security-guidance: emit schema-valid Stop-hook output (#2159) — 2.0.2 → 2.0.3

Fixes #2159. The Stop hook emits feedback via
`hookSpecificOutput: {hookEventName: "Stop", additionalContext}`, but
`Stop`/`SubagentStop` are NOT members of CC's `hookSpecificOutput`
discriminated union (coreSchemas.ts — valid members are PreToolUse,
PostToolUse, UserPromptSubmit, SessionStart, etc.). So the emitted shape
violates CC's documented hook-output schema.

Impact is CC-version-dependent — important nuance, established empirically:

  - Reporter (array0224-cloud) on CLI 2.1.150 / 2.1.152: CC rejects the
    Stop feedback; the block/reason never reaches the model, so the
    auto-rewake/fix loop is lost. (Detection still runs + logs.)

  - On CLI 2.1.160 (current) the asyncRewake completion path is lenient:
    its gate is `isSyncHookJSONOutput` (hooks.ts) which is just
    `!(json.async === true)` — NOT a strict schema parse. So the invalid
    hookSpecificOutput is tolerated: metrics + rewakeSummary are still
    consumed and the model still receives the findings. I could NOT
    reproduce the rejection on 2.1.160, and BQ confirms Stop-path
    vulns_found metrics are recorded normally (~21k with-vuln fires / 3d),
    i.e. NOT dropped. (An earlier draft of this message claimed metrics
    were dropped — that was wrong; corrected after checking telemetry +
    repro'ing the old plugin on 2.1.160.)

So this is defensive schema-correctness: the plugin should emit output
that conforms to CC's documented union regardless of how strictly a given
CC version validates it. The reporter's environment validates strictly;
relying on the current version's leniency is fragile.

Fix (CC's documented asyncRewake "clean pattern" — hooks.ts: "error text
on stderr, JSON on stdout"):
  - For Stop/SubagentStop, emit_metrics writes guidance to stderr (the
    asyncRewake body channel CC delivers via `stderr || stdout`) and sets
    top-level `decision: "block"` + `reason` (valid SyncHookJSONOutput
    fields; also the documented sync Stop-hook contract for the `-p`
    fallback). It does NOT emit a Stop hookSpecificOutput.
  - PostToolUse (commit-review, push-sweep) is unchanged — valid union
    member, keeps the modern hookSpecificOutput protocol.

Verified locally on macOS Python 3.13:

  - py_compile clean.
  - 11 new tests (test_2159_stop_hook_schema.py) pin the contract: Stop
    output carries no hookSpecificOutput, uses top-level decision/reason,
    writes guidance to stderr; the emitted hookEventName (when present) is
    a valid union member. 2 existing tests that asserted the buggy
    Stop->hookSpecificOutput shape were corrected. Full suite 464/464
    pass + 2 skipped.

  - END-TO-END in /tmux on CLI 2.1.160:
    * FIXED plugin (2.0.3): staged pickle.loads + os.system, benign edit
      pulls the file into review_set; Stop LLM review found 2 critical
      vulns; CC delivered a clean rewake ("Background security review
      found issues" + both findings). All hooks (UPS, PostToolUse[Edit]
      pattern, PostToolUse[Bash] commit-review, Stop) fired clean; zero
      schema rejections / errors / http_err in the debug log.
    * OLD plugin (2.0.2) on the SAME 2.1.160: also delivered Stop feedback
      (confirming the no-repro-on-latest finding above) — which proves the
      fix carries NO regression risk on current CC while making the output
      robust for the stricter versions where it actually breaks.

Version bumped 2.0.2 -> 2.0.3 per the per-PR-bump policy (#2114: a bump is
the only way the fix reaches the existing fleet — relevant for users still
on the CC versions where this breaks).

Closes #2159.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.claude-plugin/marketplace.json

@@ -19,7 +19,7 @@
         "url": "https://github.com/42Crunch-AI/claude-plugins.git",
         "path": "plugins/api-security-testing",
         "ref": "v1.5.5",
-        "sha": "5c8074d846b852c21da23bbf6effbfdabb18ba2d"
+        "sha": "b404d99a3f0bc1f3e74a1638671e2e3319187e2c"
       },
       "homepage": "https://42crunch.com"
     },
@@ -35,7 +35,7 @@
         "url": "https://github.com/adobe/skills.git",
         "path": "plugins/creative-cloud/adobe-for-creativity",
         "ref": "main",
-        "sha": "ecd1e2b2c493ba0627774f36a897bd44d47fef1d"
+        "sha": "8d74ee6b6fdce4a1c46b98b5a66706c9393fc369"
       },
       "homepage": "https://github.com/adobe/skills/tree/main/plugins/creative-cloud/adobe-for-creativity"
     },
@@ -57,7 +57,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/SalesforceAIResearch/agentforce-adlc.git",
-        "sha": "5ddccc36737b8bdc3dcabb3d6f51daa350c3d16d"
+        "sha": "1584dd52f388482db78949456addfa29a4c9d9c3"
       },
       "homepage": "https://github.com/SalesforceAIResearch/agentforce-adlc"
     },
@@ -107,7 +107,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/gemini-cli-extensions/alloydb.git",
-        "sha": "4a75653275b095fcacf1508796b0fee8cc758c07"
+        "sha": "bbf4eb3664faf129ab8ff8c4b959d7e59c03d347"
       },
       "homepage": "https://cloud.google.com/alloydb"
     },
@@ -120,7 +120,7 @@
         "url": "https://github.com/awslabs/agent-plugins.git",
         "path": "plugins/amazon-location-service",
         "ref": "main",
-        "sha": "5d982e8a5f1e0b06545adac69ff0348141587725"
+        "sha": "187edde6e122116b43211049195627a5069bda80"
       },
       "homepage": "https://github.com/awslabs/agent-plugins"
     },
@@ -193,7 +193,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/astronomer/agents.git",
-        "sha": "535a040ca9e27aaed6da13f0f959625fb3294820"
+        "sha": "7ce4a12d3cabb506294134c91a1b876d4b166a70"
       },
       "homepage": "https://github.com/astronomer/agents"
     },
@@ -203,7 +203,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/atlanhq/agent-toolkit.git",
-        "sha": "790398c87378f128bdc74c31bb7ecfb8e4695f29"
+        "sha": "cda594f40503cd2ae144052237fa2890e024828c"
       },
       "homepage": "https://docs.atlan.com/"
     },
@@ -226,7 +226,7 @@
         "source": "url",
         "url": "https://github.com/BrainBlend-AI/atomic-agents.git",
         "path": "claude-plugin/atomic-agents",
-        "sha": "c4e905c49884747be65e7ed42ccfb118c67f57ac"
+        "sha": "57d6099f499fe21572bdf943396630bd3d968550"
       },
       "homepage": "https://github.com/BrainBlend-AI/atomic-agents",
       "tags": [
@@ -245,7 +245,7 @@
         "url": "https://github.com/auth0/agent-skills.git",
         "path": "plugins/auth0",
         "ref": "main",
-        "sha": "c771dc1c77bfd5a67686afb464ccebd227c02b0f"
+        "sha": "c38453f6a99bbfeaf73b5be81db987ec6af982da"
       },
       "homepage": "https://auth0.com/docs/quickstart/agent-skills"
     },
@@ -274,7 +274,7 @@
         "url": "https://github.com/awslabs/agent-plugins.git",
         "path": "plugins/aws-amplify",
         "ref": "main",
-        "sha": "5d982e8a5f1e0b06545adac69ff0348141587725"
+        "sha": "187edde6e122116b43211049195627a5069bda80"
       },
       "homepage": "https://github.com/awslabs/agent-plugins"
     },
@@ -335,10 +335,26 @@
         "url": "https://github.com/awslabs/agent-plugins.git",
         "path": "plugins/aws-serverless",
         "ref": "main",
-        "sha": "5d982e8a5f1e0b06545adac69ff0348141587725"
+        "sha": "187edde6e122116b43211049195627a5069bda80"
       },
       "homepage": "https://github.com/awslabs/agent-plugins"
     },
+    {
+      "name": "aws-startup-advisor",
+      "description": "Skills for startups building on AWS: an Activate knowledge base (FAQ, credits, programs, partner offers, sample architectures, 277+ learn articles), a prompt library of 29+ copy-paste prompts plus installable agents, and an interactive discovery workflow that scaffolds an AWS architecture.",
+      "author": {
+        "name": "Amazon Web Services"
+      },
+      "category": "development",
+      "source": {
+        "source": "git-subdir",
+        "url": "https://github.com/awslabs/startups.git",
+        "path": "advisor/plugins/aws-startup-advisor",
+        "ref": "main",
+        "sha": "23a4f5eaf74a0f0fcf86f8a05bd36618a3f5faae"
+      },
+      "homepage": "https://github.com/awslabs/startups"
+    },
     {
       "name": "azure",
       "description": "Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.",
@@ -346,7 +362,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/microsoft/azure-skills.git",
-        "sha": "d02fd24f151f5133650eaa78e7da3cac2cedd72f"
+        "sha": "d3440b8a4f138585a512ecd4e0c54ede13ab1cc2"
       },
       "homepage": "https://github.com/microsoft/azure-skills"
     },
@@ -384,7 +400,7 @@
         "url": "https://github.com/Bigdata-com/bigdata-plugins-marketplace.git",
         "path": "plugins/bigdata-com",
         "ref": "main",
-        "sha": "c77a09caabdc8783adbcbf8bbe05a0f57da12b19"
+        "sha": "67c30be97a0a3f46bc6e8d56df449ae108eda9c5"
       },
       "homepage": "https://docs.bigdata.com"
     },
@@ -412,7 +428,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/brightdata/skills.git",
-        "sha": "071e9d4db77c8561e333799f25ea85f11f7b667d"
+        "sha": "68651246ad1819b98a1fc15ce10239e55406ff37"
       },
       "homepage": "https://docs.brightdata.com"
     },
@@ -442,7 +458,7 @@
         "url": "https://github.com/carta/plugins.git",
         "path": "plugins/carta-cap-table",
         "ref": "main",
-        "sha": "5e6c9d1cfa3bff9b91138e7906c6eb088fd9a66a"
+        "sha": "49cfc652620672f3e4d4ca31c4ba4c6ebcc568de"
       },
       "homepage": "https://carta.com"
     },
@@ -458,7 +474,7 @@
         "url": "https://github.com/carta/plugins.git",
         "path": "plugins/carta-crm",
         "ref": "main",
-        "sha": "5e6c9d1cfa3bff9b91138e7906c6eb088fd9a66a"
+        "sha": "49cfc652620672f3e4d4ca31c4ba4c6ebcc568de"
       },
       "homepage": "https://carta.com"
     },
@@ -474,7 +490,7 @@
         "url": "https://github.com/carta/plugins.git",
         "path": "plugins/carta-investors",
         "ref": "main",
-        "sha": "5e6c9d1cfa3bff9b91138e7906c6eb088fd9a66a"
+        "sha": "e66d331cd8e669ee121c96ee35b0c91acd828970"
       },
       "homepage": "https://carta.com"
     },
@@ -490,7 +506,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/cap-js/mcp-server.git",
-        "sha": "92dc99f5ba0c56957ed5d390484693a69ebd1206"
+        "sha": "9658cea90c782a6ab007ac16278c90fa4feca0ed"
       },
       "homepage": "https://cap.cloud.sap/"
     },
@@ -501,7 +517,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/ChromeDevTools/chrome-devtools-mcp.git",
-        "sha": "60be3e6bc157bd1121ea1d4b6ad59e37a73cac3e"
+        "sha": "692b28adac70f6475737ffbc4e6e2a0bb65569db"
       },
       "homepage": "https://github.com/ChromeDevTools/chrome-devtools-mcp"
     },
@@ -595,7 +611,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/ClickHouse/clickhouse-claude-code-plugin.git",
-        "sha": "36889764f504cb92ab71ffe54b4c55488290ed7f"
+        "sha": "bfd22b9ca64288c149a623c45ad933b23f9de019"
       },
       "homepage": "https://github.com/ClickHouse/clickhouse-claude-code-plugin"
     },
@@ -716,7 +732,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/CodSpeedHQ/codspeed.git",
-        "sha": "ecf3c2ebf959479126d631ad39d317738d559388"
+        "sha": "f79d57d207f039e44a31a976564715f7731e71b6"
       },
       "homepage": "https://codspeed.io"
     },
@@ -753,7 +769,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/get-convex/convex-backend-skill.git",
-        "sha": "5e59870cda2a5892e18a7164d1a46fcf57b70bea"
+        "sha": "002f9c834cdb834ddef1e4867d87cb6e80f0acba"
       },
       "homepage": "https://github.com/get-convex/convex-backend-skill",
       "keywords": [
@@ -784,7 +800,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/CrowdStrike/foundry-skills.git",
-        "sha": "99edea095f4e32ed008706b55257d0893fb93387"
+        "sha": "fb25d60ecdbc0129071802dad210a65168ca55a9"
       },
       "homepage": "https://github.com/CrowdStrike/foundry-skills"
     },
@@ -830,7 +846,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/dash0hq/dash0-agent-plugin.git",
-        "sha": "2909be7ebc2804af464e0d7f660ccc2b62d94623"
+        "sha": "0ec3db6b75d98badccf533597ce9a22fec744f5f"
       },
       "homepage": "https://dash0.com/"
     },
@@ -841,7 +857,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/astronomer/agents.git",
-        "sha": "535a040ca9e27aaed6da13f0f959625fb3294820"
+        "sha": "7ce4a12d3cabb506294134c91a1b876d4b166a70"
       },
       "homepage": "https://github.com/astronomer/agents"
     },
@@ -855,7 +871,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/gemini-cli-extensions/data-agent-kit-starter-pack.git",
-        "sha": "7bc75b5e53d6eaae103132fd1a47de26239e4ae4"
+        "sha": "86eb482b33d943aa4242ae6f06d627ec12064d46"
       },
       "homepage": "https://github.com/gemini-cli-extensions/data-agent-kit-starter-pack"
     },
@@ -865,7 +881,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/astronomer/agents.git",
-        "sha": "535a040ca9e27aaed6da13f0f959625fb3294820"
+        "sha": "7ce4a12d3cabb506294134c91a1b876d4b166a70"
       },
       "homepage": "https://github.com/astronomer/agents"
     },
@@ -878,7 +894,7 @@
         "url": "https://github.com/awslabs/agent-plugins.git",
         "path": "plugins/databases-on-aws",
         "ref": "main",
-        "sha": "5d982e8a5f1e0b06545adac69ff0348141587725"
+        "sha": "187edde6e122116b43211049195627a5069bda80"
       },
       "homepage": "https://github.com/awslabs/agent-plugins"
     },
@@ -920,7 +936,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/datarobot-oss/datarobot-agent-skills.git",
-        "sha": "8124faae2154117382b1046aa74d8901a3ffe930"
+        "sha": "1bef28436b91fc945b8529d1a57b471cde3154ea"
       },
       "homepage": "https://datarobot.com"
     },
@@ -946,7 +962,7 @@
         "url": "https://github.com/awslabs/agent-plugins.git",
         "path": "plugins/deploy-on-aws",
         "ref": "main",
-        "sha": "5d982e8a5f1e0b06545adac69ff0348141587725"
+        "sha": "187edde6e122116b43211049195627a5069bda80"
       },
       "homepage": "https://github.com/awslabs/agent-plugins"
     },
@@ -962,7 +978,7 @@
         "url": "https://github.com/wonderwhy-er/DesktopCommanderMCP.git",
         "path": "plugins/claude",
         "ref": "main",
-        "sha": "9c44119a480ec6460f82d59aeb90cf274bc3dd7b"
+        "sha": "ce4669cca7a07bd5d493cedb01df400790ec9e23"
       },
       "homepage": "https://desktopcommander.app"
     },
@@ -982,7 +998,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/dominodatalab/domino-claude-plugin.git",
-        "sha": "47c6e0a7daa11b21eb6e12779c9d679569e8ffe2"
+        "sha": "56c3fc39d2f2f26d58d0f27d4dad138b0edec456"
       },
       "homepage": "https://www.domino.ai"
     },
@@ -1010,7 +1026,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/DuendeSoftware/duende-skills.git",
-        "sha": "2c803785061db150d8ecea098327b404b74dbf6a"
+        "sha": "72e39de9f10c5dafaa7f32f58fcdbd5a8f3e5c14"
       },
       "homepage": "https://duendesoftware.com"
     },
@@ -1048,7 +1064,7 @@
         "url": "https://github.com/expo/skills.git",
         "path": "plugins/expo",
         "ref": "main",
-        "sha": "510373b50956ef4dc84c20bb4c9cce70b618aa06"
+        "sha": "fdd3df12151a208853fe540ffea9a67773446377"
       },
       "homepage": "https://github.com/expo/skills/blob/main/plugins/expo/README.md"
     },
@@ -1114,7 +1130,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/firecrawl/firecrawl-claude-plugin.git",
-        "sha": "01d11b30ace699a27f9ea7decf6ce6c9857f71ff"
+        "sha": "81178096fa7ae860285923948b8ba13d03c7fa0c"
       },
       "homepage": "https://github.com/firecrawl/firecrawl-claude-plugin.git"
     },
@@ -1217,7 +1233,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/huggingface/skills.git",
-        "sha": "7a493b09c81aae09a41bd2e1fa33dfc0f68acd75"
+        "sha": "49abf82b2ef2ff2bcc6ca072aac0fe8627390a1d"
       },
       "homepage": "https://github.com/huggingface/skills.git"
     },
@@ -1231,7 +1247,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/hunter-io/claude-plugin.git",
-        "sha": "c67942395cde155e9ad4ed8e3a137926f9992fb8"
+        "sha": "4eb5fbbcb75e0c4c4f2c0d8aa02756165fdde629"
       },
       "homepage": "https://hunter.io"
     },
@@ -1245,7 +1261,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/heygen-com/hyperframes.git",
-        "sha": "7ea4d1c1314bd60d5273efa92626bd1d0f9c621d"
+        "sha": "3c7e2f36497de471e5a63ecc6d582522d206b208"
       },
       "homepage": "https://hyperframes.heygen.com"
     },
@@ -1410,7 +1426,7 @@
         "url": "https://github.com/pydantic/skills.git",
         "path": "plugins/logfire",
         "ref": "main",
-        "sha": "0c38c5bb5679f6cc41956bbbf811396a0d108ac9"
+        "sha": "56dadc9c3b4551b7baf01a9a9f728dc72383bd07"
       },
       "homepage": "https://github.com/pydantic/skills/tree/main/plugins/logfire"
     },
@@ -1485,7 +1501,7 @@
         "url": "https://github.com/modelcontextprotocol/ext-apps.git",
         "path": "plugins/mcp-apps",
         "ref": "main",
-        "sha": "9a37ad71827d076af06978fa7f7f510449687061"
+        "sha": "7d4434e991516d91286dded5bb10266cd6cddd02"
       },
       "homepage": "https://modelcontextprotocol.io"
     },
@@ -1523,7 +1539,7 @@
         "url": "https://github.com/mercadopago/mercadopago-claude-marketplace.git",
         "path": "plugins/mercadopago",
         "ref": "main",
-        "sha": "f52c138924d8035b39e8fe02d41c6712fc41ceb4"
+        "sha": "ba967158392bec9f0c199cd39196af64222f0ab0"
       },
       "homepage": "https://github.com/mercadopago/mercadopago-claude-marketplace/tree/main/plugins/mercadopago"
     },
@@ -1638,7 +1654,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/Nimbleway/agent-skills.git",
-        "sha": "95ed06468957ddc9de609b25c390b30c3864eac8"
+        "sha": "9736dfc757f5ed4f05da0480b202af09e93a27de"
       },
       "homepage": "https://docs.nimbleway.com/integrations/agent-skills/plugin-installation"
     },
@@ -1653,6 +1669,22 @@
       },
       "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": "91dbdf239b8af3b4c1511e0cfa5b505235a08ab1"
+      },
+      "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.",
@@ -1665,7 +1697,7 @@
         "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": "f7ea9cae6fce69a4e3798dfc1d5216ac1d0dd7e8"
+        "sha": "6e59f24cd3e8870649e7f9b2e3e106502b43fd5f"
       },
       "homepage": "https://docs.oracle.com/en/cloud/paas/ai-data-platform/index.html"
     },
@@ -1681,7 +1713,7 @@
         "url": "https://github.com/growthxai/output.git",
         "path": "coding_assistants/claude/plugins/outputai",
         "ref": "main",
-        "sha": "93dd22ee568a97911a332b5aa0d9cebb2b6f7da1"
+        "sha": "5a87ebc13343ce6ebabac0bcc443c1da0bcf2459"
       },
       "homepage": "https://output.ai"
     },
@@ -1729,7 +1761,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/gopigment/ai-plugins.git",
-        "sha": "4bf16c80558416b9d69fa6531af8588fb2fcbe27"
+        "sha": "abf36e64750d1323a4cc5fe79161597668231224"
       },
       "homepage": "https://www.pigment.com"
     },
@@ -1801,7 +1833,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/gitroomhq/postiz-agent.git",
-        "sha": "238aede6c72672b3201ae0ee533ec0cd53eb51d1"
+        "sha": "41c5a9dbd6b2776863e7c05c22e7a385c208321c"
       },
       "homepage": "https://postiz.com/agent"
     },
@@ -1846,7 +1878,7 @@
         "url": "https://github.com/pydantic/skills.git",
         "path": "plugins/ai",
         "ref": "main",
-        "sha": "0c38c5bb5679f6cc41956bbbf811396a0d108ac9"
+        "sha": "56dadc9c3b4551b7baf01a9a9f728dc72383bd07"
       },
       "homepage": "https://github.com/pydantic/skills/tree/main/plugins/ai"
     },
@@ -1884,7 +1916,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/qdrant/skills.git",
-        "sha": "1390c811e03922b822dc9e12b832ba4dc82e0bf0"
+        "sha": "ea62a9857dabcc169597549da7681bd6d4cd13e9"
       },
       "homepage": "https://skills.qdrant.tech"
     },
@@ -1895,7 +1927,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/qodo-ai/qodo-skills.git",
-        "sha": "b1eb0389480ee6de8df874f40a230ed2625ef0d3"
+        "sha": "8aec13d6ac60feb9d9f84f36aa1753234de17dc8"
       },
       "homepage": "https://github.com/qodo-ai/qodo-skills.git"
     },
@@ -1909,7 +1941,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/TheQtCompanyRnD/agent-skills.git",
-        "sha": "23772fa2264b3ff1037a96164b2c28d2b29a4c2f"
+        "sha": "a7189a7bc17e616b725e7ce4e46a4f5ebd50d94f"
       },
       "homepage": "https://www.qt.io/"
     },
@@ -1923,7 +1955,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/quarkusio/quarkus-agent-mcp.git",
-        "sha": "77fd36284a80b3ed1bde3d2fe48a0b2f99e4941e"
+        "sha": "065b4595cf9116f76bf87323fe29573d72a77a65"
       },
       "homepage": "https://quarkus.io"
     },
@@ -1975,7 +2007,7 @@
         "url": "https://github.com/redis/agent-skills.git",
         "path": "plugins/redis-development",
         "ref": "main",
-        "sha": "18da4e42371f7eee0dcfafd8461effd41de351e9"
+        "sha": "5ca2e1a2d82a768221e8f71a02e3ca095a37d38e"
       },
       "homepage": "https://redis.io"
     },
@@ -1985,7 +2017,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/Digital-Process-Tools/claude-remember.git",
-        "sha": "c9b34417a8132f0416411a0ca51d009a256a3acc"
+        "sha": "c2c82ab5fd2f4f5c0cddc9c7d8a749655dec4cb9"
       },
       "homepage": "https://github.com/Digital-Process-Tools/claude-remember"
     },
@@ -1999,7 +2031,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/resend/resend-skills.git",
-        "sha": "78469829399beec62b8f815f109ebfcfa3b0680b"
+        "sha": "376d1c3fb37cc7d22ab21cce836f4d6f323922de"
       },
       "homepage": "https://resend.com"
     },
@@ -2087,6 +2119,19 @@
         }
       }
     },
+    {
+      "name": "sagemaker-ai",
+      "description": "Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.",
+      "category": "development",
+      "source": {
+        "source": "git-subdir",
+        "url": "https://github.com/awslabs/agent-plugins.git",
+        "path": "plugins/sagemaker-ai",
+        "ref": "main",
+        "sha": "187edde6e122116b43211049195627a5069bda80"
+      },
+      "homepage": "https://github.com/awslabs/agent-plugins"
+    },
     {
       "name": "sanity",
       "description": "Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual Editing.",
@@ -2097,7 +2142,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/sanity-io/agent-toolkit.git",
-        "sha": "236348e29b31e834ce71e4e2e3072184dd1c1e27"
+        "sha": "d7545f5cc6f8fb39554083b52ad074a6d912db9f"
       },
       "homepage": "https://www.sanity.io"
     },
@@ -2131,7 +2176,7 @@
         "url": "https://github.com/SAP/open-ux-tools.git",
         "path": "packages/fiori-mcp-server",
         "ref": "main",
-        "sha": "d2a6fce818f3c046c5bbb041507be4632f926602"
+        "sha": "7432d23a7b5c3bd1c0a01cf76696bf0c417ecd1f"
       },
       "homepage": "https://github.com/SAP/open-ux-tools/tree/main/packages/fiori-mcp-server"
     },
@@ -2170,7 +2215,7 @@
     {
       "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": "2.0.0",
+      "version": "2.0.3",
       "author": {
         "name": "Anthropic",
         "email": "support@anthropic.com"
@@ -2198,7 +2243,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/getsentry/sentry-for-claude.git",
-        "sha": "ed0875684192bb8a050297a896657ff9db1ffdf5"
+        "sha": "849303a8411c242d250885ffe714235a3bc2f5fe"
       },
       "homepage": "https://github.com/getsentry/sentry-for-claude/tree/main"
     },
@@ -2214,7 +2259,7 @@
         "url": "https://github.com/getsentry/cli.git",
         "path": "plugins/sentry-cli",
         "ref": "main",
-        "sha": "d9bcd70eaa467fb3ddf591bfbfb0686fd1e9c016"
+        "sha": "5abcacdf8f0b613bceee7aa7aebb9db1d75ed5e2"
       },
       "homepage": "https://sentry.io"
     },
@@ -2279,7 +2324,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/Shopify/Shopify-AI-Toolkit.git",
-        "sha": "c164cf45c4bc1d17bbc105168d99a4f744cfaac2"
+        "sha": "859be93bfc858f183ff5eb40183e35a4d91d2950"
       },
       "homepage": "https://shopify.dev"
     },
@@ -2364,7 +2409,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/spotify/ads-claude-plugin.git",
-        "sha": "7ed948b85337f6b31a82dfaa8f033b6843659fa3"
+        "sha": "73b8bd490e02d3ed0bb4c8e228a470c46f995154"
       },
       "homepage": "https://github.com/spotify/ads-claude-plugin"
     },
@@ -2377,7 +2422,7 @@
         "url": "https://github.com/stripe/ai.git",
         "path": "providers/claude/plugin",
         "ref": "main",
-        "sha": "a34795211da530a168f581122011bb5ceb2e4bd0"
+        "sha": "38cc559cab7eab62f11bc3809b93af45f28063f6"
       },
       "homepage": "https://github.com/stripe/ai/tree/main/providers/claude/plugin"
     },
@@ -2400,7 +2445,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/supabase-community/supabase-plugin.git",
-        "sha": "1b910c021aee8c9c054196f0e840b3a65e1a7c63"
+        "sha": "3217ac038647f6901a166f3264a32f01833f73ba"
       },
       "homepage": "https://github.com/supabase-community/supabase-plugin"
     },
@@ -2411,7 +2456,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/obra/superpowers.git",
-        "sha": "f2cbfbefebbfef77321e4c9abc9e949826bea9d7"
+        "sha": "6fd4507659784c351abbd2bc264c7162cfd386dc"
       },
       "homepage": "https://github.com/obra/superpowers.git"
     },
@@ -2445,7 +2490,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/JetBrains/teamcity-cli.git",
-        "sha": "7f8419738b452108ff181365be30c1fab0a6905e"
+        "sha": "533c8cb20928be912188fd8ae40fcba24cc720ca"
       },
       "homepage": "https://www.jetbrains.com/teamcity/"
     },
@@ -2476,7 +2521,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/togethercomputer/skills.git",
-        "sha": "a1277729f7914d886df213de922865d30a214a9d"
+        "sha": "f957e2929edebde0c364e804f8b38a3714db92b4"
       },
       "homepage": "https://www.together.ai"
     },
@@ -2538,7 +2583,7 @@
         "url": "https://github.com/UI5/plugins-coding-agents.git",
         "path": "plugins/ui5",
         "ref": "main",
-        "sha": "78f657e6a5004b5cdd1b998aabea616023eeabbb"
+        "sha": "7acd8328399a221e161ae5bb04a5675696f92920"
       },
       "homepage": "https://github.com/UI5/plugins-coding-agents"
     },
@@ -2556,7 +2601,7 @@
         "url": "https://github.com/UI5/plugins-coding-agents.git",
         "path": "plugins/ui5-typescript-conversion",
         "ref": "main",
-        "sha": "78f657e6a5004b5cdd1b998aabea616023eeabbb"
+        "sha": "7acd8328399a221e161ae5bb04a5675696f92920"
       },
       "homepage": "https://github.com/UI5/plugins-coding-agents"
     },
@@ -2595,7 +2640,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/explorium-ai/vibeprospecting-plugin.git",
-        "sha": "ada4d569dbf70194fe18750ecbc5170e9a3f120a"
+        "sha": "7ed0c4e2965ee315132c3c714609b46b23b5edc0"
       },
       "homepage": "https://www.vibeprospecting.ai/product/claude-plugin"
     },
@@ -2620,7 +2665,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/wix/skills.git",
-        "sha": "5da7e749a466ef9ddcdb2822099b940b9a1bc151"
+        "sha": "2da8231fcdc49a48af64b050ba5e1a85c3968670"
       },
       "homepage": "https://dev.wix.com/docs/wix-cli/guides/development/about-wix-skills"
     },
@@ -2727,7 +2772,7 @@
       "source": {
         "source": "url",
         "url": "https://github.com/zscaler/zscaler-mcp-server.git",
-        "sha": "8409e1661b7f7171bfbb9297e1ecfc61c28b6d92"
+        "sha": "be37fb604a07dc9c5a4c3e009312c4f11acaa6d3"
       },
       "homepage": "https://github.com/zscaler/zscaler-mcp-server"
     }

.github/workflows/bump-plugin-shas.yml

@@ -2,25 +2,24 @@ 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 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.
+# inline, then open one PR per bumped plugin on branch `bump/<slug>`.
+# Failing entries stay isolated in their own PR; passing bumps merge
+# independently.
 #
 # Bot-free — uses the default GITHUB_TOKEN. PRs opened with GITHUB_TOKEN don't
-# 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.
+# 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.)
 #
-# 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.
+# 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.
 
 on:
   schedule:
@@ -30,12 +29,12 @@ on:
       max_bumps:
         description: Cap on plugins bumped this run
         required: false
-        default: '130'
+        default: '30'
 
 permissions:
   contents: write
   pull-requests: write
-  actions: write  # gh workflow run scan-plugins.yml on the bump branch
+  actions: write  # gh workflow run {scan-plugins,check-mcp-urls,validate-plugins}.yml per bump branch
 
 concurrency:
   group: bump-plugin-shas
@@ -43,8 +42,8 @@ concurrency:
 jobs:
   bump:
     runs-on: ubuntu-latest
-    # 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
+    # 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
     # pathological run consume the default 360 min budget.
     timeout-minutes: 60
     steps:
@@ -52,18 +51,44 @@ 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@c41c6911de0afffd2bc5cd8b21fb1e06444ee13b
+      - uses: anthropics/claude-plugins-community/.github/actions/bump-plugin-shas@e2019b2a01f11aa1484c53540b1cfab5eebbc299
         id: bump
         with:
           marketplace-path: .claude-plugin/marketplace.json
-          max-bumps: ${{ inputs.max_bumps || '130' }}
+          max-bumps: ${{ inputs.max_bumps || '30' }}
+          pr-mode: per-entry
           claude-cli-version: latest
 
-      # `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 != ''
+      # 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 != '[]'
         env:
           GH_TOKEN: ${{ github.token }}
-        run: gh workflow run scan-plugins.yml --ref bump/plugin-shas
+          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

.github/workflows/validate-plugins.yml

@@ -12,6 +12,14 @@ 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

plugins/security-guidance/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "security-guidance",
-  "version": "2.0.0",
+  "version": "2.0.3",
   "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",

plugins/security-guidance/hooks/_base.py

@@ -10,15 +10,42 @@ import os
 import threading
 from datetime import datetime
 
+def state_dir():
+    """Return the absolute path of the plugin's state directory.
+
+    Resolution precedence (highest first):
+      1. SECURITY_WARNINGS_STATE_DIR — plugin-specific override (existing)
+      2. CLAUDE_CONFIG_DIR/security  — CC's config-dir env var (#1868)
+      3. ~/.claude/security          — default fallback
+
+    Empty-string env vars are treated as not-set so a misconfigured shell
+    (`CLAUDE_CONFIG_DIR=` with no value) doesn't silently write to
+    /security at the filesystem root.
+
+    Returns a fully-expanded absolute path (no literal `~`) so subprocess
+    callers can pass it through to code that doesn't re-expand tildes.
+
+    Called per-invocation rather than cached at import time so test
+    monkeypatches of the env vars take effect — the plugin's hooks each
+    run as fresh subprocesses in production, so the per-call cost is
+    negligible compared to subprocess spawn.
+    """
+    explicit = os.environ.get("SECURITY_WARNINGS_STATE_DIR")
+    if explicit:
+        return os.path.expanduser(explicit)
+    cc_config = os.environ.get("CLAUDE_CONFIG_DIR")
+    if cc_config:
+        return os.path.expanduser(os.path.join(cc_config, "security"))
+    return os.path.expanduser("~/.claude/security")
+
+
 # Debug log file. Lives under the plugin state dir (default ~/.claude/security/)
 # rather than /tmp because /tmp is world-writable on multi-user hosts (TOCTOU /
 # symlink-attack surface, cross-user log leakage). Overridable per-process via
-# SECURITY_GUIDANCE_DEBUG_LOG, or per-state-dir via SECURITY_WARNINGS_STATE_DIR.
-_DEFAULT_STATE_DIR = os.path.expanduser(
-    os.environ.get("SECURITY_WARNINGS_STATE_DIR") or "~/.claude/security"
-)
+# SECURITY_GUIDANCE_DEBUG_LOG, or per-state-dir via SECURITY_WARNINGS_STATE_DIR
+# (plugin-specific override) or CLAUDE_CONFIG_DIR (CC-wide config dir, #1868).
 DEBUG_LOG_FILE = os.environ.get("SECURITY_GUIDANCE_DEBUG_LOG") or os.path.join(
-    _DEFAULT_STATE_DIR, "log.txt"
+    state_dir(), "log.txt"
 )
 # Cap the debug log so parallel-worker fleets don't fill disk. When the active
 # file exceeds this it's atomically rotated to <file>.1 (overwriting any prior
@@ -89,7 +116,18 @@ _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}
+_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_LOCK = threading.Lock()
 
 # $/Mtok (input, output). Used only for the raw-HTTP path; the SDK path
@@ -139,19 +177,55 @@ 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
-    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:
-            return {}
-        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"],
-        }
+    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.
+    """
+    with _USAGE_LOCK:
+        if _USAGE["n"] == 0 and _USAGE["http_err_count"] == 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
 

plugins/security-guidance/hooks/diffstate.py

@@ -355,9 +355,9 @@ def _list_untracked(cwd):
     the holdouts."""
     try:
         repo = _git_toplevel(cwd) or cwd
+        # core.quotePath=false comes from GIT_CMD globally (see gitutil.py).
         r = subprocess.run(
-            [*GIT_CMD, "-c", "core.quotePath=false", "ls-files",
-             "--others", "--exclude-standard", "-z"],
+            [*GIT_CMD, "ls-files", "--others", "--exclude-standard", "-z"],
             cwd=repo, capture_output=True, timeout=15,
         )
         if r.returncode != 0:

plugins/security-guidance/hooks/ensure_agent_sdk.py

@@ -23,6 +23,12 @@ import sys
 import time
 from pathlib import Path
 
+# Shared state-dir resolver: SECURITY_WARNINGS_STATE_DIR → CLAUDE_CONFIG_DIR/security
+# → ~/.claude/security. See _base.state_dir for resolution precedence. Re-aliased
+# here to match the existing local name (state_dir was already a local var in
+# main() and _maybe_emit_user_notice).
+from _base import state_dir as _resolve_state_dir
+
 # Outcome codes for the sdk_bootstrap metric. Values are stable for telemetry.
 NOOP_SYSTEM = 0      # claude_agent_sdk already importable in system python
 NOOP_VENV = 1        # venv already built and SDK imports from it
@@ -36,6 +42,122 @@ 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
@@ -90,10 +212,7 @@ def main() -> tuple[int, str, str]:
     if _sdk_on_syspath():
         return NOOP_SYSTEM, "", ""
 
-    state_dir = Path(
-        os.environ.get("SECURITY_WARNINGS_STATE_DIR")
-        or os.path.expanduser("~/.claude/security")
-    )
+    state_dir = Path(_resolve_state_dir())
     venv = state_dir / "agent-sdk-venv"
     # Windows venvs put the interpreter at Scripts\python.exe; POSIX uses bin/python.
     if sys.platform == "win32":
@@ -177,7 +296,34 @@ def main() -> tuple[int, str, str]:
         else:
             stderr_str = str(stderr_b)
         s = stderr_str.lower()
-        if "no matching distribution" in s or "could not find a version" in s:
+        # 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:
             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:
@@ -196,6 +342,15 @@ 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
@@ -239,10 +394,7 @@ def _maybe_emit_user_notice(outcome: int, pv: int) -> str | None:
     if outcome != HOOK_PY_INCOMPATIBLE:
         return None
     try:
-        state_dir = Path(
-            os.environ.get("SECURITY_WARNINGS_STATE_DIR")
-            or os.path.expanduser("~/.claude/security")
-        )
+        state_dir = Path(_resolve_state_dir())
         marker = state_dir / f".agentic_unavailable_notice_v{pv or 0}"
         if marker.exists():
             return None
@@ -288,21 +440,33 @@ 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. 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.
+    # \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.
     metrics: dict[str, object] = {
         "sdk_bootstrap": outcome,
         "sdk_bootstrap_ms": round((time.perf_counter() - t0) * 1000),
     }
     if err_kind:
-        # 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]
+        # 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
     pv = _plugin_version_int()
     if pv:
         metrics["pv"] = pv

plugins/security-guidance/hooks/gitutil.py

@@ -26,18 +26,34 @@ GIT_CMD = [
     "git",
     "-c", "core.fsmonitor=false",
     "-c", "core.hooksPath=/dev/null",
+    # core.quotePath=false: emit raw UTF-8 in path-emitting commands instead
+    # of C-quoting non-ASCII bytes (default `"\\303\\201vila/..."` vs
+    # `Ávila/...`). Downstream parsers — both ours (parse_diff_into_files,
+    # extract_file_paths_from_diff) and Python stdlib (os.path.isabs,
+    # os.path.join) — expect raw paths and silently drop / mishandle the
+    # quoted form. Adding the flag globally to GIT_CMD covers every
+    # subprocess.run site that uses the splat — diff feeders, rev-parse
+    # path queries (--show-toplevel, --git-dir, --git-common-dir),
+    # reflog %gs subjects, ls-files, status, etc. — without per-site
+    # flag duplication. See #2082, #2099.
+    "-c", "core.quotePath=false",
 ]
 
 
 def _git_rev_parse_head(cwd):
     """Return the current HEAD SHA, or None if not a git repo / no commits."""
     try:
+        # See #2099: text=True on Windows cp1252 crashes the reader thread on
+        # any UTF-8 byte undefined in cp1252 (e.g. via a git error message
+        # referencing a non-ASCII filename in stderr). stdout is a SHA so it
+        # IS safe; stderr is not. capture_output=True with bytes-by-default
+        # never decodes, so the reader thread can't crash.
         result = subprocess.run(
             [*GIT_CMD, "rev-parse", "HEAD"],
-            cwd=cwd, capture_output=True, text=True, timeout=5
+            cwd=cwd, capture_output=True, timeout=5
         )
         if result.returncode == 0 and result.stdout.strip():
-            return result.stdout.strip()
+            return result.stdout.decode("utf-8", errors="replace").strip()
         return None
     except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
         return None
@@ -52,13 +68,17 @@ def _find_git_index(cwd):
     Returns the absolute path to the index file, or None.
     """
     try:
+        # See #2099: stdout here is a PATH which can contain non-ASCII bytes
+        # (e.g. C:\אבטחה\repo\.git). text=True decodes via cp1252 strict on
+        # Windows → crashes the reader thread → returns stdout=None →
+        # caller does .strip() on None → AttributeError. Decode manually.
         result = subprocess.run(
             [*GIT_CMD, "rev-parse", "--git-dir"],
-            cwd=cwd, capture_output=True, text=True, timeout=5
+            cwd=cwd, capture_output=True, timeout=5
         )
         if result.returncode != 0:
             return None
-        git_dir = result.stdout.strip()
+        git_dir = result.stdout.decode("utf-8", errors="replace").strip()
         if not os.path.isabs(git_dir):
             git_dir = os.path.join(cwd, git_dir)
         index_path = os.path.join(git_dir, "index")
@@ -128,9 +148,13 @@ def _temp_index(cwd, untracked_paths=None):
         else:
             add_args = None
         if add_args:
+            # No stdout used here (only returncode matters), but text=True
+            # still spawns reader threads that decode stderr — git error
+            # messages can reference non-ASCII filenames and crash on
+            # cp1252. See #2099. Drop text=True so bytes stay raw.
             subprocess.run(
                 [*GIT_CMD, "add", "--intent-to-add"] + add_args,
-                cwd=cwd, capture_output=True, text=True, timeout=10,
+                cwd=cwd, capture_output=True, timeout=10,
                 env=env,
             )
         yield env
@@ -144,11 +168,17 @@ def _temp_index(cwd, untracked_paths=None):
 def _git_toplevel(cwd):
     """Absolute repo root for `cwd`, or None if not in a work tree."""
     try:
+        # See #2099: stdout is a PATH — `C:\אבטחה\repo` returned as UTF-8
+        # bytes by git. text=True would decode via cp1252 strict on Windows
+        # → reader-thread crash. Decode manually with errors="replace".
         r = subprocess.run(
             [*GIT_CMD, "rev-parse", "--show-toplevel"],
-            cwd=cwd, capture_output=True, text=True, timeout=5,
+            cwd=cwd, capture_output=True, timeout=5,
         )
-        return r.stdout.strip() if r.returncode == 0 and r.stdout.strip() else None
+        if r.returncode != 0:
+            return None
+        path = r.stdout.decode("utf-8", errors="replace").strip()
+        return path if path else None
     except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
         return None
 
@@ -164,13 +194,15 @@ def _git_dir(repo_root):
     callers can degrade (push-sweep state is best-effort).
     """
     try:
+        # See #2099: stdout is a PATH (shared gitdir), may be non-ASCII.
+        # Decode bytes manually to avoid cp1252 reader-thread crash.
         r = subprocess.run(
             [*GIT_CMD, "rev-parse", "--git-common-dir"],
-            cwd=repo_root, capture_output=True, text=True, timeout=5,
+            cwd=repo_root, capture_output=True, timeout=5,
         )
         if r.returncode != 0:
             return None
-        d = r.stdout.strip()
+        d = r.stdout.decode("utf-8", errors="replace").strip()
         return d if os.path.isabs(d) else os.path.join(repo_root, d)
     except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
         return None
@@ -179,13 +211,15 @@ def _git_dir(repo_root):
 def _git_rev_list_range(repo_root, base, head="HEAD"):
     """Shas in `base..head`, oldest→newest. Empty list on error."""
     try:
+        # See #2099: stdout is ASCII SHAs, but stderr can carry git error
+        # messages referencing non-ASCII filenames — keep bytes raw.
         r = subprocess.run(
             [*GIT_CMD, "rev-list", "--reverse", f"{base}..{head}"],
-            cwd=repo_root, capture_output=True, text=True, timeout=10,
+            cwd=repo_root, capture_output=True, timeout=10,
         )
         if r.returncode != 0:
             return []
-        return [s for s in r.stdout.strip().split("\n") if s]
+        return [s for s in r.stdout.decode("utf-8", errors="replace").strip().split("\n") if s]
     except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
         return []
 
@@ -199,15 +233,12 @@ def _git_diff_range(repo_root, base, head="HEAD"):
     them reviewed — otherwise unreviewed commits get permanently silenced.
     """
     try:
-        # core.quotePath=false makes git emit raw UTF-8 in `diff --git a/... b/...`
-        # headers instead of C-quoting non-ASCII path bytes (`"a/\303\201vila/..."`
-        # vs `a/Ávila/...`). The downstream `re.match(r'^a/(.+?) b/(.+)$', ...)`
-        # in parse_diff_into_files / extract_file_paths_from_diff matches the
-        # raw form only — quoted headers slip past and the entire file is
-        # silently dropped from review. See #2082 (sibling of #2056 / #2075).
+        # GIT_CMD globally passes core.quotePath=false (see definition) so
+        # non-ASCII paths in `diff --git a/... b/...` headers come through as
+        # raw UTF-8, not C-quoted. Required by the downstream
+        # parse_diff_into_files / extract_file_paths_from_diff regex.
         r = subprocess.run(
-            [*GIT_CMD, "-c", "core.quotePath=false",
-             "diff", "-p", "--no-color", "--no-ext-diff", base, head],
+            [*GIT_CMD, "diff", "-p", "--no-color", "--no-ext-diff", base, head],
             cwd=repo_root, capture_output=True, timeout=30,
         )
         if r.returncode != 0:
@@ -220,9 +251,11 @@ def _git_diff_range(repo_root, base, head="HEAD"):
 def _detect_main_branch(repo_root):
     for ref in ("origin/HEAD", "origin/main", "origin/master", "main", "master"):
         try:
+            # See #2099: stdout is a SHA but stderr can carry non-ASCII git
+            # warnings — keep bytes raw to avoid cp1252 reader-thread crash.
             r = subprocess.run(
                 [*GIT_CMD, "rev-parse", "--verify", "-q", ref],
-                cwd=repo_root, capture_output=True, text=True, timeout=5,
+                cwd=repo_root, capture_output=True, timeout=5,
             )
             if r.returncode == 0 and r.stdout.strip():
                 return ref
@@ -330,8 +363,9 @@ def _git_name_only(cwd, base, include_untracked=False):
     # result.stdout=None, and propagate AttributeError out of the helper.
     # Same fix shape as diffstate._list_untracked. See #2056.
     def _run(env):
+        # core.quotePath=false comes from GIT_CMD globally (see definition).
         result = subprocess.run(
-            [*GIT_CMD, "-c", "core.quotePath=false", "diff", "--name-only", "-z", base],
+            [*GIT_CMD, "diff", "--name-only", "-z", base],
             cwd=cwd, capture_output=True, timeout=30,
             env=env,
         )
@@ -368,9 +402,9 @@ def _git_status_porcelain(cwd):
     # sibling helpers — a non-ASCII path in the worktree would otherwise
     # crash the cp1252 reader thread on Windows. See #2056.
     try:
+        # core.quotePath=false comes from GIT_CMD globally (see definition).
         r = subprocess.run(
-            [*GIT_CMD, "-c", "core.quotePath=false", "status",
-             "--porcelain=v1", "-uall", "-z"],
+            [*GIT_CMD, "status", "--porcelain=v1", "-uall", "-z"],
             cwd=cwd, capture_output=True, timeout=30,
         )
         if r.returncode != 0:
@@ -410,9 +444,12 @@ def _is_ancestor(cwd, maybe_ancestor, descendant):
     """True if `maybe_ancestor` is reachable from `descendant` (i.e. HEAD
     moved forward via commit/merge, not sideways via checkout)."""
     try:
+        # See #2099: only returncode matters, but text=True spawns reader
+        # threads that decode stderr — git error messages can carry non-ASCII
+        # filenames. Drop text=True to keep bytes raw, avoid cp1252 crash.
         result = subprocess.run(
             [*GIT_CMD, "merge-base", "--is-ancestor", maybe_ancestor, descendant],
-            cwd=cwd, capture_output=True, text=True, timeout=5,
+            cwd=cwd, capture_output=True, timeout=5,
         )
         return result.returncode == 0
     except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
@@ -443,11 +480,8 @@ def get_git_diff(cwd, baseline_sha, full_context=False, paths=None, untracked_pa
         # change exists to fix.
         return ""
 
-    # core.quotePath=false: emit raw UTF-8 in `diff --git a/... b/...` headers
-    # so non-ASCII paths aren't C-quoted past the downstream parse_diff_into_files
-    # regex. See #2082 (sibling of #2056 / #2075).
-    cmd = [*GIT_CMD, "-c", "core.quotePath=false",
-           "diff", "--no-color", "--no-ext-diff", baseline_sha] + (["--unified=99999"] if full_context else []) + pathspec
+    # core.quotePath=false comes from GIT_CMD globally (see definition).
+    cmd = [*GIT_CMD, "diff", "--no-color", "--no-ext-diff", baseline_sha] + (["--unified=99999"] if full_context else []) + pathspec
     try:
         with _temp_index(cwd, untracked_paths) as env:
             # env is None when no index could be found (bare repo / not a

plugins/security-guidance/hooks/hooks.json

@@ -49,6 +49,30 @@
             "asyncRewake": true,
             "rewakeMessage": "Background security review of pushed commits not yet reviewed — address or acknowledge the findings below, then continue with the user's original request or continue waiting for their reply:",
             "rewakeSummary": "Push security review found issues"
+          },
+          {
+            "type": "command",
+            "command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/sg-python.sh\" \"${CLAUDE_PLUGIN_ROOT}/hooks/security_reminder_hook.py\"",
+            "if": "Bash(gt create:*)",
+            "asyncRewake": true,
+            "rewakeMessage": "Background security review of commit — address or acknowledge the findings below, then continue with the user's original request or continue waiting for their reply:",
+            "rewakeSummary": "Commit security review found issues"
+          },
+          {
+            "type": "command",
+            "command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/sg-python.sh\" \"${CLAUDE_PLUGIN_ROOT}/hooks/security_reminder_hook.py\"",
+            "if": "Bash(gt modify:*)",
+            "asyncRewake": true,
+            "rewakeMessage": "Background security review of commit — address or acknowledge the findings below, then continue with the user's original request or continue waiting for their reply:",
+            "rewakeSummary": "Commit security review found issues"
+          },
+          {
+            "type": "command",
+            "command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/sg-python.sh\" \"${CLAUDE_PLUGIN_ROOT}/hooks/security_reminder_hook.py\"",
+            "if": "Bash(gt submit:*)",
+            "asyncRewake": true,
+            "rewakeMessage": "Background security review of pushed commits not yet reviewed — address or acknowledge the findings below, then continue with the user's original request or continue waiting for their reply:",
+            "rewakeSummary": "Push security review found issues"
           }
         ],
         "matcher": "Bash"

plugins/security-guidance/hooks/llm.py

@@ -27,7 +27,7 @@ from typing import Optional, Tuple, Dict, Any, List
 
 import extensibility
 import review_api
-from _base import debug_log, _record_usage, _PV, PROVENANCE_TAG  # noqa: F401
+from _base import debug_log, _record_usage, _record_http_error, _PV, PROVENANCE_TAG, state_dir as _resolve_state_dir  # noqa: F401
 from session_state import with_locked_state
 
 
@@ -355,10 +355,7 @@ def _call_claude_via_sdk(prompt, output_schema, *, max_tokens=16000, model=None)
         # Try the venv ensure_agent_sdk.py builds. Same fallback logic as
         # agentic_review() — duplicated here so the 3P path doesn't require
         # the agentic path to have run first.
-        _state_dir = os.environ.get(
-            "SECURITY_WARNINGS_STATE_DIR",
-            os.path.expanduser("~/.claude/security"),
-        )
+        _state_dir = _resolve_state_dir()
         _inject_agent_sdk_venv_into_syspath(_state_dir)
         try:
             import asyncio as _asyncio  # noqa: F811
@@ -371,6 +368,7 @@ 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
@@ -428,6 +426,7 @@ 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})")
@@ -436,6 +435,7 @@ 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
 
 
@@ -482,10 +482,21 @@ def _call_claude(prompt, output_schema, thinking_budget=10000, max_tokens=16000,
         "max_tokens": max_tokens,
         "system": CLAUDE_CODE_SYSTEM_PROMPT,
         "messages": [{"role": "user", "content": prompt}],
-        "output_format": {
-            "type": "json_schema",
-            "schema": output_schema
-        }
+        # API moved the structured-output schema from top-level `output_format`
+        # to `output_config.format` per
+        # https://platform.claude.com/docs/en/build-with-claude/structured-outputs.
+        # The old form "continues to work for a transition period" for some
+        # auth modes (API key + non-streaming), but is rejected with
+        # `invalid_request_error: output_format: This field is deprecated.
+        # Use 'output_config.format' instead.` for others (OAuth Bearer +
+        # newer CLI versions hit it consistently — reporter saw 462 errors
+        # in one day). See #2098.
+        "output_config": {
+            "format": {
+                "type": "json_schema",
+                "schema": output_schema,
+            },
+        },
     }
     if thinking_budget > 0:
         # Models trained on adaptive thinking (4.6+) reject the budget_tokens
@@ -493,7 +504,10 @@ def _call_claude(prompt, output_schema, thinking_budget=10000, max_tokens=16000,
         # models (4.5 and earlier, all 3.x) reject adaptive. Pick by model.
         if _model_supports_adaptive_thinking(payload["model"]):
             payload["thinking"] = {"type": "adaptive"}
-            payload["output_config"] = {"effort": "high"}
+            # Merge `effort` into the existing output_config dict (which
+            # now carries the `format` schema) rather than reassigning —
+            # otherwise the schema is silently overwritten. See #2098.
+            payload["output_config"]["effort"] = "high"
         else:
             payload["thinking"] = {
                 "type": "enabled",
@@ -531,6 +545,7 @@ 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:
@@ -540,6 +555,7 @@ 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:
@@ -548,6 +564,7 @@ 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)
@@ -1145,10 +1162,7 @@ def agentic_review(
         # ~/.claude/security/ with the SDK installed; try that as a fallback
         # before giving up. The system import is attempted first so users
         # who DO have it never touch the venv.
-        _state_dir = os.environ.get(
-            "SECURITY_WARNINGS_STATE_DIR",
-            os.path.expanduser("~/.claude/security"),
-        )
+        _state_dir = _resolve_state_dir()
         _venv_tried = _inject_agent_sdk_venv_into_syspath(_state_dir)
         try:
             import asyncio as _asyncio  # noqa: F811

plugins/security-guidance/hooks/security_reminder_hook.py

@@ -82,6 +82,7 @@ from _base import (  # noqa: E402,F401
     PROVENANCE_TAG, PROVENANCE_BANNER,
     _read_plugin_version_int, _PV, _USAGE, _USAGE_LOCK,
     _PRICE_PER_MTOK, _PRICE_DEFAULT, _record_usage, _usage_metrics,
+    state_dir as _resolve_state_dir,
 )
 import extensibility  # noqa: E402
 from patterns import (  # noqa: E402,F401
@@ -190,7 +191,13 @@ CONTINUATION_SUFFIX = (
     "response."
 )
 
-def emit_metrics(metrics, rewake_summary=None):
+def emit_metrics(
+    metrics,
+    rewake_summary=None,
+    additional_context=None,
+    system_message=None,
+    hook_event_name="PostToolUse",
+):
     """
     Write a SyncHookJSONOutput line to stdout for Claude Code to pick up.
     For asyncRewake (Stop) hooks, CC scans stdout for the first {-prefixed line
@@ -213,6 +220,45 @@ def emit_metrics(metrics, rewake_summary=None):
     rewakeSummary in hooks.json, shown to the user in the terminal as the
     task-notification one-liner. Must be in the same JSON line as the metrics
     because CC stops scanning stdout after the first {-prefixed line.
+
+    `additional_context` (asyncRewake findings): model-visible guidance text.
+    Delivery channel depends on `hook_event_name` because CC's hook-output
+    contract is NOT symmetric across events:
+
+      - PostToolUse (commit-review, push-sweep): surfaced via the modern
+        hookSpecificOutput.additionalContext protocol. `PostToolUse` is a
+        member of CC's hookSpecificOutput discriminated union
+        (coreSchemas.ts), so the JSON validates and metrics/rewakeSummary
+        are consumed. See #1375 / #1783 for why this replaced the legacy
+        stderr + exit(2) shape for PostToolUse.
+
+      - Stop / SubagentStop: there is NO `Stop` member in that union, so
+        emitting hookSpecificOutput{hookEventName:"Stop"} makes the whole
+        line fail isSyncHookJSONOutput validation — which on the asyncRewake
+        path silently drops metrics AND rewakeSummary, and (because the
+        legacy stderr write was removed) leaks the raw JSON to the model as
+        the rewake body. CC's asyncRewake delivery actually reads
+        `stderr || stdout` for the model-visible body and only scans stdout
+        JSON for metrics+rewakeSummary — it never reads additionalContext
+        on this path. So for Stop we use the documented clean pattern:
+        guidance on stderr, valid JSON (metrics + rewakeSummary +
+        top-level decision/reason) on stdout. The top-level decision:"block"
+        + reason also covers the sync-fallback path (single-shot `claude -p`,
+        where asyncRewake degrades to a sync Stop hook that reads
+        decision/reason). See #2159.
+
+    Empty/None additional_context emits neither channel (back-compat for
+    metrics-only callers).
+
+    `system_message` (optional, asyncRewake only): user-visible TUI message,
+    distinct from rewakeSummary which is the task-notification one-liner.
+    Use sparingly — the rewakeMessage in hooks.json is the primary user
+    surface; systemMessage adds a per-fire override when the static
+    rewakeMessage isn't specific enough for the finding being shown.
+
+    `hook_event_name` (used only when additional_context is set): selects the
+    delivery channel above. Defaults to "PostToolUse" (commit-review and
+    push-sweep are the most common callers); handle_stop_hook passes "Stop".
     """
     head = {}
     if _PV and "pv" not in metrics:
@@ -223,6 +269,26 @@ def emit_metrics(metrics, rewake_summary=None):
     out = {"metrics": metrics}
     if rewake_summary:
         out["rewakeSummary"] = rewake_summary
+    if additional_context:
+        if hook_event_name in ("Stop", "SubagentStop"):
+            # Stop is NOT in CC's hookSpecificOutput union — emitting it there
+            # fails schema validation and drops metrics+rewakeSummary (#2159).
+            # Clean pattern: guidance on stderr (the asyncRewake body channel,
+            # delivered via `stderr || stdout`), top-level decision/reason for
+            # the sync-fallback path. stdout JSON stays valid so metrics +
+            # rewakeSummary survive.
+            sys.stderr.write(additional_context)
+            sys.stderr.flush()
+            out["decision"] = "block"
+            out["reason"] = additional_context
+        else:
+            # PostToolUse et al. — valid union member; modern protocol.
+            out["hookSpecificOutput"] = {
+                "hookEventName": hook_event_name,
+                "additionalContext": additional_context,
+            }
+    if system_message:
+        out["systemMessage"] = system_message
     print(json.dumps(out), flush=True)
 
 # =====================================================================
@@ -510,7 +576,11 @@ def handle_user_prompt_submit(input_data):
     elif sha:
         debug_log(f"Captured git baseline: {sha[:12]}")
     else:
-        debug_log("Failed to capture git baseline (not a git repo?)")
+        # Show cwd so the next reporter can immediately see when this isn't
+        # actually "not a git repo" but a path-encoding / permissions / git
+        # invocation failure. See #2099.
+        debug_log(f"Failed to capture git baseline (cwd={cwd!r}) — not a git repo, "
+                  f"or git invocation failed (check log entries above)")
 
     sys.exit(0)
 
@@ -594,8 +664,29 @@ _COMMIT_SHA_RE = re.compile(r'^\[[^\]]*?\b([0-9a-f]{7,40})\]', re.MULTILINE)
 # detection — it does NOT tolerate `git -c k=v commit` global options, which
 # keeps this hook aligned with CC's commit attribution on what counts as a
 # commit.
-_GIT_COMMIT_RE = re.compile(r'\bgit\s+commit(?:\s|$)')
-_GIT_AMEND_RE = re.compile(r'\s--amend\b')
+#
+# Also matches `gt create` and `gt modify` — Graphite's stacked-PR wrapper
+# around git. `gt create` produces a new commit (mapped to git commit
+# semantics); `gt modify` amends the current commit (mapped to git commit
+# --amend, also flagged by _GIT_AMEND_RE below). The hooks.json matcher
+# widening for `gt create:*` / `gt modify:*` / `gt submit:*` ships in the
+# same change set — without that widening this regex change is dead code
+# because the hook subprocess never spawns for gt invocations. See #2048.
+_GIT_COMMIT_RE = re.compile(
+    # `git -C <path>` and `git -c key=val` global options are allowed between
+    # `git` and `commit` (mirrors the long-standing tolerance in
+    # _GIT_PUSH_RE). Without this, `git -C /repo commit` is silently dropped
+    # by the handler — see #2089's secondary finding. The gt branch has no
+    # global-option layer to worry about.
+    r'\bgit(?:\s+-[Cc]\s+\S+|\s+--\S+=\S+)*\s+commit\b'
+    r'|\bgt\s+(?:create|modify)\b'
+)
+# Match either the `--amend` flag (with the leading whitespace boundary
+# preserved from the original) OR `gt modify` which is semantically an
+# amend. The handler treats matches as "find the pre-amend SHA via reflog
+# and diff against THAT, not against the post-amend HEAD's parent" — same
+# code path for both git --amend and gt modify.
+_GIT_AMEND_RE = re.compile(r'(?:\s--amend\b|\bgt\s+modify\b)')
 
 # Rolling-window cap on LLM commit-review calls. See atomic_check_rate_limit
 # docstring for the rationale that motivated the switch from a lifetime cap.
@@ -624,8 +715,13 @@ COMMIT_REVIEW_RATE_WINDOW_S = int(
 # entry would buy minimal extra coverage (sessions that push only via gh) at
 # the cost of an extra python spawn on every `... && gh pr create` compound
 # (the common case). Those sessions are caught on their next standalone `git push`.
+# Matches `git push` (with optional `-c k=v` / `-C path` global options
+# CC's hooks.json matcher doesn't tolerate) OR `gt submit` — Graphite's
+# stacked-PR push command. gt submit forwards to `git push` internally,
+# but the bash hook fires on Claude's top-level command so we need to
+# recognize gt submit at the matcher level. See #2048.
 _GIT_PUSH_RE = re.compile(
-    r'\bgit(?:\s+-[cC]\s+\S+|\s+--\S+=\S+)*\s+push\b'
+    r'(?:\bgit(?:\s+-[cC]\s+\S+|\s+--\S+=\S+)*\s+push\b|\bgt\s+submit\b)'
 )
 
 # `git push` stdout: "abc1234..def5678  branch -> branch" (or `+abc..def` on
@@ -791,23 +887,30 @@ def _detect_prev_upstream(repo_root, bash_output):
     # @{u}@{1} — only meaningful if an upstream is configured.
     for ref in ("@{u}@{1}", "@{push}@{1}"):
         try:
+            # See #2099: stdout is a SHA but stderr can carry non-ASCII git
+            # warnings — keep bytes raw to avoid cp1252 reader-thread crash.
             r = subprocess.run(
                 [*GIT_CMD, "rev-parse", "--verify", "-q", ref],
-                cwd=repo_root, capture_output=True, text=True, timeout=5,
+                cwd=repo_root, capture_output=True, timeout=5,
             )
-            if r.returncode == 0 and r.stdout.strip():
-                return r.stdout.strip()
+            sha = r.stdout.decode("utf-8", errors="replace").strip()
+            if r.returncode == 0 and sha:
+                return sha
         except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
             pass
     main = _detect_main_branch(repo_root)
     if main:
         try:
+            # See #2099: drop text=True; decode bytes manually so a
+            # cp1252-undefined byte in git's stderr doesn't crash the
+            # reader thread.
             r = subprocess.run(
                 [*GIT_CMD, "merge-base", "HEAD", main],
-                cwd=repo_root, capture_output=True, text=True, timeout=5,
+                cwd=repo_root, capture_output=True, timeout=5,
             )
-            if r.returncode == 0 and r.stdout.strip():
-                return r.stdout.strip()
+            sha = r.stdout.decode("utf-8", errors="replace").strip()
+            if r.returncode == 0 and sha:
+                return sha
         except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
             pass
     return None
@@ -1121,18 +1224,18 @@ def handle_commit_review_posttooluse(input_data):
             # core.quotePath=false: emit raw UTF-8 in `diff --git a/... b/...`
             # headers so non-ASCII paths aren't C-quoted past the downstream
             # parse_diff_into_files regex (sibling of #2056 / #2075). See #2082.
+            # core.quotePath=false comes from GIT_CMD globally (see gitutil.py).
             if pre_amend_sha:
                 # Delta review: pre-amend → post-amend. `git diff` (not show)
                 # so the output is a pure unified diff with no commit header.
                 result = subprocess.run(
-                    [*GIT_CMD, "-c", "core.quotePath=false",
-                     "diff", "--no-color", "--no-ext-diff", pre_amend_sha, sha, "--"],
+                    [*GIT_CMD, "diff", "--no-color", "--no-ext-diff",
+                     pre_amend_sha, sha, "--"],
                     cwd=repo_root, capture_output=True, timeout=15
                 )
             else:
                 result = subprocess.run(
-                    [*GIT_CMD, "-c", "core.quotePath=false",
-                     "show", "-p", "--no-color", "--no-ext-diff", sha, "--"],
+                    [*GIT_CMD, "show", "-p", "--no-color", "--no-ext-diff", sha, "--"],
                     cwd=repo_root, capture_output=True, timeout=15
                 )
         except (subprocess.TimeoutExpired, FileNotFoundError, OSError) as e:
@@ -1259,12 +1362,13 @@ def handle_commit_review_posttooluse(input_data):
     try:
         full_shas = []
         for s in shas:
+            # See #2099: drop text=True; decode manually for cp1252 safety.
             r = subprocess.run(
                 [*GIT_CMD, "rev-parse", "--verify", "-q", s],
-                cwd=repo_root, capture_output=True, text=True, timeout=5,
+                cwd=repo_root, capture_output=True, timeout=5,
             )
             if r.returncode == 0:
-                full_shas.append(r.stdout.strip())
+                full_shas.append(r.stdout.decode("utf-8", errors="replace").strip())
         _append_reviewed_shas(repo_root, full_shas, vulns_found=len(vulns or []))
     except Exception:
         pass
@@ -1366,18 +1470,26 @@ def handle_commit_review_posttooluse(input_data):
         if s in sev:
             sev[s] += 1
 
+    # Rebuild guidance from new_vulns only — concrete_guidance from the LLM
+    # still lists deduped entries. Pass via additional_context so CC surfaces
+    # the reason via hookSpecificOutput.additionalContext instead of empty
+    # stdout (#1783) / stderr-only "json output validation failed" (#1375).
+    _commit_guidance = (PROVENANCE_BANNER + "\n\n"
+                        + _format_vulns_guidance(new_vulns)
+                        + CONTINUATION_SUFFIX + "\n")
     emit_metrics({
         "vulns_found": len(new_vulns), **_base, **_agentic_m,
         "critical_count": sev["critical"], "high_count": sev["high"],
         "files_reviewed": len(diff_files), "review_ms": review_ms,
         **({"deduped": n_deduped} if n_deduped else {}),
-    }, rewake_summary=_format_vulns_summary(new_vulns, prefix="Commit security review found"))
+    }, rewake_summary=_format_vulns_summary(new_vulns, prefix="Commit security review found"),
+       additional_context=_commit_guidance,
+       hook_event_name="PostToolUse")
 
-    # Rebuild guidance from new_vulns only — concrete_guidance from the LLM
-    # still lists deduped entries.
-    sys.stderr.write(PROVENANCE_BANNER + "\n\n"
-                     + _format_vulns_guidance(new_vulns)
-                     + CONTINUATION_SUFFIX + "\n")
+    # exit(2) is preserved per the asyncRewake protocol — it's what CC
+    # uses as the "force fix" signal that triggers the rewakeMessage flow.
+    # The stderr.write was removed; additional_context above now carries
+    # the same text via the modern JSON channel. See #1358/#1375/#1783.
     sys.exit(2)
 
 def handle_push_sweep_posttooluse(input_data):
@@ -1458,9 +1570,10 @@ def handle_push_sweep_posttooluse(input_data):
     # both.
     head = None
     try:
+        # See #2099: drop text=True; decode manually for cp1252 safety.
         r = subprocess.run([*GIT_CMD, "rev-parse", "HEAD"], cwd=repo_root,
-                           capture_output=True, text=True, timeout=5)
-        head = r.stdout.strip() if r.returncode == 0 else None
+                           capture_output=True, timeout=5)
+        head = r.stdout.decode("utf-8", errors="replace").strip() if r.returncode == 0 else None
     except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
         pass
     push_section = _push_section(bash_output or "")
@@ -1490,14 +1603,15 @@ def handle_push_sweep_posttooluse(input_data):
         quiet_success = False
         if not (bash_output or "").strip() and not interrupted:
             try:
+                # See #2099: drop text=True; decode manually for cp1252 safety.
                 r_cur = subprocess.run(
                     [*GIT_CMD, "rev-parse", "--verify", "-q", "@{u}"],
-                    cwd=repo_root, capture_output=True, text=True, timeout=5)
+                    cwd=repo_root, capture_output=True, timeout=5)
                 r_prev = subprocess.run(
                     [*GIT_CMD, "rev-parse", "--verify", "-q", "@{u}@{1}"],
-                    cwd=repo_root, capture_output=True, text=True, timeout=5)
-                cur = r_cur.stdout.strip() if r_cur.returncode == 0 else ""
-                prev_u = r_prev.stdout.strip() if r_prev.returncode == 0 else ""
+                    cwd=repo_root, capture_output=True, timeout=5)
+                cur = r_cur.stdout.decode("utf-8", errors="replace").strip() if r_cur.returncode == 0 else ""
+                prev_u = r_prev.stdout.decode("utf-8", errors="replace").strip() if r_prev.returncode == 0 else ""
                 quiet_success = bool(cur and prev_u and cur == head and prev_u != cur)
             except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
                 pass
@@ -1511,11 +1625,12 @@ def handle_push_sweep_posttooluse(input_data):
         # reviewed-shas state.
         for local_ref in new_branch_matches:
             try:
+                # See #2099: drop text=True; decode manually for cp1252 safety.
                 r = subprocess.run(
                     [*GIT_CMD, "rev-parse", "--verify", "-q", local_ref],
-                    cwd=repo_root, capture_output=True, text=True, timeout=5,
+                    cwd=repo_root, capture_output=True, timeout=5,
                 )
-                local_sha = r.stdout.strip() if r.returncode == 0 else ""
+                local_sha = r.stdout.decode("utf-8", errors="replace").strip() if r.returncode == 0 else ""
             except (subprocess.TimeoutExpired, FileNotFoundError, OSError):
                 local_sha = ""
             if local_sha and local_sha != head:
@@ -1634,17 +1749,23 @@ def handle_push_sweep_posttooluse(input_data):
     # Metrics — keep within the 10-key cap; agentic sub-metrics are dropped
     # here in favour of the push-sweep funnel keys (telemetry can join on session_id
     # to the per-commit fires for agentic detail). rewake_summary must ride
-    # this line (CC reads only the first {-prefixed stdout line); it's a
-    # no-op when new_vulns is empty since we exit 0 below.
-    emit_metrics({
+    # this line (CC reads only the first {-prefixed stdout line); the emit
+    # is deferred to the two exit points below so the with-vulns path can
+    # also pass additional_context in the same JSON line (#1375/#1783) —
+    # the by-design "CC keeps only the first JSON line" constraint means
+    # we can't emit twice. Builds the shared metrics dict here; vulns path
+    # adds additional_context, no-vulns path emits as-is.
+    _push_metrics = {
         **_base, "pushed": len(push_range), "unreviewed": len(tail),
         "prefix_advanced": prefix_advanced, "vulns_found": len(new_vulns),
         "files_reviewed": len(diff_files), "review_ms": review_ms,
         **({"deduped": n_deduped} if n_deduped else {}),
-    }, rewake_summary=_format_vulns_summary(new_vulns, prefix="Push security review found"))
+    }
+    _push_rewake_summary = _format_vulns_summary(new_vulns, prefix="Push security review found")
 
     if not new_vulns:
         debug_log("Push sweep: no new findings")
+        emit_metrics(_push_metrics, rewake_summary=_push_rewake_summary)
         sys.exit(0)
 
     # First-push of a big branch can surface many findings at once across
@@ -1697,9 +1818,14 @@ def handle_push_sweep_posttooluse(input_data):
         guidance = _format_vulns_guidance(reported) or ""
     else:
         guidance = concrete_guidance or _format_vulns_guidance(reported) or ""
-    sys.stderr.write(
-        PROVENANCE_BANNER + "\n\n" + guidance + CONTINUATION_SUFFIX + "\n"
-    )
+    # Emit metrics + additional_context together — single JSON line is the
+    # contract CC's hook parser expects. exit(2) preserved as the asyncRewake
+    # "force fix" trigger (see comment near handle_commit_review_posttooluse).
+    # See #1358 / #1375 / #1783.
+    emit_metrics(_push_metrics, rewake_summary=_push_rewake_summary,
+                 additional_context=(PROVENANCE_BANNER + "\n\n"
+                                     + guidance + CONTINUATION_SUFFIX + "\n"),
+                 hook_event_name="PostToolUse")
     sys.exit(2)
 
 def handle_stop_hook(input_data):
@@ -1932,6 +2058,11 @@ def handle_stop_hook(input_data):
         # untracked_baseline_n is the signal for whether the UPS-time
         # untracked-snapshot capture actually ran.
         sweep_trimmed = {k: v for k, v in sweep.items() if k != "warn_unresolved_mask"}
+        # Pass guidance via additional_context so CC surfaces the findings via
+        # hookSpecificOutput.additionalContext instead of stderr-only (which
+        # was the cause of "json output validation failed" / empty-reason UI in
+        # #1375 / #1783). exit(2) preserved as the asyncRewake "force fix"
+        # signal — that's the documented mechanism. See #1358 / #1375 / #1783.
         emit_metrics({
             "vulns_found": len(vulns),
             "untracked_baseline_n": len(untracked_at_baseline),
@@ -1945,10 +2076,10 @@ def handle_stop_hook(input_data):
             **({"diff_truncated": llm._last_review_truncated_bytes}
                if llm._last_review_truncated_bytes else {}),
             **sweep_trimmed,
-        }, rewake_summary=_format_vulns_summary(vulns))
-
-        # Exit code 2 with stderr forces Claude to continue and fix
-        sys.stderr.write(PROVENANCE_BANNER + "\n\n" + concrete_guidance + CONTINUATION_SUFFIX + "\n")
+        }, rewake_summary=_format_vulns_summary(vulns),
+           additional_context=(PROVENANCE_BANNER + "\n\n"
+                               + concrete_guidance + CONTINUATION_SUFFIX + "\n"),
+           hook_event_name="Stop")
         sys.exit(2)
 
     if llm._last_call_claude_http_error is not None:
@@ -1976,10 +2107,7 @@ def handle_stop_hook(input_data):
     })
     sys.exit(0)
 
-_SDK_BOOTSTRAP_THROTTLE = os.path.join(
-    os.environ.get("SECURITY_WARNINGS_STATE_DIR")
-    or os.path.expanduser("~/.claude/security"),
-    ".sdk_bootstrap_spawned")
+_SDK_BOOTSTRAP_THROTTLE = os.path.join(_resolve_state_dir(), ".sdk_bootstrap_spawned")
 
 def _maybe_bootstrap_agent_sdk_async():
     """Fire-and-forget SDK bootstrap, for remote-pod environments.

plugins/security-guidance/hooks/session_state.py

@@ -19,7 +19,7 @@ import os
 import re
 from datetime import datetime
 
-from _base import debug_log
+from _base import debug_log, state_dir as _state_dir
 
 
 def _state_key(session_id):
@@ -36,20 +36,20 @@ def _state_key(session_id):
 
 def get_state_file(session_id):
     """Get session-specific state file path."""
-    state_dir = os.environ.get("SECURITY_WARNINGS_STATE_DIR", os.path.expanduser("~/.claude/security"))
+    state_dir = _state_dir()
     return os.path.join(state_dir, f"security_warnings_state_{_state_key(session_id)}.json")
 
 
 def get_lock_file(session_id):
     """Get session-specific lock file path."""
-    state_dir = os.environ.get("SECURITY_WARNINGS_STATE_DIR", os.path.expanduser("~/.claude/security"))
+    state_dir = _state_dir()
     return os.path.join(state_dir, f"security_warnings_state_{_state_key(session_id)}.lock")
 
 
 def cleanup_old_state_files():
     """Remove state files and lock files older than 30 days."""
     try:
-        state_dir = os.environ.get("SECURITY_WARNINGS_STATE_DIR", os.path.expanduser("~/.claude/security"))
+        state_dir = _state_dir()
         if not os.path.exists(state_dir):
             return
 

plugins/security-guidance/hooks/sg-python.sh

@@ -22,6 +22,17 @@
 #        "${CLAUDE_PLUGIN_ROOT}/hooks/security_reminder_hook.py"
 set -e
 
+# Force UTF-8 for ALL Python filesystem + IO operations (PEP 540).
+# Without this, Windows Python defaults `locale.getpreferredencoding()` to
+# cp1252 — which makes `text=True` in subprocess.run / open() / json.load
+# crash the internal reader thread on any byte that's undefined in cp1252
+# (e.g. the 0x81 byte from ف, present in any path/filename with
+# Arabic/Hebrew/CJK characters). See #2056, #2099.
+#
+# No-op on macOS/Linux (already UTF-8). Must be set BEFORE Python starts —
+# changing it from inside the interpreter has no effect.
+export PYTHONUTF8=1
+
 # Git Bash / MSYS on Windows hands script paths to this shim in POSIX form
 # (`/c/Users/...`). When we exec a Windows `python.exe` (which we do on
 # Windows since `python3` is the Microsoft Store stub), python interprets the