Smoke check 8d required Claude's PostToolUse matcher to be exactly Read. The
drift note widens it on purpose to Read|mcp__.*codebase-memory-mcp__.*, so a
graph tool call can reset the search count, and the macOS PR smoke failed on
it. 8d now requires exactly the new matcher, and besides a Search matcher it
also refuses a catch-all ("*" or empty) matcher, as its comment promised.
Checked against real installs: the previous binary's Read-only settings fail
8d, the new install passes, and the new install plus a catch-all PostToolUse
entry fails.
Refs #509
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
The search hook gives each Grep, Glob or Bash search the matching graph
symbols, but a session can keep searching text for questions the graph answers
in one call (#509). Once a session has run three searches with no
codebase-memory-mcp tool call, the next augmentation now adds one factual line
saying so. The next note comes after six searches, then twelve, and any graph
tool call resets the count.
- State: a per-session counter in the process that runs hook requests (the
daemon), keyed by the payload's session_id, in a bounded 64-slot table that
evicts the least recently used session, behind a spin lock. Only searches
that reach the graph lookup count. A search without an augmentation still
counts, and the note waits for the next augmentation.
- Reset: Claude's managed PostToolUse entry now matches
"Read|mcp__.*codebase-memory-mcp__.*", covering plain and plugin server
names. The previous Read-only entry, as installs up to v0.12 wrote it, is
recognized as owned, so install replaces it in place and uninstall removes
either.
- Scope: Claude Code only. Codex sends the same event payload with a turn_id
but has no reset hook, so its sessions are not tracked, and payloads without
a session_id are not tracked either.
- Cost: a graph tool call now runs one hook round-trip to the daemon for the
reset, about 130 ms on a local build.
Refs #509
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
The PostToolUse change rendered the manifest twice per install and uninstall
(current and previous generation) and freed both with free(), which grew the
raw allocator count in src/cli/cli.c past its baseline (lint-memory-core).
The manifest is now written with cbm_json_writer_allocator() and released with
cbm_free(CBM_MEM_CLASS_OTHER, ...), including the frees that predate the
change, so cli.c drops from 170 to 166 raw sites and its baseline is lowered
to match. The rendered bytes are unchanged, so byte-exact ownership of
manifests written by earlier installs still holds.
Refs #509
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
The Codex CLI row still listed only SessionStart and SubagentStart after the
PreToolUse Bash hook landed (#2719), and the hook section described only
Claude Code's search context. The row now names the Codex search hook, and the
section says how Codex, Copilot CLI and VS Code's Copilot runtime get search
context.
Refs #509
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
Copilot CLI's preToolUse output can only decide permissions, and its command
hooks fail closed on errors, so the graph context that Claude Code and Codex
searches get could not ride a pre-tool hook there. postToolUse
additionalContext is appended to the tool result the model sees on the same
turn (github/docs content/copilot/reference/hooks-reference.md). VS Code's
agent mode shares the Copilot harness and reads the same ~/.copilot/hooks
manifest.
- Manifest: $COPILOT_HOME/hooks/codebase-memory-mcp.json adds a PascalCase
PostToolUse entry, matcher "Bash|Grep|Glob|bash|powershell|grep|rg|glob",
running hook-augment --event PostToolUse --dialect copilot. The previous
lifecycle-only manifest, as installs up to v0.12 wrote it, stays recognized
as owned: install upgrades it in place and uninstall removes either
generation. A foreign manifest still fails closed.
- hook-augment: the Copilot dialect reads either payload form
(tool_name/tool_input or toolName/toolArgs), maps runtime tool names to the
Claude names (bash/powershell to Bash, grep/rg to Grep, glob to Glob),
parses arguments passed as a JSON string, and answers with top-level
additionalContext.
- Fast path: Copilot's forced PostToolUse goes through the no-op gate before
executable-identity hashing. The gate also skips tools the augmenter does
not read, because VS Code's local hook parser ignores matchers, so a
non-search shell call or an edit exits in about 20 ms instead of paying the
full round-trip of about 130 ms.
- The context header no longer says the search results are "below": after a
post-tool hook they are above it.
- Tests: the three Copilot foreign-manifest tests now create
.copilot/mcp-config.json. Without it Copilot CLI was never detected, so
install and uninstall never reached the manifest, and the tests also passed
with the ownership checks removed.
Refs #509
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
The template opens with an HTML-comment note for maintainers, and the
workflow posted the file verbatim, so every acknowledgement comment
carried text a contributor cannot see but a tool reads. Our own PR
screening holds every comment with such hidden text, which parked nine
contributor PRs on a note we wrote ourselves.
Strip HTML comments (an unterminated one runs to the end, as GitHub
renders it) into a temporary body file and post that. The posted text is
byte-identical to what rendered before. A template whose only content is
the note now counts as blank, which is the documented off switch.
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
config_toml_codex_accepts_v0102_managed_windows_crlf asserted that re-upserting
over the v0.10.2 lifecycle-only block left the file byte-identical. That block
is now the previous generation: the upsert accepts it as owned and upgrades it
in place. The test now pins that upgrade (one PreToolUse table, BOM, CRLF and
the surrounding tables kept) and that a second upsert is byte-identical.
Refs #715
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
Codex runs its hooks with the same contract as Claude Code: its shell tool is
named Bash, tool_input.command is a string, and PreToolUse hookSpecificOutput
additionalContext reaches the model (openai/codex hooks/src/events/
pre_tool_use.rs, core/src/hook_runtime.rs). Codex only had the SessionStart and
SubagentStart reminders (#330), so its grep and rg calls never got the graph
context Claude Code's searches get (#715).
- config.toml: the managed block adds [[hooks.PreToolUse]] matcher = "Bash"
running the same hook-augment command. The previous block (lifecycle pair
only, as installs up to v0.12 wrote it) stays recognized as owned, so an
upgrade replaces it in place and uninstall removes either generation.
- Inline forms (#1432): Codex's inline rewrite of our PreToolUse is replaced.
A user's own inline hooks.PreToolUse is kept and our block then leaves
PreToolUse out, because TOML cannot hold an inline array and array-of-tables
entries for the same key; install says so instead of failing.
- hooks.json: the Codex-only PreToolUse Bash entry is added and removed next to
the lifecycle pair, touching only the entry whose command is ours.
Codex asks users to re-trust changed hook definitions (/hooks).
Refs #715, #509
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
A RETURN made only of aggregates is one group over the whole input, so it
answers exactly one row. The RETURN aggregation sink emitted one row per
group it had seen, and when MATCH/WHERE produced no bindings it had seen
none: `MATCH (f:Function) WHERE f.name = "nope" RETURN count(*) AS total`
answered no rows instead of total = 0.
ret_sink_finish now emits that row when no group was created and every
RETURN item is an aggregate: count and sum are 0, collect is [], and
avg/min/max are null (""). A grouped aggregation over empty input still
returns no rows, and the row goes through the usual DISTINCT / ORDER BY /
SKIP / LIMIT post-pass.
Fixes#2742
Signed-off-by: Gaurav Dubey <gauravdubey0107@gmail.com>
.comp, .geom, .tesc and .tese are the glslang stage extensions next to the
already-mapped .vert and .frag; Vulkan compute shaders were not indexed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Leonardo trindade miranda <tmonestudio@gmail.com>
Signed-off-by: mbrl <mbrl@local>
Martin Vogel
harshitaajoshi
Kris
Mukkara Rithvik Reddy
Petteri Ponsimaa
Gaurav Dubey
dependabot[bot]
Leonardo trindade mirandaandClaude Opus 5.5