify update] Code-only changes detected - sk
 If `code_only` is False (any changed file is a doc/paper/image/video): **first, if any changed file is in `new_files['video']`, run `references/transcribe.md` (Step 2.5) on those files, then rewrite `.graphify_detect.json` to move the resulting transcript paths into `files['document']` and drop `files['video']`** — otherwise raw `.mp4/.mp3` paths are fed to semantic subagents as unreadable media (#1392). Then run the full Steps 3A–3C pipeline as normal.
 
 
-If no new files exist (only deletions), create an empty extraction so the merge step can prune:
+If no new files exist (only deletions or newly excluded files), create an empty extraction so the merge step can prune:
 
 ```bash
 if [ ! -f graphify-out/.graphify_extract.json ]; then
-    echo '[graphify update] Only deletions -- creating empty extraction for merge.'
+    echo '[graphify update] Nothing to re-extract -- creating empty extraction so the merge can prune.'
     $(cat graphify-out/.graphify_python) -c "
 import json
 from pathlib import Path
@@ -93,13 +99,21 @@ from graphify.detect import save_manifest
 new_extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
 incremental = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\"))
 deleted = list(incremental.get('deleted_files', []))
-# prune_sources is ONLY for genuinely DELETED files. Changed/re-extracted files are
-# handled by build_merge's replace-on-re-extract (#1344): every source_file in
+# Files that left the corpus because an ignore rule or --exclude changed. These are
+# NOT deletions — detect_incremental splits them out precisely so they are not
+# reported as such (#1908) — but their nodes are just as stale, and graphify's own
+# library path prunes both (cli.py: `list(excluded_files) + graph_stale_sources`).
+# Without this an added .graphifyignore rule never removes what it excluded, and the
+# leak is permanent: save_manifest below drops the excluded row, so on the next run
+# the file is neither deleted nor excluded and nothing can prune it again (#2773).
+excluded = list(incremental.get('excluded_files', []))
+# prune_sources is for genuinely DELETED and newly EXCLUDED files. Changed/re-extracted
+# files are handled by build_merge's replace-on-re-extract (#1344): every source_file in
 # new_chunks is dropped from the base before merge, so old/stale nodes don't survive.
 # Do NOT add `changed` here: with root= passed, prune_set relativizes to the same base
 # as the freshly merged nodes and would DELETE the re-extracted content (#1178 is moot
 # now that replace — not the dedup pass — reconciles changed files).
-prune = list(deleted) or None
+prune = (list(deleted) + excluded) or None
 
 # Use build_merge() — reads graph.json directly without NetworkX round-trip
 # so edge direction (calls, implements, imports) is always preserved (#801).

graphify/skills/codex/references/update.md

@@ -17,11 +17,17 @@ new_total = result.get('new_total', 0)
 print(json.dumps(result, indent=2, ensure_ascii=False))
 Path('graphify-out/.graphify_incremental.json').write_text(json.dumps(result, ensure_ascii=False), encoding=\"utf-8\")
 deleted = list(result.get('deleted_files', []))
-if new_total == 0 and not deleted:
+# Newly ignored/excluded files are stale in exactly the same way as deleted ones
+# (#2773). They must count here too, or adding a .graphifyignore rule with nothing
+# else changed exits 'Nothing to update' and never reaches the prune below.
+excluded = list(result.get('excluded_files', []))
+if new_total == 0 and not deleted and not excluded:
     print('No files changed since last run. Nothing to update.')
     raise SystemExit(0)
 if deleted:
     print(f'{len(deleted)} deleted file(s) to prune.')
+if excluded:
+    print(f'{len(excluded)} newly excluded file(s) to prune.')
 if new_total > 0:
     print(f'{new_total} new/changed file(s) to re-extract.')
 "
@@ -66,11 +72,11 @@ If `code_only` is True: print `[graphify update] Code-only changes detected - sk
 If `code_only` is False (any changed file is a doc/paper/image/video): **first, if any changed file is in `new_files['video']`, run `references/transcribe.md` (Step 2.5) on those files, then rewrite `.graphify_detect.json` to move the resulting transcript paths into `files['document']` and drop `files['video']`** — otherwise raw `.mp4/.mp3` paths are fed to semantic subagents as unreadable media (#1392). Then run the full Steps 3A–3C pipeline as normal.
 
 
-If no new files exist (only deletions), create an empty extraction so the merge step can prune:
+If no new files exist (only deletions or newly excluded files), create an empty extraction so the merge step can prune:
 
 ```bash
 if [ ! -f graphify-out/.graphify_extract.json ]; then
-    echo '[graphify update] Only deletions -- creating empty extraction for merge.'
+    echo '[graphify update] Nothing to re-extract -- creating empty extraction so the merge can prune.'
     $(cat graphify-out/.graphify_python) -c "
 import json
 from pathlib import Path
@@ -93,13 +99,21 @@ from graphify.detect import save_manifest
 new_extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
 incremental = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\"))
 deleted = list(incremental.get('deleted_files', []))
-# prune_sources is ONLY for genuinely DELETED files. Changed/re-extracted files are
-# handled by build_merge's replace-on-re-extract (#1344): every source_file in
+# Files that left the corpus because an ignore rule or --exclude changed. These are
+# NOT deletions — detect_incremental splits them out precisely so they are not
+# reported as such (#1908) — but their nodes are just as stale, and graphify's own
+# library path prunes both (cli.py: `list(excluded_files) + graph_stale_sources`).
+# Without this an added .graphifyignore rule never removes what it excluded, and the
+# leak is permanent: save_manifest below drops the excluded row, so on the next run
+# the file is neither deleted nor excluded and nothing can prune it again (#2773).
+excluded = list(incremental.get('excluded_files', []))
+# prune_sources is for genuinely DELETED and newly EXCLUDED files. Changed/re-extracted
+# files are handled by build_merge's replace-on-re-extract (#1344): every source_file in
 # new_chunks is dropped from the base before merge, so old/stale nodes don't survive.
 # Do NOT add `changed` here: with root= passed, prune_set relativizes to the same base
 # as the freshly merged nodes and would DELETE the re-extracted content (#1178 is moot
 # now that replace — not the dedup pass — reconciles changed files).
-prune = list(deleted) or None
+prune = (list(deleted) + excluded) or None
 
 # Use build_merge() — reads graph.json directly without NetworkX round-trip
 # so edge direction (calls, implements, imports) is always preserved (#801).