The incremental step dumped every file path into the agent context even
though later steps read the sidecar from disk. Print a short summary
and leave the full result in .graphify_incremental.json.
(cherry picked from commit d23d1c618a)
A committed graphify-out/graph.json is rewritten whole on every build, so
its pull-request diffs are large by design. Assistants reviewing such PRs
flagged them as churn and proposed skipping the rebuild or its hooks. The
Claude, AGENTS.md and Gemini blocks now say the diff is expected.
(cherry picked from commit e6cf17c171)
Persist validated Codex extraction responses as chunk files so the shared B3 merge preserves semantic nodes and edges.
Fail before cache and graph updates when extraction responses are missing or invalid.
Add regression coverage for chunk merging, cached reruns, and failure handling.
Fixes#4311
Co-authored-by: OpenAI Codex <codex@openai.com>
(cherry picked from commit da5850f0ac)
The #3490 lock predated its own setuptools>=83 / pypdf / yt-dlp floor bumps, so
a frozen sync resolved setuptools 82.0.1 and the no-isolation wheel-build test
failed. Regenerate the lock so it honors the floors. Also update the windows
skill test: the troubleshooting item is now 'Skip Leiden' (graspologic ->
graspologic-native gating), which #3490 changed in the fragment but not the test.
Complete the read-side BOM fix: the graphify update (no-args) recovery path at cli.py read
.graphify_root with plain utf-8, so a PowerShell-written BOM would fail the exists() check
and abort with path not found. Switch it to utf-8-sig like the other five reader sites.
Also clean up two invalid-escape f-strings in the windows skillgen test.
Windows PowerShell 5.1 writes a UTF-8 BOM, so the .graphify_root marker it produced carried
a leading BOM that Python's utf-8 decode kept as U+FEFF; .strip() left it in, breaking the
post-commit rebuild (WinError 123) and silently mis-rooting _infer_merge_root. Write the
marker BOM-less from PowerShell (WriteAllText + UTF8Encoding $false) and read the marker
with utf-8-sig at the reader sites so already-broken installs recover too.
The Windows skill variant had a PowerShell Step 1 but its later steps came
from the shared core fragment as bash-only shell (cat-piped interpreter
invocations, rm -f, find -delete). The skillgen renderer now translates the
composed core to PowerShell for powershell-shell platforms (here-string
interpreter invocations, Remove-Item cleanup); POSIX skills are unchanged
and step / #2490 parity is enforced by a generator check. Not a regression
from 0.9.35 (skill files were unchanged between 0.9.34 and 0.9.35).
Thanks @tannermosher2015-debug.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The semantic cache keyed entries on sha256(file content + path) alone, with
no component for the extraction prompt that produced them. After an upgrade
that changed the prompt, every unchanged file was a cache hit and replayed
the older prompt's extraction: the run exited 0, cost.json looked cheap, and
the graph silently carried two prompt generations side by side. The reporter
saw 506 of 512 docs replay an older vintage on a rebuild they expected to be
cold; deleting the whole cache was the only workaround.
output, and invalidating them on every release would re-bill extraction for
unchanged files. Fingerprinting the prompt itself keeps both properties:
entries survive releases that don't touch the prompt, and invalidate only
when it actually changed.
Semantic entries now live under cache/semantic/p{fingerprint}/, mirroring the
AST cache's v{version}/ layout. Both extraction paths pass their prompt: the
Python/CLI path from llm.py's _EXTRACTION_SYSTEM (shared by every backend),
and the skill path via a new prompt_file argument in Step B0/B3 naming the
references/extraction-spec.md the subagents were handed. The fingerprint
normalizes line endings so a CRLF checkout isn't mistaken for a new prompt.
Pre-existing entries predate fingerprinting and have unknowable vintage, so
they are still served rather than re-billing a whole corpus on upgrade — but
check_semantic_cache now warns with the count, turning "no signal at all"
into a visible one. merge_existing refuses to fuse such an entry into a
current-vintage write, which would mix two prompts inside one entry and then
attest the result to a prompt that produced half of it.
Old-fingerprint entries are pruned by liveness only, never swept wholesale
the way stale AST versions are: two hosts with different prompts (verbose vs
compact extraction-spec) can share one graphify-out/, and a wholesale sweep
would have each run delete the other's entries and re-bill on every
alternation. prune/clear/cached_files glob recursively so fingerprinted
entries can't become unprunable orphans (the #1527 failure mode).
The two monolith skills (aider, devin) inline their prompt instead of
shipping a spec sidecar and stay on the unfingerprinted path for now.
#1635: the windows skill variant declared `name: graphify-windows`, but
`graphify install --platform windows` writes it to ~/.claude/skills/graphify/
SKILL.md and Claude Code requires the folder name to equal the frontmatter
`name` — the suffix broke discovery. platforms.toml now sets name = "graphify"
(regenerated + re-blessed).
#1646: the OpenCode (and Kilo) plugin prepended its reminder with `&&`, which
Windows PowerShell 5.1 rejects as a statement separator, breaking the first
bash command of every session. Switched to `;` (valid in PowerShell 5.1, Bash,
POSIX).
#1657: the GRAPH_REPORT.md "Import Cycles" section printed "None detected" on
documents-only corpora where imports don't exist — now gated on code nodes /
import edges being present. The other two items in that issue (mojibake in
manifest/report, stdout encoding) are already handled on current v8: both files
are written UTF-8 and main() reconfigures stdout/stderr to UTF-8.
Full suite: 2909 passed, 3 skipped.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Generated install/skill guidance told agents to invoke a literal `skill`
tool with `skill: "graphify"`, which is host-specific and not valid in
every environment. The always-on AGENTS fragment, packaged artifact,
expected snapshot, and _skill_registration() output now use host-generic
wording: "use the installed graphify skill or instructions". Also decodes
skillgen git blob reads as UTF-8 for Windows and replaces stale English
code-block examples in the translated READMEs.
The always-on roundtrip guard deliberately freezes the v8 baseline, so an
intentional wording change would otherwise fail it. Rather than only
patching the pytest mirror (which left the blocking CLI guard
--always-on-roundtrip red, as the original PR did), this adds an explicit,
reviewable ALWAYS_ON_SANCTIONED_EDITS registry: the guard applies the
approved old->new substitution to the baseline before the byte-for-byte
compare, so this exact sentence is allowed while any other drift still
fails. CLI guard and pytest test now agree and CI passes.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Hermes and the other AGENTS.md hosts (Codex, Aider, OpenClaw, Droid, Trae, ...)
run the graphify CLI directly and do not dispatch subagents. The Step 3 extraction
guidance only described the no-API-key path as "fall straight through to subagent
dispatch", so on `/graphify .` those agents had no path they could take, fixated on
the GEMINI/ANTHROPIC key language, and looped for minutes insisting on a missing key
before eventually proceeding (a pure-code corpus is AST-only and needs no key at all).
Step 3 now opens with a hoisted, host-agnostic statement -- graphify needs no API
key, never prompt for one, never block on one; code is AST-only; a code-only corpus
skips semantic extraction entirely -- and the no-key fallback now spells out a
terminal-only path (write the empty semantic file and continue, or extract content
inline) instead of assuming subagent dispatch.
Applied in the shared core fragment and in the aider/devin core variants, so all 16
skill bodies carry it; the aider/devin change is registered as a sanctioned
monolith-roundtrip diff. Regression test (test_extraction_states_no_api_key_required_
for_every_host) renders every host and pins the wording, ordering, and the
non-subagent fallback so this can't silently regress.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
`graphify install --platform agents` installs the skill to the generic
Agent-Skills locations: the spec's user-global ~/.agents/skills (global) and
./.agents/skills (--project) — the directories `npx skills` and spec-compliant
frameworks read. `--platform skills` is an alias. Previously that user-global
location was only reachable as an accidental side effect of the gemini-on-Windows
branch. Bare `graphify install` is unchanged (still single-platform claude/windows).
The platform is registered in tools/skillgen/platforms.toml (split, mirroring
amp's agents-md body) and rendered through the skillgen drift/coverage guards.
Since it is a post-v8 platform with no own v8 body, its --audit-coverage baseline
is amp's v8 body (the body it re-homes). The rendered skill body is byte-identical
to amp's; only the on-demand hooks reference differs (its own `graphify agents
install` wording).
The `graphify agents install` / `graphify skills install` subcommand is the
amp-twin: it also wires an AGENTS.md always-on section, keeping it honest with the
hooks reference it points at. The `--platform agents` path stays skill-only,
exactly as amp's `--platform amp` does.
Also: `skill-agents.md` added to package-data, and the wheel-packaging guard now
covers every platform's skill body (not just references/always-on), so a missing
skill body fails CI instead of only breaking install for real users.
Closes#1405. Implements #1432.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The skill runbooks called save_manifest(...) with no root=, so manifest keys
were stored as absolute paths (e.g. /Users/.../main.go). Cloning or moving the
repo then broke `graphify --update`: detect_incremental matched none of the
cached keys, so the entire corpus re-extracted (and the report showed ghost
nodes). The native `graphify extract`/`update` CLI already passed root=target;
the agent-executed runbooks did not.
All four runbook call sites now pass root='INPUT_PATH', relativizing manifest
keys to the scan root (portable forward-slash form, per save_manifest's #777
support): the lean-core skill.md Step 9, the shared --update reference, and the
Aider/Devin monoliths.
The monolith edit is registered as a new sanctioned change-class
(_is_manifest_root_fix_line) in the round-trip guard, mirroring how the #1392
runbook fixes were sanctioned. Regenerated + blessed all artifacts; added a
regression test asserting every shipped runbook threads root= into save_manifest.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The monoliths are hand-maintained single files frozen against a pinned pristine-v8 blob by the round-trip guard, so they were excluded from the 0.8.44 #1392 batch. Evolve the guard from a positional zip (line-count-exact, single-line-class allowlist) to a multiset diff that classifies every added/removed line against documented sanctioned change-classes, so the multi-line fixes can land while any unsanctioned drift still fails. Add predicates for the four fix classes and broaden the enum/chunk-cleanup predicates to match both the v8 and rewritten forms.
Both monoliths now: thread directed=IS_DIRECTED through every build_from_json call (a --directed run no longer collapses reciprocal edges), scope semantic extraction to document/paper/image, unlink a stale .graphify_cached.json on a cache miss, and run Step 4's zero-node guard before any write with the report/analysis gated on to_json persisting the graph (#1392).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The query skill was split across two fragments so no platform got both
capabilities: Claude had the vocab/IDF query-expansion step but no fallback if
the CLI was unavailable; every other platform had the inline NetworkX fallback
but the weaker raw-question matcher. Merge into one unified query reference +
stub (Step 0 expansion -> CLI traversal -> inline NetworkX fallback, plus
path/explain inline) shipped to all hosts. Remove the query_variant enum, its
toml field, and the _CLI_ONLY_QUERY_HEADINGS coverage-audit exemption. Re-render
all skill artifacts and re-bless expected/. skillgen check/audit-coverage/
monolith-roundtrip/schema-singleton all pass. Refs #1325.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Agent Skills spec only defines name, description, license,
compatibility, metadata, and allowed-tools as valid frontmatter fields.
The trigger: /graphify line was non-spec, silently ignored by spec-
following hosts, and flagged by agentskills validate CI checks.
- gen.py: removed trigger emission from _render_frontmatter; added
_is_trigger_line() helper for roundtrip allow-list
- fragments/core/aider.md: removed hardcoded trigger: /graphify
- platforms.toml: removed trigger doc comment and trigger="" entries
- test_skillgen.py: replaced trigger-assertion tests with a single
test asserting no host has trigger: in frontmatter
- Regenerated all 125 skill artifacts
Routing intent is preserved: the description field already contains
"treated as a graphify query first" and "graphify-out/ exists".
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
#1174: affected.py load_graph now forces directed=True before
node_link_graph, matching the identical fix in serve.py and __main__.py.
Undirected graphs (directed:false in graph.json) were causing in_edges
to fall back to a direction-blind scan, missing true callers and
reporting false positives. Regression test added.
#1173: post-commit and post-checkout hook bodies now read
graphify-out/.graphify_root before calling _rebuild_code, falling back
to Path('.') if absent. A scoped build (graphify src/) no longer gets
silently expanded to the full repo on the next commit. Tests added.
#1172: Step 9 cleanup split into rm -f for fixed files and
find -maxdepth 1 -delete for the chunk glob. Under fish/zsh an
unmatched glob aborts the entire rm -f line, leaving temp files on disk.
Fixed in the three skillgen source fragments and regenerated.
#1163: detect_incremental type guard on stored mtime — if the manifest
contains a dict-valued mtime (schema drift from older versions), coerce
to None rather than propagating a non-numeric into comparisons.
Regression test added.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
R1: the 6 always-on blocks were read into module-level constants at import,
so a missing/corrupt always_on/*.md crashed `import graphify.__main__` and
bricked every CLI command, not just install. Make _always_on lazy + lru_cached,
raising a clear "reinstall" error only on the install path that needs the block;
a module __getattr__ keeps the legacy constant names importable for the tests.
Verified: deleting a block no longer crashes `graphify --version`.
skillgen baselines: the self-check guards pinned to the moving `origin/v8` ref,
which stops pointing at the pre-split state once the split lands on v8 (the
always-on-roundtrip guard then fails in CI and monolith-roundtrip goes vacuous).
Pin _v8_baseline_ref, ALWAYS_ON_BASELINE_REF, and the two monolith roundtrip_refs
to the immutable pre-split commit SHA, matching the stated "does not track HEAD"
intent; update the 4 tests that asserted the old ref string.
R2: add tests/test_wheel_packaging.py - build the wheel and assert every
references bundle and always-on block ships in it, so a package-data glob miss
can't pass the repo-tree guards yet hard-exit `graphify install` for real users.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
All-platform progressive-disclosure skill split + generator (addresses #1106).
Splits each platform's skill into a lean core (~615 lines, full default pipeline inline) + on-demand references/, generated from a single source via tools/skillgen with a CI/pre-commit drift gate. 13 hosts split, aider/devin stay monoliths. Also fixes the stale bare-path bugs across the previously hand-maintained variants and moves the always-on blocks into packaged markdown.
Verified: all 5 generator guards pass, byte-verbatim load-bearing slices, lean cores self-sufficient on the default path across all 13 split hosts, references gated to non-default branches, description preserves the graphify-out-query-first clause. Supersedes #1119 (Claude-first subset).
Known follow-up applied on top: harden _always_on() against a missing packaged file so a partial install can't brick the CLI.
shazeb