The two bedrock-runtime clients (primary extraction in _call_bedrock and
the secondary dispatch path in _call_llm) were built with no botocore
config, so Converse used botocore's 60s default read timeout and ignored
GRAPHIFY_API_TIMEOUT / --api-timeout entirely. A long opus-class
generation then died with "Read timeout on endpoint URL" no matter how
high the timeout was set.
Both client constructions now pass a botocore.config.Config wiring
read_timeout to _resolve_api_timeout() (default 600s), a 10s
connect_timeout, and retries from _resolve_max_retries() in adaptive
mode. This mirrors the fixes that closed the same gap for the claude-cli
subprocess (#1112/#1111) and the secondary LLM dispatch path (#1442) --
bedrock was the last cloud backend still ignoring the knob.
Also updates the README env-var row, which listed the timeout as
applying to HTTP/claude-cli/Anthropic only, and the _fake_boto3 test
fixture to register botocore.config and capture the client config so the
new coverage can assert the timeout is wired.
`graphify codex install` registers `graphify hook-check` in .codex/hooks.json,
and #2165 reported that as a stale/unrecognized subcommand producing a silent
no-op. `hook-check` is in fact a real, deliberate no-op command: Codex Desktop
rejects hookSpecificOutput.additionalContext on PreToolUse, so the Codex hook
intentionally does nothing and AGENTS.md carries the always-on guidance
(cli.py dispatches `hook-check`; __main__.py lists it in _silent_cmds).
Repointing the installer at `hook-guard` would reintroduce the #522-class
breakage on Codex Desktop, so the behavior is left as is.
What actually misled the report was the documentation and the installer's own
output, which both describe the Codex hook as if it enforced graph usage:
- README: the Codex row claimed a PreToolUse hook that "fires before every Bash
tool call, same always-on mechanism as Claude Code". It now states that the
hook is a deliberate no-op, why (Codex Desktop rejects additionalContext), and
that AGENTS.md is the always-on mechanism on this platform.
- `_install_codex_hook` printed "PreToolUse hook registered (... hook-check)"
with no hint that the entry is inert. It now says so inline.
Also adds the regression guard the issue implicitly asks for: a test that reads
the command out of the generated .codex/hooks.json and asserts its subcommand is
one the CLI actually dispatches. A genuinely renamed/stale hook command now
fails the suite instead of shipping a permanently dead hook.
Note: contrary to the report, an unrecognized subcommand already exits non-zero
(`graphify totally-bogus-subcommand` -> "error: unknown command", exit 1), so no
change was needed there.
The inline api.star-history.com SVG rate-limits on a repo this large and
serves a 503 instead of a chart, so the image was permanently broken.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The top-level `graphify --help` has listed --code-only since #1734, but the
`graphify extract` usage string and the README never mentioned it. A user
evaluating graphify on a "can this run with no network call" constraint sees
the extract usage / README first and can conclude the flag doesn't exist.
Add --code-only to the extract usage line, name it in the Privacy section and
the command reference, and add a test asserting the usage advertises it.
`uv run --with graphifyy python -m graphify` runs the system interpreter, so an
older `graphifyy` in system site-packages loads before the uv-managed one — with
no error. Env overrides like OPENAI_BASE_URL are then ignored and requests 401
against the default endpoint. The existing `skill is from graphify X, package is
Y` warning is the real fingerprint, but users dismiss it as a stale skill.
Add a troubleshooting entry next to the uvx-resolution one: name the symptom,
show how to confirm which module actually loaded, and point at
`uvx --from graphifyy` / uninstalling the stale copy.
GitHub is the top organic source of waitlist signups, but the only path to the
site was the logo and a CTA at the very bottom of the README. Add a short,
plain-voice waitlist line right after the value proposition, and change the
Enterprise-section CTA from "Learn more" to an explicit "Join the waitlist".
Rename the "Penpax" section to "graphify Enterprise" (linking graphify.com) and
add a Website badge to the Community and links footer.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Stamp the 0.9.19 release date, add a README note for the strict PreToolUse hook
(graphify install --project --strict), and credit both the #1814 reporter
(@Greg-Moskalenko) and the fix author (@alphanury).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Stamp the 0.9.18 release date and add a README troubleshooting entry for the
new #1951 behavior: an incomplete extraction refuses to overwrite a larger
existing graph, with --allow-partial as the escape hatch.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
querylog wrote every query/path/explain question + corpus path (and full
responses under GRAPHIFY_QUERY_LOG_RESPONSES) to a default-on, unbounded,
fail-silent plaintext file at ~/.cache/graphify-queries.log — outside any repo's
.gitignore/retention, and undocumented. A default-on plaintext record of
proprietary queries contradicts graphify's on-device / no-telemetry posture.
Flip to opt-in: _log_path() returns None unless GRAPHIFY_QUERY_LOG_ENABLE=1
(default path) or GRAPHIFY_QUERY_LOG=<path> is set; GRAPHIFY_QUERY_LOG_DISABLE=1
still forces it off (back-compat, wins). Document all four env vars in the
README (the old entries implied default-on). Regression tests cover
default-off, both enable paths, disable-wins, and that log_query writes nothing
without opt-in.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Switch every website URL from graphifylabs.ai to graphify.com — the hero logo,
the Penpax section, and the waitlist link — across the main README and the
translated READMEs. The contact email stays on graphifylabs.ai (mail is hosted
there); no mailto links were changed. graphify.com is the official graphify
product site; graphifylabs.ai remains the company site (org profile + email).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The badge's href pointed at www.ycombinator.com/companies/graphify, which 404s
— the public S26 company page isn't published yet. Show the badge without a
link rather than ship a dead click; re-add the href once YC publishes the page.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Badges reranked for click-through and split: lean top strip (PyPI, Downloads,
Discord, LinkedIn, YC S26) with trust signals leading and social/company links
at the tail; a "Community and links" footer (Discord, X, Sponsor, Book); CI
badge dropped, book also linked from "Learn more".
- Hero leads with three differentiator bullets, corrected to match the codebase:
code is tree-sitter AST (deterministic, no LLM, local), while docs/PDFs/images/
video use your assistant's model or a configured API key for a semantic pass.
Removed the inaccurate "local embedder" claim (there is no embedder; dedup is
MinHash/LSH and there is no vector store) and qualified "zero LLM tokens" to the
code path. "Not a vector index" is accurate.
- Added a 30-second quickstart (install + graphify install + /graphify .) above
the fold, moved "See it in action" above "What it does" so differentiation is
shown before it is enumerated, and compressed the "works in" list to one line.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
An animated SVG that mirrors the real `graphify path` output: a terminal
types the query on the left while the answer draws itself hop by hop across
the knowledge graph on the right, ending on "3 hops. Zero files opened."
Pure SMIL inside a self-contained dark card, so it renders inline on both
GitHub themes with no JS and no external fonts. Palette is brand-only:
muted emerald (sampled from the logo) as the single accent, no neon.
Generated by scripts/gen_demo_path.py (re-run to regenerate; STATIC=1 bakes
a still frame for QA).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds the Hebrew translation under docs/translations/README.he-IL.md and
links it from the language row (30 -> 31 languages). Merged from PR #1639
by @AdirBuskila; the language-row link was adapted to the current README
structure by hand since the English README changed after the PR was opened.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rework the top of the README into a self-contained pitch:
- New logo + Trendshift badge; collapse the 31-language row into a toggle so the
tagline and hero land in the first screen.
- Hero screenshot of the FastAPI graph, tagline with selective bold.
- 'What it does' capability table and a 'See it in action' section with verbatim
explain/path output (real relations + confidence tags).
- Benchmarks as a scannable table, honest: shows where competitors lead, only
bolds rows graphify wins or ties, names the tie.
- Collapse platform picker + optional extras into <details>; typography and
identifier-formatting polish; fix orphaned paragraphs; reword the confidence-tag
gloss; drop the redundant callflow CTA from the hero.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Applied the .claudeignore troubleshooting entry from #1539 manually (the PR
branched from an older README). Closes#1387.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
extract_pascal() already imports tree-sitter-pascal for AST-quality
extraction and falls back to a regex extractor when it is absent (#781),
but the grammar was not declared anywhere in the package metadata, so it
was never installed and the AST path never ran out of the box.
Declare a `pascal` extra (and add it to `all`) so users can opt into the
AST extractor with `uv tool install "graphifyy[pascal]"`. tree-sitter-pascal
publishes prebuilt wheels for every platform (win/macOS/Linux), so unlike
the `dm` extra it needs no C toolchain.
On a mid-size Delphi codebase the AST path yields notably more accurate
relationship edges than the regex fallback (calls and inherits both up
~25%). README extras table and uv.lock updated accordingly.
The 20+ row platform-install table and the optional-extras table (~60 lines
combined) sat between Install and the value content. Wrapping both in collapsible
<details> blocks keeps a skimmer moving to the report/commands sections while each
platform's command stays one click away. No content changed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds a hero screenshot of the interactive graph (FastAPI codebase, community
coloring) right after the tagline so the value prop is shown, not just told.
Converts the Benchmarks prose into a compact scannable table (LOCOMO recall/QA,
LongMemEval, zero-credit build) while keeping the judge-validation credibility
line and the link to BENCHMARKS.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replaces the old v4-hosted SVG wordmark with the new brand logo (graph-cube
icon + "Graphify" on the green brand gradient), tightly cropped from the source
export (1384x645, ~2.15:1, even ~90px padding). Served from docs/logo.png on v8.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds a benchmark writeup covering graphify as long-term memory (LOCOMO,
LongMemEval-S vs mem0/supermemory/bm25/dense/hybrid) and as a code-intelligence
layer (ERPNext), run on graphify's own harness with competitors as adapters:
one shared model (Kimi K2.6), identical budgets, shared BGE-m3 embedder where
allowed, and a judge blind-validated against a second judge (90.6% agreement,
kappa 0.81). Numbers are wins-forward but every retained figure is exact; the
supermemory recall comparison is labeled embedder-confounded. README gets a
short Benchmarks section linking to it.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The "What files it handles" code row omitted several extensions that reuse
existing tree-sitter grammars (so the grammar count is unchanged): `.mts`/`.cts`
(TypeScript, #1607, new in 0.9.6), `.cc`/`.cxx` (C++), `.kts` (Kotlin), `.psd1`
(PowerShell), `.toc` (Lua). Apex (`.cls`/`.trigger`) and Terraform already have
their own rows. `.r`/`.ejs`/`.ets` are intentionally left out — they are in
CODE_EXTENSIONS but have no registered extractor.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Swap the personal LinkedIn link for the Graphify Labs company page across the
main README and all translated READMEs; relabel the badge to Graphify Labs.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
README: document that `reflect --graph` writes the .graphify_learning.json
overlay and that explain/query surface a Lesson hint (with the
code-changed staleness flag).
CHANGELOG: add an Unreleased section for the post-0.9.2 work — the
work-memory overlay (#1441/#1542), this.field.method() injected-field
resolution (#1316), TS wildcard path aliases (#1544), JS namespace
re-exports (#1552), and the ObjC dot-syntax/@selector edges (#1475/#1543).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The --obsidian-dir flag was undocumented in the README. Add it to the command
list with a note that exporting into an existing vault never overwrites the user's
own notes or .obsidian config (the guard shipped in 0.8.51).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Documents two expected uv behaviors that read as bugs on macOS: (1) uv tool
install puts `graphify` in ~/.local/bin which a fresh zsh shell may not have on
PATH (run `uv tool update-shell`); (2) `uvx graphify` fails because the package is
`graphifyy` and `graphify` is only its console script — use
`uvx --from graphifyy graphify install`. README install note + Troubleshooting.
Ported from PR #1474 by @TPAteeq. Maintainer fix on port: moved the CHANGELOG
entry from the already-released 0.8.50 block (where the stale base placed it) into
the current Unreleased section.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The README showed `global add graph.json myrepo` (positional tag) writing to
`~/.graphify/global.json`. The real CLI takes the tag via `--as` (the positional
was silently ignored) and the file is `~/.graphify/global-graph.json`. Corrected
to `global add graph.json --as myrepo`.
Ported from PR #1489 by @MikeKatsoulakis.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Metal Shading Language is C++14, so .metal files are classified as code and routed
through the existing C++ extractor, mirroring the CUDA .cu/.cuh reuse. Also adds
.cu/.cuh/.metal to build.py's _LANG_FAMILY map (they were all missing), so the
cross-language phantom-`calls`-edge filter treats them as C++. README language
table updated.
Ported from PR #1480 by @jiangyq9. This supersedes the earlier #1450 by
@GoodOlClint (same .metal -> C++ approach and fixture) — credit to @GoodOlClint
for the original; #1480 additionally closes the CUDA family-map gap and updates
the docs, and merges clean against current v8.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Makes .xaml a first-class code input. extract_xaml() uses stdlib XML (no new
parser dependency) behind the same DOCTYPE/ENTITY and size guards as the .csproj
extractor, and captures: the root element, named controls (x:Name/Name) and their
control types, {Binding ...} references, x:Class, and -- the useful part -- a
bridge from the view markup to its .xaml.cs code-behind by resolving event-handler
attributes to the matching methods on the partial class.
Ported from PR #1460 by @MikeKatsoulakis onto current v8.
Maintainer hardening on top of the original PR: event resolution is now gated so
it can't fabricate edges. The original matched any attribute value against
code-behind method names, so Content="Save" next to a business method Save(), or
Tag="<a-handler-name>", produced spurious "event" edges. Resolution now requires
(a) the attribute is not a known free-form/identity property (Content, Text, Tag,
Title, ToolTip, Header, ...), (b) the value is a bare identifier, and (c) the
matched method actually has the .NET event-handler signature
(object sender, <T>EventArgs e) -- read from the code-behind source since the C#
extractor does not record parameter lists on method nodes. Added regression tests
for both false-positive cases.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
get_community shows the community name (#1448); starlette floored >=1.3.1 for
CVE-2026-48818 / CVE-2026-54283 (#1391, #1396); begin per-language extractor
split into graphify/extractors/ (#1212); parallel community labeling via
--max-concurrency / --batch-size (#1390); reflect dedups dead-ends/corrections;
and the work-memory loop no longer depends on the git hook (reflect --if-stale).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Work-memory (#1441): save-result --outcome + graphify reflect, with recency-decayed
scoring, corroboration threshold, label-matched node-existence gate, contested
handling, and zero-config adoption (skill reads LESSONS.md + records outcomes; git
hooks auto-reflect). Fixes: Python ClassName.method() qualified-call edges (#1446);
validate_extraction/build crash on non-hashable id (#1447); graphify update now
prunes a symbol removed from a surviving file without --force.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds the deterministic work-memory loop: `save-result --outcome
useful|dead_end|corrected [--correction]` records how a saved Q&A turned out, and
`graphify reflect` aggregates graphify-out/memory/ into a deterministic
reflections/LESSONS.md an agent loads next session.
Source nodes are scored, not counted: signed, recency-decayed (useful +,
dead_end/corrected -, configurable --half-life-days, default 30), so a fresh dead
end outweighs a stale useful. A node is "preferred" only once corroborated by
>=--min-corroboration distinct results (default 2); others are "tentative", and
mixed-signal nodes render once as "contested" (recency-wins). Source nodes are
matched to the graph by label OR id, and citations whose node no longer exists are
dropped, so a plain `graphify update` after deleting code clears stale lessons.
Deterministic, no LLM; bare save-result and existing behavior unchanged.
Rigorously verified end-to-end on real data: corroboration boundary, recency flip,
contested verdict, foreign/malformed memory docs, cold start, 300-doc scale +
byte-stable output, and the node-gate dropping deleted-code lessons after update.
Full suite 2383 passed; skillgen --check clean; ruff clean.
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>
CUDA is a C++ superset, so .cu/.cuh files parse cleanly with
tree-sitter-cpp (already a dependency). Two registrations wire it up:
- detect.py: add .cu/.cuh to CODE_EXTENSIONS so they're detected and
watched (watch.py's _WATCHED_EXTENSIONS derives from CODE_EXTENSIONS).
- extract.py: route .cu/.cuh through extract_cpp in _DISPATCH, which
also makes collect_files() pick them up (_EXTENSIONS = _DISPATCH.keys()).
Adds tests/fixtures/sample.cu (kernel + __device__/host functions +
struct + includes) and CUDA cases in test_languages.py covering kernel/
device function extraction, structs, includes, and host call edges.
Documents the new extensions in the README extension table and CHANGELOG.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A .graphifyignore made graphify skip that directory's .gitignore entirely, so a
file excluded only by .gitignore (including neutrally-named secrets the
sensitive-file heuristic misses) got indexed into the graph and could leak into
committed graph artifacts. Read .gitignore first and .graphifyignore last so
their patterns merge and graphifyignore negations still win.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add changelog entries for the Swift cross-file (#1356), update prune (#1361),
obsidian canvas (#1324), and edge source_file backfill (#1279) fixes that
shipped without changelog notes, and a README troubleshooting entry for the
LLM JSON-truncation warnings and how to reduce them.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Bump version to 0.8.40; document this release in CHANGELOG (PowerShell .psm1
indexing, Swift import survival, no-cluster edge dedup, custom OpenAI/Anthropic
endpoints, JS/TS assignment-form extraction, community-name + --graph fixes,
four production bug fixes, perf, security CI); add .psm1 to the README
supported-extensions table.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
