mirror of
https://github.com/anthropics/claude-plugins-official.git
synced 2026-07-16 20:33:30 +00:00
Compare commits
1 Commits
venv-failu
...
bump/plugi
| Author | SHA1 | Date | |
|---|---|---|---|
|
4f2543cbe7 |
@@ -120,7 +120,7 @@
|
||||
"url": "https://github.com/awslabs/agent-plugins.git",
|
||||
"path": "plugins/amazon-location-service",
|
||||
"ref": "main",
|
||||
"sha": "9d46cc0a092c0a8c01a5bd06a4349985cc6c8f08"
|
||||
"sha": "f16aaf2a4ec7d59963c4fdf91e7358bd485e992e"
|
||||
},
|
||||
"homepage": "https://github.com/awslabs/agent-plugins"
|
||||
},
|
||||
@@ -245,7 +245,7 @@
|
||||
"url": "https://github.com/auth0/agent-skills.git",
|
||||
"path": "plugins/auth0",
|
||||
"ref": "main",
|
||||
"sha": "c38453f6a99bbfeaf73b5be81db987ec6af982da"
|
||||
"sha": "a4fdd4d0605239aa7be75a57371f4e7e71efc40c"
|
||||
},
|
||||
"homepage": "https://auth0.com/docs/quickstart/agent-skills"
|
||||
},
|
||||
@@ -346,7 +346,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/microsoft/azure-skills.git",
|
||||
"sha": "7cb89c221ecc9eccb71580aaff3695408cdeef2b"
|
||||
"sha": "d3440b8a4f138585a512ecd4e0c54ede13ab1cc2"
|
||||
},
|
||||
"homepage": "https://github.com/microsoft/azure-skills"
|
||||
},
|
||||
@@ -474,7 +474,7 @@
|
||||
"url": "https://github.com/carta/plugins.git",
|
||||
"path": "plugins/carta-investors",
|
||||
"ref": "main",
|
||||
"sha": "e66d331cd8e669ee121c96ee35b0c91acd828970"
|
||||
"sha": "f512df80dd54fd0a607ece2f18a9d226ca705019"
|
||||
},
|
||||
"homepage": "https://carta.com"
|
||||
},
|
||||
@@ -490,7 +490,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/cap-js/mcp-server.git",
|
||||
"sha": "92dc99f5ba0c56957ed5d390484693a69ebd1206"
|
||||
"sha": "9658cea90c782a6ab007ac16278c90fa4feca0ed"
|
||||
},
|
||||
"homepage": "https://cap.cloud.sap/"
|
||||
},
|
||||
@@ -716,7 +716,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/CodSpeedHQ/codspeed.git",
|
||||
"sha": "407dd3c930b8dc5e5655a2d91a65d88f01829955"
|
||||
"sha": "f79d57d207f039e44a31a976564715f7731e71b6"
|
||||
},
|
||||
"homepage": "https://codspeed.io"
|
||||
},
|
||||
@@ -753,7 +753,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/get-convex/convex-backend-skill.git",
|
||||
"sha": "ece93250d560f0ce32a24223dea92b33050b2a66"
|
||||
"sha": "002f9c834cdb834ddef1e4867d87cb6e80f0acba"
|
||||
},
|
||||
"homepage": "https://github.com/get-convex/convex-backend-skill",
|
||||
"keywords": [
|
||||
@@ -784,7 +784,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/CrowdStrike/foundry-skills.git",
|
||||
"sha": "fb25d60ecdbc0129071802dad210a65168ca55a9"
|
||||
"sha": "2908d2f470f14f58d378b26c2af58825fa8d0149"
|
||||
},
|
||||
"homepage": "https://github.com/CrowdStrike/foundry-skills"
|
||||
},
|
||||
@@ -878,7 +878,7 @@
|
||||
"url": "https://github.com/awslabs/agent-plugins.git",
|
||||
"path": "plugins/databases-on-aws",
|
||||
"ref": "main",
|
||||
"sha": "9d46cc0a092c0a8c01a5bd06a4349985cc6c8f08"
|
||||
"sha": "f16aaf2a4ec7d59963c4fdf91e7358bd485e992e"
|
||||
},
|
||||
"homepage": "https://github.com/awslabs/agent-plugins"
|
||||
},
|
||||
@@ -946,7 +946,7 @@
|
||||
"url": "https://github.com/awslabs/agent-plugins.git",
|
||||
"path": "plugins/deploy-on-aws",
|
||||
"ref": "main",
|
||||
"sha": "9d46cc0a092c0a8c01a5bd06a4349985cc6c8f08"
|
||||
"sha": "f16aaf2a4ec7d59963c4fdf91e7358bd485e992e"
|
||||
},
|
||||
"homepage": "https://github.com/awslabs/agent-plugins"
|
||||
},
|
||||
@@ -1114,7 +1114,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/firecrawl/firecrawl-claude-plugin.git",
|
||||
"sha": "e71cec486062680f0c8f8823afcb3558ad81ce60"
|
||||
"sha": "81178096fa7ae860285923948b8ba13d03c7fa0c"
|
||||
},
|
||||
"homepage": "https://github.com/firecrawl/firecrawl-claude-plugin.git"
|
||||
},
|
||||
@@ -1217,7 +1217,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/huggingface/skills.git",
|
||||
"sha": "df627be1837523c91ac6df472e3dc543d3107bd9"
|
||||
"sha": "49abf82b2ef2ff2bcc6ca072aac0fe8627390a1d"
|
||||
},
|
||||
"homepage": "https://github.com/huggingface/skills.git"
|
||||
},
|
||||
@@ -1231,7 +1231,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/hunter-io/claude-plugin.git",
|
||||
"sha": "9b6146520c48f9dcc6092f106e5c1a5762ca3e7a"
|
||||
"sha": "4eb5fbbcb75e0c4c4f2c0d8aa02756165fdde629"
|
||||
},
|
||||
"homepage": "https://hunter.io"
|
||||
},
|
||||
@@ -1245,7 +1245,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/heygen-com/hyperframes.git",
|
||||
"sha": "bc3701f5905c5ba7c8cf03c3bbe3a49162d2b1f1"
|
||||
"sha": "f8abff2e1c0958b61419b4d2ad91ceca7a7ea110"
|
||||
},
|
||||
"homepage": "https://hyperframes.heygen.com"
|
||||
},
|
||||
@@ -1653,22 +1653,6 @@
|
||||
},
|
||||
"homepage": "https://github.com/makenotion/claude-code-notion-plugin"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-skills",
|
||||
"description": "NVIDIA agent skills for accelerated-computing workflows — starting with cuOpt vehicle-routing optimization (VRP, TSP, PDP) via the cuOpt Python API.",
|
||||
"author": {
|
||||
"name": "NVIDIA"
|
||||
},
|
||||
"category": "development",
|
||||
"source": {
|
||||
"source": "git-subdir",
|
||||
"url": "https://github.com/NVIDIA/skills.git",
|
||||
"path": "plugins/nvidia-skills",
|
||||
"ref": "main",
|
||||
"sha": "62b685a20ac45285cafd1e22782abbed33172c17"
|
||||
},
|
||||
"homepage": "https://github.com/NVIDIA/skills"
|
||||
},
|
||||
{
|
||||
"name": "oracle-ai-data-platform-workbench-spark-connectors",
|
||||
"description": "Oracle AI Data Platform Workbench Spark connectors for Claude Code. 18 connector skills covering every data source workbench customers commonly need: Oracle Autonomous DB family (ALH/ADW/ATP) via wallet/IAM-DB-Token/API-key, ExaCS, Fusion ERP REST, Fusion BICC, EPM Cloud Planning, Essbase 21c, OCI Streaming (Kafka), OCI Object Storage, Apache Iceberg, plus external systems (PostgreSQL, MySQL/HeatWave, SQL Server, Snowflake, Azure ADLS Gen2, AWS S3, generic REST, custom JDBC, Excel). Live-validated on the workbench `tpcds` cluster (Spark 3.5.0): 17 PASS / 4 ship-as-is out of 21 test rows.",
|
||||
@@ -1681,7 +1665,7 @@
|
||||
"url": "https://github.com/oracle-samples/oracle-aidp-samples.git",
|
||||
"path": "ai/claude-code-plugins/oracle-ai-data-platform-workbench-spark-connectors",
|
||||
"ref": "main",
|
||||
"sha": "6e59f24cd3e8870649e7f9b2e3e106502b43fd5f"
|
||||
"sha": "d20075e440af2a209bc3b011a336276336e6d10c"
|
||||
},
|
||||
"homepage": "https://docs.oracle.com/en/cloud/paas/ai-data-platform/index.html"
|
||||
},
|
||||
@@ -1697,7 +1681,7 @@
|
||||
"url": "https://github.com/growthxai/output.git",
|
||||
"path": "coding_assistants/claude/plugins/outputai",
|
||||
"ref": "main",
|
||||
"sha": "0eeffece25b6f471c48b705a214471164b8c5946"
|
||||
"sha": "5a87ebc13343ce6ebabac0bcc443c1da0bcf2459"
|
||||
},
|
||||
"homepage": "https://output.ai"
|
||||
},
|
||||
@@ -1745,7 +1729,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/gopigment/ai-plugins.git",
|
||||
"sha": "4bf16c80558416b9d69fa6531af8588fb2fcbe27"
|
||||
"sha": "abf36e64750d1323a4cc5fe79161597668231224"
|
||||
},
|
||||
"homepage": "https://www.pigment.com"
|
||||
},
|
||||
@@ -2001,7 +1985,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/Digital-Process-Tools/claude-remember.git",
|
||||
"sha": "c2c82ab5fd2f4f5c0cddc9c7d8a749655dec4cb9"
|
||||
"sha": "a4ff96f38622f7c4920dc349d59cc980663336f4"
|
||||
},
|
||||
"homepage": "https://github.com/Digital-Process-Tools/claude-remember"
|
||||
},
|
||||
@@ -2129,7 +2113,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/cap-js/mcp-server.git",
|
||||
"sha": "92dc99f5ba0c56957ed5d390484693a69ebd1206"
|
||||
"sha": "9658cea90c782a6ab007ac16278c90fa4feca0ed"
|
||||
},
|
||||
"homepage": "https://cap.cloud.sap/"
|
||||
},
|
||||
@@ -2147,7 +2131,7 @@
|
||||
"url": "https://github.com/SAP/open-ux-tools.git",
|
||||
"path": "packages/fiori-mcp-server",
|
||||
"ref": "main",
|
||||
"sha": "7432d23a7b5c3bd1c0a01cf76696bf0c417ecd1f"
|
||||
"sha": "c3e0940ef29ac520b4cc5bd6fd71fecede7b3342"
|
||||
},
|
||||
"homepage": "https://github.com/SAP/open-ux-tools/tree/main/packages/fiori-mcp-server"
|
||||
},
|
||||
@@ -2186,7 +2170,7 @@
|
||||
{
|
||||
"name": "security-guidance",
|
||||
"description": "Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.",
|
||||
"version": "2.0.2",
|
||||
"version": "2.0.0",
|
||||
"author": {
|
||||
"name": "Anthropic",
|
||||
"email": "support@anthropic.com"
|
||||
@@ -2214,7 +2198,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/getsentry/sentry-for-claude.git",
|
||||
"sha": "d6123be331e2224b037e1ffefd27c806e7566dcf"
|
||||
"sha": "849303a8411c242d250885ffe714235a3bc2f5fe"
|
||||
},
|
||||
"homepage": "https://github.com/getsentry/sentry-for-claude/tree/main"
|
||||
},
|
||||
@@ -2230,7 +2214,7 @@
|
||||
"url": "https://github.com/getsentry/cli.git",
|
||||
"path": "plugins/sentry-cli",
|
||||
"ref": "main",
|
||||
"sha": "db90767935558db16c45036f89e68edaa1dde106"
|
||||
"sha": "213c156a47fb2952287938f91e94b5073402530d"
|
||||
},
|
||||
"homepage": "https://sentry.io"
|
||||
},
|
||||
@@ -2427,7 +2411,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/obra/superpowers.git",
|
||||
"sha": "f2cbfbefebbfef77321e4c9abc9e949826bea9d7"
|
||||
"sha": "6fd4507659784c351abbd2bc264c7162cfd386dc"
|
||||
},
|
||||
"homepage": "https://github.com/obra/superpowers.git"
|
||||
},
|
||||
@@ -2461,7 +2445,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/JetBrains/teamcity-cli.git",
|
||||
"sha": "9436b94b228579ba952aba809357776c3db9ce1a"
|
||||
"sha": "533c8cb20928be912188fd8ae40fcba24cc720ca"
|
||||
},
|
||||
"homepage": "https://www.jetbrains.com/teamcity/"
|
||||
},
|
||||
@@ -2636,7 +2620,7 @@
|
||||
"source": {
|
||||
"source": "url",
|
||||
"url": "https://github.com/wix/skills.git",
|
||||
"sha": "c5b343f2dadba06da91ee6de07272161fb68d40d"
|
||||
"sha": "357f8d5b7cd81455e6a57cc64dba83985131d78f"
|
||||
},
|
||||
"homepage": "https://dev.wix.com/docs/wix-cli/guides/development/about-wix-skills"
|
||||
},
|
||||
|
||||
81
.github/workflows/bump-plugin-shas.yml
vendored
81
.github/workflows/bump-plugin-shas.yml
vendored
@@ -2,24 +2,25 @@ name: Bump Plugin SHAs
|
||||
|
||||
# Nightly sweep: for each external entry whose upstream HEAD has moved past
|
||||
# its pinned SHA, validate at the new SHA with `claude plugin validate`
|
||||
# inline, then open one PR per bumped plugin on branch `bump/<slug>`.
|
||||
# Failing entries stay isolated in their own PR; passing bumps merge
|
||||
# independently.
|
||||
# inline, then open one PR with all passing bumps. Each run force-resets the
|
||||
# bump/plugin-shas branch, so a previous night's unmerged PR is replaced (and
|
||||
# its review state discarded) — review and merge same-day to avoid churn.
|
||||
#
|
||||
# Bot-free — uses the default GITHUB_TOKEN. PRs opened with GITHUB_TOKEN don't
|
||||
# trigger on:pull_request workflows, so the required status checks on main
|
||||
# (`scan` from Scan Plugins, `check` from Check MCP URLs, `validate` from
|
||||
# Validate Plugins) would never run and the bump PR could never merge.
|
||||
# workflow_dispatch is exempt from that recursion guard, so we dispatch all
|
||||
# three ourselves against each per-entry bump branch after its PR is opened.
|
||||
# Each check run lands on the branch HEAD — the same SHA as the PR head — and
|
||||
# satisfies the corresponding required check. (Each of those workflows runs
|
||||
# its job unconditionally on workflow_dispatch, so a dispatch always reports.)
|
||||
# trigger on:pull_request workflows, so the policy scan (`Scan Plugins`, a
|
||||
# required status check on main) would never run and the bump PR could never
|
||||
# merge. workflow_dispatch is exempt from that recursion guard, so we dispatch
|
||||
# the scan ourselves on the bump branch after the PR is opened. The check run
|
||||
# lands on the branch HEAD — the same SHA as the PR head — and satisfies the
|
||||
# required check.
|
||||
#
|
||||
# max-bumps caps the per-night work for cost control. Per-entry scans are
|
||||
# more expensive than a single batched scan, so the cap is conservative.
|
||||
# The composite action skips entries that already have an open bump PR, so
|
||||
# re-dispatches don't pile up duplicate work.
|
||||
# max-bumps is set above the external-entry count so a single run can clear
|
||||
# any backlog. The cost-control mechanisms are downstream:
|
||||
# - scan-plugins.yml caches verdicts by (plugin, sha) so an unchanged SHA
|
||||
# is never re-scanned across nightly force-resets.
|
||||
# - revert-failed-bumps.yml drops policy-failing entries from the bump PR
|
||||
# so one bad upstream can't block the rest.
|
||||
# See those files for details.
|
||||
|
||||
on:
|
||||
schedule:
|
||||
@@ -29,12 +30,12 @@ on:
|
||||
max_bumps:
|
||||
description: Cap on plugins bumped this run
|
||||
required: false
|
||||
default: '30'
|
||||
default: '130'
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: write
|
||||
actions: write # gh workflow run {scan-plugins,check-mcp-urls,validate-plugins}.yml per bump branch
|
||||
actions: write # gh workflow run scan-plugins.yml on the bump branch
|
||||
|
||||
concurrency:
|
||||
group: bump-plugin-shas
|
||||
@@ -42,8 +43,8 @@ concurrency:
|
||||
jobs:
|
||||
bump:
|
||||
runs-on: ubuntu-latest
|
||||
# Per-bump cost is ~2s (ls-remote + shallow clone + validate); 30 entries
|
||||
# is ~1-2 min. The 60 min ceiling absorbs slow upstreams without letting a
|
||||
# Per-bump cost is ~2s (ls-remote + shallow clone + validate); 130 entries
|
||||
# is ~5 min. The 60 min ceiling absorbs slow upstreams without letting a
|
||||
# pathological run consume the default 360 min budget.
|
||||
timeout-minutes: 60
|
||||
steps:
|
||||
@@ -51,44 +52,18 @@ jobs:
|
||||
|
||||
# createCommitOnBranch-based bump so commits are signed by GitHub and
|
||||
# satisfy the org-level required_signatures ruleset on main.
|
||||
- uses: anthropics/claude-plugins-community/.github/actions/bump-plugin-shas@e2019b2a01f11aa1484c53540b1cfab5eebbc299
|
||||
- uses: anthropics/claude-plugins-community/.github/actions/bump-plugin-shas@c41c6911de0afffd2bc5cd8b21fb1e06444ee13b
|
||||
id: bump
|
||||
with:
|
||||
marketplace-path: .claude-plugin/marketplace.json
|
||||
max-bumps: ${{ inputs.max_bumps || '30' }}
|
||||
pr-mode: per-entry
|
||||
max-bumps: ${{ inputs.max_bumps || '130' }}
|
||||
claude-cli-version: latest
|
||||
|
||||
# Per-entry fan-out: dispatch the three required checks against each bump
|
||||
# branch. `pr-urls` is a JSON array of {name, old_sha, new_sha, branch,
|
||||
# pr_url} entries emitted by the composite action when pr-mode is
|
||||
# per-entry. All three (scan / check / validate) are required on main and
|
||||
# none fire on the GITHUB_TOKEN-opened PR, so each must be dispatched.
|
||||
# A single failed dispatch (transient API error / rate limit) must not
|
||||
# strand the remaining branches, so we attempt every dispatch, then fail
|
||||
# the step if any failed: a missing required check would otherwise leave
|
||||
# its bump PR silently blocked behind a green run, and the composite
|
||||
# action skips slugs with an open PR so it would never be retried.
|
||||
- name: Dispatch required checks per per-entry PR
|
||||
if: steps.bump.outputs.pr-urls != '' && steps.bump.outputs.pr-urls != '[]'
|
||||
# `bump/plugin-shas` is the action's default `pr-branch`. The scan diffs
|
||||
# the branch against origin/main (the action's base-ref fallback when
|
||||
# there's no pull_request event) and scans only the bumped entries.
|
||||
- name: Dispatch policy scan on bump branch
|
||||
if: steps.bump.outputs.pr-url != ''
|
||||
env:
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
PR_URLS: ${{ steps.bump.outputs.pr-urls }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
dispatch_failures="$(mktemp)"
|
||||
jq -c '.[]' <<<"$PR_URLS" | while read -r entry; do
|
||||
branch=$(jq -r '.branch' <<<"$entry")
|
||||
name=$(jq -r '.name' <<<"$entry")
|
||||
for wf in scan-plugins check-mcp-urls validate-plugins; do
|
||||
echo "Dispatching ${wf}.yml against $branch ($name)"
|
||||
if ! gh workflow run "${wf}.yml" --ref "$branch"; then
|
||||
echo "::error::Failed to dispatch ${wf}.yml against $branch ($name) — required check will be missing; re-dispatch with: gh workflow run ${wf}.yml --ref $branch"
|
||||
echo "${wf} ${branch}" >> "$dispatch_failures"
|
||||
fi
|
||||
done
|
||||
done
|
||||
if [ -s "$dispatch_failures" ]; then
|
||||
echo "::error::$(wc -l < "$dispatch_failures" | tr -d ' ') required-check dispatch(es) failed; the affected bump PR(s) are blocked until re-dispatched (see annotations above)."
|
||||
exit 1
|
||||
fi
|
||||
run: gh workflow run scan-plugins.yml --ref bump/plugin-shas
|
||||
|
||||
8
.github/workflows/validate-plugins.yml
vendored
8
.github/workflows/validate-plugins.yml
vendored
@@ -12,14 +12,6 @@ on:
|
||||
branches: [main]
|
||||
paths:
|
||||
- '.claude-plugin/**'
|
||||
# `validate` is a required status check on main. Bump PRs are opened with
|
||||
# GITHUB_TOKEN, which doesn't fire on:pull_request (recursion guard), so the
|
||||
# path-filtered trigger above never reports on them and the PR would be
|
||||
# blocked forever. The bump workflow dispatches this against each per-entry
|
||||
# bump branch instead; the check run lands on the branch HEAD (= PR head)
|
||||
# and satisfies the required check. The validate job runs unconditionally,
|
||||
# so a dispatch always reports.
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "security-guidance",
|
||||
"version": "2.0.2",
|
||||
"version": "2.0.0",
|
||||
"description": "Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.",
|
||||
"author": {
|
||||
"name": "David Dworken",
|
||||
|
||||
@@ -116,18 +116,7 @@ _PV = _read_plugin_version_int()
|
||||
# Emitted via _usage_metrics() into the existing emit_metrics() channel so
|
||||
# hook metrics rows carry per-invocation token/cost totals
|
||||
# alongside the existing skip_reason / vulns_found fields.
|
||||
_USAGE = {
|
||||
"in": 0, "out": 0, "cr": 0, "cw": 0, "cost": 0.0, "n": 0,
|
||||
# HTTP error visibility (#2098 visibility gap — see emit comment in
|
||||
# _usage_metrics). Without this, API failures from `_call_claude` left
|
||||
# zero fingerprint in telemetry: the call returns None, the caller's
|
||||
# emit_metrics carries no api_calls field, and the failure is
|
||||
# indistinguishable from "no review needed". The deprecation outage
|
||||
# that broke every commit-review LLM call was invisible until users
|
||||
# reported it manually.
|
||||
"http_err_last": 0, # most recent HTTP error code this invocation
|
||||
"http_err_count": 0, # total HTTP errors (4xx + 5xx + network)
|
||||
}
|
||||
_USAGE = {"in": 0, "out": 0, "cr": 0, "cw": 0, "cost": 0.0, "n": 0}
|
||||
_USAGE_LOCK = threading.Lock()
|
||||
|
||||
# $/Mtok (input, output). Used only for the raw-HTTP path; the SDK path
|
||||
@@ -177,55 +166,19 @@ def _record_usage(usage, model, cost_usd=None):
|
||||
_USAGE["n"] += 1
|
||||
|
||||
|
||||
def _record_http_error(status):
|
||||
"""Record an HTTP error from an LLM API call. `status` is the HTTP
|
||||
status code (integer 400–599) or -1 for network/timeout errors. Stored
|
||||
in `_USAGE["http_err_last"]` (most recent) and counted in
|
||||
`_USAGE["http_err_count"]`. Snapshot via `_usage_metrics()` so every
|
||||
subsequent `emit_metrics` includes the failure fingerprint.
|
||||
|
||||
Background: without this, the most recent example was the #2098
|
||||
deprecation 400. Every hook fire's LLM call returned HTTP 400; the
|
||||
plugin caught it and returned None; the emit_metrics carried no
|
||||
api_calls field; aggregate dashboards looked normal. The failure
|
||||
only became visible when a user manually reported errors out of
|
||||
their debug log. With this field, a category-of-failure spike (4xx,
|
||||
5xx, or -1 network) is queryable from BQ in real time.
|
||||
"""
|
||||
try:
|
||||
s = int(status)
|
||||
except (TypeError, ValueError):
|
||||
return
|
||||
with _USAGE_LOCK:
|
||||
_USAGE["http_err_last"] = s
|
||||
_USAGE["http_err_count"] += 1
|
||||
|
||||
|
||||
def _usage_metrics():
|
||||
"""Snapshot the accumulator as metric keys. Returns {} when no API calls
|
||||
AND no HTTP errors were made so skip-path emits don't burn key budget.
|
||||
cost_usd rounded to 1e-6 to keep the float finite/short for the zod
|
||||
schema.
|
||||
|
||||
HTTP errors (`http_err_last`, `http_err_count`) emitted ONLY when
|
||||
`http_err_count > 0` so successful calls don't pad every metrics row
|
||||
with two zero fields.
|
||||
"""
|
||||
were made so skip-path emits don't burn key budget. cost_usd rounded to
|
||||
1e-6 to keep the float finite/short for the zod schema."""
|
||||
with _USAGE_LOCK:
|
||||
if _USAGE["n"] == 0 and _USAGE["http_err_count"] == 0:
|
||||
if _USAGE["n"] == 0:
|
||||
return {}
|
||||
out = {}
|
||||
if _USAGE["n"] > 0:
|
||||
out.update({
|
||||
"tok_in": _USAGE["in"],
|
||||
"tok_out": _USAGE["out"],
|
||||
"tok_cache_r": _USAGE["cr"],
|
||||
"tok_cache_w": _USAGE["cw"],
|
||||
"cost_usd": round(_USAGE["cost"], 6),
|
||||
"api_calls": _USAGE["n"],
|
||||
})
|
||||
if _USAGE["http_err_count"] > 0:
|
||||
out["http_err_last"] = _USAGE["http_err_last"]
|
||||
out["http_err_count"] = _USAGE["http_err_count"]
|
||||
return out
|
||||
return {
|
||||
"tok_in": _USAGE["in"],
|
||||
"tok_out": _USAGE["out"],
|
||||
"tok_cache_r": _USAGE["cr"],
|
||||
"tok_cache_w": _USAGE["cw"],
|
||||
"cost_usd": round(_USAGE["cost"], 6),
|
||||
"api_calls": _USAGE["n"],
|
||||
}
|
||||
|
||||
|
||||
@@ -42,122 +42,6 @@ HOOK_PY_INCOMPATIBLE = 6 # hook interpreter is <3.10 — SDK syntax can't load
|
||||
# here no matter how the venv was built. See #2071.
|
||||
|
||||
|
||||
# Phase + err-kind integer encoding for sdk_bootstrap_phase / sdk_bootstrap_err.
|
||||
#
|
||||
# Earlier versions emitted these as STRINGS (e.g. "pip", "dns_fail"). CC's
|
||||
# plugin-metrics pipeline silently drops plugin-emitted string values —
|
||||
# only `bool|finite-number` plugin metrics reach BigQuery. (CC-core
|
||||
# metrics like `subscription_type` are exempt because they're injected
|
||||
# downstream of plugin validation.) Confirmed empirically: 185K
|
||||
# BUILD_FAILED rows in BQ had `sdk_bootstrap_phase`/`sdk_bootstrap_err`
|
||||
# = NULL despite the Python code emitting them. This left ~28K
|
||||
# BUILD_FAILED sessions/day with no diagnostic split — flying blind on
|
||||
# the real failure modes (pip-no-match vs dns-fail vs ssl-verify etc.).
|
||||
#
|
||||
# Fix: encode as small integers per the maps below. Values are
|
||||
# APPEND-ONLY for telemetry stability. Reserve 99 as the "unknown /
|
||||
# uncategorized" bucket so an unmapped err_kind (e.g., a new exception
|
||||
# type) still emits a non-zero signal.
|
||||
SDK_BOOTSTRAP_PHASE_CODES = {
|
||||
"pre": 1, # pre-venv (state_dir.mkdir, sentinel open)
|
||||
"venv": 2, # python -m venv --clear
|
||||
"pip": 3, # pip install
|
||||
"main": 4, # uncaught exception above main()
|
||||
}
|
||||
SDK_BOOTSTRAP_ERR_CODES = {
|
||||
"pip_no_match": 1,
|
||||
"dns_fail": 2,
|
||||
"conn_refused": 3,
|
||||
"ssl_verify": 4,
|
||||
"perm_denied": 5,
|
||||
"no_pip": 6,
|
||||
"disk_full": 7,
|
||||
"proxy_auth": 8,
|
||||
"stderr_timeout": 9, # pip stderr containing "timeout"/"timed out"
|
||||
"subprocess_timeout": 10, # subprocess.TimeoutExpired (>120s)
|
||||
# Venv-stage specific categories added after PR #2112 telemetry surfaced
|
||||
# 2,406 phase=2/err=99 sessions in the first 3h of v2.0.1 — venv phase
|
||||
# failing in ways the original pip-flavored patterns didn't catch. These
|
||||
# all split out of what was previously collapsing to _uncategorized.
|
||||
"venv_ensurepip_fail": 11, # Debian/Ubuntu missing python3-venv;
|
||||
# stderr mentions ensurepip non-zero exit
|
||||
# or "ensurepip is not available"
|
||||
"venv_path_too_long": 12, # Windows MAX_PATH (260) or POSIX
|
||||
# ENAMETOOLONG — venv writes deep paths
|
||||
# under state_dir/agent-sdk-venv/Lib/...
|
||||
"venv_no_module": 13, # `python3 -m venv` itself missing — "No
|
||||
# module named 'venv'" / "No module named venv"
|
||||
"venv_already_exists": 14, # Errno 17 / "file exists" — sentinel race
|
||||
# past O_EXCL or stale dir survived --clear
|
||||
"venv_setup_failed": 15, # Generic "virtual environment was not
|
||||
# created successfully" — catches the long
|
||||
# tail of venv setup failures that don't
|
||||
# match a more specific category above
|
||||
# 16–98 reserved for future categories; APPEND-ONLY.
|
||||
# 99 catches everything else (including "exc:<TypeName>" and "other:<tail>"
|
||||
# — the original string is debug-loggable but the integer is what makes
|
||||
# it to telemetry). For the "other:" tail, `sdk_bootstrap_stderr_sig`
|
||||
# carries a bounded integer hash so we can still distinguish patterns
|
||||
# in BQ aggregation.
|
||||
"_uncategorized": 99,
|
||||
}
|
||||
|
||||
|
||||
def _encode_phase(s):
|
||||
"""Map err_phase string to its telemetry integer code, or 0 if unset.
|
||||
Empty/None → 0 lets `if encoded:` cleanly skip emission. Per
|
||||
SDK_BOOTSTRAP_PHASE_CODES, valid codes are 1-4."""
|
||||
return SDK_BOOTSTRAP_PHASE_CODES.get((s or "").strip(), 0)
|
||||
|
||||
|
||||
def _encode_err_kind(s):
|
||||
"""Map err_kind string to its telemetry integer code, or 0 if unset.
|
||||
Direct hits use the static map; "exc:<X>" and "other:<tail>" both
|
||||
collapse to _uncategorized (99) — the raw string survives in debug
|
||||
logs, only the integer reaches BQ."""
|
||||
s = (s or "").strip()
|
||||
if not s:
|
||||
return 0
|
||||
if s in SDK_BOOTSTRAP_ERR_CODES:
|
||||
return SDK_BOOTSTRAP_ERR_CODES[s]
|
||||
# Prefix matches for the catch-all categories
|
||||
if s.startswith("exc:") or s.startswith("other:") or s == "other":
|
||||
return SDK_BOOTSTRAP_ERR_CODES["_uncategorized"]
|
||||
# Unknown string — still emit as uncategorized rather than dropping
|
||||
return SDK_BOOTSTRAP_ERR_CODES["_uncategorized"]
|
||||
|
||||
|
||||
def _encode_stderr_sig(err_kind):
|
||||
"""Bounded integer hash of the stderr tail captured in "other:<tail>"
|
||||
err_kinds. Lets us distinguish patterns INSIDE the _uncategorized
|
||||
(code 99) bucket without unbounded cardinality.
|
||||
|
||||
Returns 0 for non-"other:" err_kinds (so the field auto-omits from
|
||||
emit_metrics on categorized failures — see the emit block in main()).
|
||||
|
||||
Strategy: take the tail's first ~30 chars (post-lowercase, post-trim),
|
||||
SHA-1, fold the first 2 bytes to 0–999. Different stderr messages
|
||||
cluster into different buckets; same stderr always maps to the same
|
||||
bucket. Cardinality is bounded at 1000, well below any "high
|
||||
cardinality" alarm — and a real failure mode typically produces
|
||||
near-identical stderr across thousands of machines, so 1000 buckets
|
||||
is comfortably wide.
|
||||
|
||||
Why first ~30 chars: stderr like "ERROR: Command failed: <full
|
||||
path>" varies the tail wildly (paths) but the categorization signal
|
||||
is in the leading words. Dropping the suffix focuses the hash on
|
||||
the discriminative part.
|
||||
"""
|
||||
if not err_kind or not err_kind.startswith("other:"):
|
||||
return 0
|
||||
import hashlib
|
||||
tail = err_kind[len("other:"):].strip().lower()[:30]
|
||||
if not tail:
|
||||
return 0
|
||||
h = hashlib.sha1(tail.encode("utf-8", errors="replace")).digest()
|
||||
return int.from_bytes(h[:2], "big") % 1000
|
||||
|
||||
|
||||
def _sdk_on_syspath() -> bool:
|
||||
# find_spec is ~10ms; actually importing the SDK pulls in
|
||||
# transitive deps and costs ~800ms — too heavy for a
|
||||
@@ -296,34 +180,7 @@ def main() -> tuple[int, str, str]:
|
||||
else:
|
||||
stderr_str = str(stderr_b)
|
||||
s = stderr_str.lower()
|
||||
# Venv-specific patterns checked FIRST — they overlap with some pip
|
||||
# patterns (e.g. "no module named ensurepip" could match no_pip OR
|
||||
# venv_ensurepip_fail; the venv-stage interpretation is the right
|
||||
# one when err_phase=="venv"). Order is venv-most-specific →
|
||||
# pip-historical → generic.
|
||||
if err_phase == "venv" and (
|
||||
"ensurepip is not available" in s
|
||||
or ("ensurepip" in s and "returned non-zero" in s)
|
||||
or "the virtual environment was not created" in s and "ensurepip" in s
|
||||
):
|
||||
err_kind = "venv_ensurepip_fail"
|
||||
elif err_phase == "venv" and (
|
||||
"[errno 36]" in s
|
||||
or "file name too long" in s
|
||||
or "path too long" in s
|
||||
):
|
||||
err_kind = "venv_path_too_long"
|
||||
elif err_phase == "venv" and (
|
||||
"no module named venv" in s
|
||||
or "no module named 'venv'" in s
|
||||
):
|
||||
err_kind = "venv_no_module"
|
||||
elif err_phase == "venv" and (
|
||||
"[errno 17]" in s
|
||||
or ("file exists" in s and "venv" in s)
|
||||
):
|
||||
err_kind = "venv_already_exists"
|
||||
elif "no matching distribution" in s or "could not find a version" in s:
|
||||
if "no matching distribution" in s or "could not find a version" in s:
|
||||
err_kind = "pip_no_match"
|
||||
elif "name or service not known" in s or "name resolution" in s \
|
||||
or "nodename nor servname" in s or "temporary failure in name" in s:
|
||||
@@ -342,15 +199,6 @@ def main() -> tuple[int, str, str]:
|
||||
err_kind = "proxy_auth"
|
||||
elif "timeout" in s or "timed out" in s:
|
||||
err_kind = "stderr_timeout"
|
||||
elif err_phase == "venv" and (
|
||||
"virtual environment was not created" in s
|
||||
or "error: command" in s and "venv" in s
|
||||
):
|
||||
# Generic venv-setup catch-all — matched AFTER the more specific
|
||||
# venv patterns above so we don't shadow them, but BEFORE the
|
||||
# other: fallback so generic venv setup failures get their own
|
||||
# bucket instead of polluting the long-tail signature space.
|
||||
err_kind = "venv_setup_failed"
|
||||
else:
|
||||
# First 60 chars of the last non-empty stderr line — bounded to
|
||||
# stay inside CC's metric value-length budget. Real failure modes
|
||||
@@ -440,33 +288,21 @@ if __name__ == "__main__":
|
||||
# and takes the FIRST non-{"async":...} JSON line as the hook response;
|
||||
# its `metrics` key is forwarded to the hook metrics event on the
|
||||
# next attachments pass. Must be a single line — the registry splits on
|
||||
# \n and json-parses each independently.
|
||||
#
|
||||
# IMPORTANT — values must be bool|finite-number. The validation comment
|
||||
# has historically said "or short strings" but that was wrong: CC's
|
||||
# plugin-metrics pipeline silently drops plugin-emitted string values.
|
||||
# Stay inside the 10-key emit cap.
|
||||
# \n and json-parses each independently. Values must be bool|number OR
|
||||
# short strings (CC accepts string metric values if they're not
|
||||
# null). Stay inside the 10-key emit cap.
|
||||
metrics: dict[str, object] = {
|
||||
"sdk_bootstrap": outcome,
|
||||
"sdk_bootstrap_ms": round((time.perf_counter() - t0) * 1000),
|
||||
}
|
||||
if err_kind:
|
||||
# Encode phase + err_kind as integer codes (see
|
||||
# SDK_BOOTSTRAP_PHASE_CODES / SDK_BOOTSTRAP_ERR_CODES). Earlier
|
||||
# versions emitted these as strings and CC dropped them — restoring
|
||||
# the diagnostic split that 28K BUILD_FAILED/day need to triage by
|
||||
# root cause. err_phase defaults to "pre" when empty (pre-venv
|
||||
# failure path, e.g. state_dir.mkdir perm-denied).
|
||||
metrics["sdk_bootstrap_phase"] = _encode_phase(err_phase or "pre")
|
||||
metrics["sdk_bootstrap_err"] = _encode_err_kind(err_kind)
|
||||
# For "other:<tail>" (encoded err==99), emit a bounded integer
|
||||
# hash of the stderr tail so BQ can distinguish patterns inside
|
||||
# the _uncategorized bucket without unbounded cardinality. Zero
|
||||
# when err_kind is categorized — the schema reader treats 0 as
|
||||
# "no signal", matching the absence convention.
|
||||
sig = _encode_stderr_sig(err_kind)
|
||||
if sig:
|
||||
metrics["sdk_bootstrap_stderr_sig"] = sig
|
||||
# Truncate defensively; categorized values are <40 chars but the
|
||||
# `other:<tail>` mode could be longer. err_phase may be empty for
|
||||
# pre-venv failures (state_dir.mkdir perm-denied, sentinel O_EXCL
|
||||
# raising a non-FileExistsError OSError) — emit as "pre" so the
|
||||
# err_kind isn't silently dropped.
|
||||
metrics["sdk_bootstrap_phase"] = (err_phase or "pre")[:16]
|
||||
metrics["sdk_bootstrap_err"] = err_kind[:96]
|
||||
pv = _plugin_version_int()
|
||||
if pv:
|
||||
metrics["pv"] = pv
|
||||
|
||||
@@ -27,7 +27,7 @@ from typing import Optional, Tuple, Dict, Any, List
|
||||
|
||||
import extensibility
|
||||
import review_api
|
||||
from _base import debug_log, _record_usage, _record_http_error, _PV, PROVENANCE_TAG, state_dir as _resolve_state_dir # noqa: F401
|
||||
from _base import debug_log, _record_usage, _PV, PROVENANCE_TAG, state_dir as _resolve_state_dir # noqa: F401
|
||||
from session_state import with_locked_state
|
||||
|
||||
|
||||
@@ -368,7 +368,6 @@ def _call_claude_via_sdk(prompt, output_schema, *, max_tokens=16000, model=None)
|
||||
except Exception as e:
|
||||
debug_log(f"3P sdk-single-turn: SDK unavailable ({e})")
|
||||
_last_call_claude_http_error = -1
|
||||
_record_http_error(-1)
|
||||
return None
|
||||
|
||||
cli_path = os.environ.get("SG_AGENTIC_CLI_PATH") or None
|
||||
@@ -426,7 +425,6 @@ def _call_claude_via_sdk(prompt, output_schema, *, max_tokens=16000, model=None)
|
||||
except _asyncio.TimeoutError:
|
||||
debug_log("3P sdk-single-turn: timeout after 60s")
|
||||
_last_call_claude_http_error = -1
|
||||
_record_http_error(-1)
|
||||
return None
|
||||
except Exception as e:
|
||||
debug_log(f"3P sdk-single-turn: query failed ({e})")
|
||||
@@ -435,7 +433,6 @@ def _call_claude_via_sdk(prompt, output_schema, *, max_tokens=16000, model=None)
|
||||
for _l in _captured_stderr[:20]:
|
||||
debug_log(f" | {_l.rstrip()}")
|
||||
_last_call_claude_http_error = -1
|
||||
_record_http_error(-1)
|
||||
return None
|
||||
|
||||
|
||||
@@ -545,7 +542,6 @@ def _call_claude(prompt, output_schema, thinking_budget=10000, max_tokens=16000,
|
||||
error_body = e.read().decode("utf-8") if e.fp else ""
|
||||
debug_log(f"API error: {e.code} - {error_body[:200]}")
|
||||
_last_call_claude_http_error = e.code
|
||||
_record_http_error(e.code)
|
||||
return None
|
||||
except (urllib.error.URLError, TimeoutError) as e:
|
||||
if attempt < 2:
|
||||
@@ -555,7 +551,6 @@ def _call_claude(prompt, output_schema, thinking_budget=10000, max_tokens=16000,
|
||||
else:
|
||||
debug_log(f"Request failed after retries: {e}")
|
||||
_last_call_claude_http_error = -1
|
||||
_record_http_error(-1)
|
||||
return None
|
||||
|
||||
if not response_data:
|
||||
@@ -564,7 +559,6 @@ def _call_claude(prompt, output_schema, thinking_budget=10000, max_tokens=16000,
|
||||
# call uses the token; record the 401 so callers don't see error=None.
|
||||
if _last_call_claude_http_error is None:
|
||||
_last_call_claude_http_error = 401
|
||||
_record_http_error(401)
|
||||
return None
|
||||
|
||||
# Find the text block (skip thinking blocks)
|
||||
|
||||
Reference in New Issue
Block a user