Commit Graph

1286 Commits

Author SHA1 Message Date
Peter Steinberger
83c24ff5f9 fix: use active auth profile for auto-compaction 2026-01-24 22:23:49 +00:00
Rodrigo Uroz
8fe2b9be43 fix: auto-compact on context overflow promptError before returning error (#1627)
* fix: detect Anthropic 'Request size exceeds model context window' as context overflow

Anthropic now returns 'Request size exceeds model context window' instead of
the previously detected 'prompt is too long' format. This new error message
was not recognized by isContextOverflowError(), causing auto-compaction to
NOT trigger. Users would see the raw error twice without any recovery attempt.

Changes:
- Add 'exceeds model context window' and 'request size exceeds' to
  isContextOverflowError() detection patterns
- Add tests that fail without the fix, verifying both the raw error
  string and the JSON-wrapped format from Anthropic's API
- Add test for formatAssistantErrorText to ensure the friendly
  'Context overflow' message is shown instead of the raw error

Note: The upstream pi-ai package (@mariozechner/pi-ai) also needs a fix
in its OVERFLOW_PATTERNS regex: /exceeds the context window/i should be
changed to /exceeds.*context window/i to match both 'the' and 'model'
variants for triggering auto-compaction retry.

* fix(tests): remove unused imports and helper from test files

Remove WorkspaceBootstrapFile references and _makeFile helper that were
incorrectly copied from another test file. These caused type errors and
were unrelated to the context overflow detection tests.

* fix: trigger auto-compaction on context overflow promptError

When the LLM rejects a request with a context overflow error that surfaces
as a promptError (thrown exception rather than streamed error), the existing
auto-compaction in pi-coding-agent never triggers. This happens because the
error bypasses the agent's message_end → agent_end → _checkCompaction path.

This fix adds a fallback compaction attempt directly in the run loop:
- Detects context overflow in promptError (excluding compaction_failure)
- Calls compactEmbeddedPiSessionDirect (bypassing lane queues since already in-lane)
- Retries the prompt after successful compaction
- Limits to one compaction attempt per run to prevent infinite loops

Fixes: context overflow errors shown to user without auto-compaction attempt

* style: format compact.ts and run.ts with oxfmt

* fix: tighten context overflow match (#1627) (thanks @rodrigouroz)

---------

Co-authored-by: Claude <claude@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-01-24 22:09:24 +00:00
Peter Steinberger
cbdfaf8231 fix: cover elevated ask approvals (#1636) 2026-01-24 21:12:46 +00:00
Ivan Casco
2b3ecfcc64 fix(exec): only set security=full when elevated mode is full (#1616) 2026-01-24 20:55:21 +00:00
Peter Steinberger
25ad0e77bf fix: unify reasoning tags + agent ids (#1613) (thanks @kyleok) (#1629) 2026-01-24 19:56:02 +00:00
Peter Steinberger
0ee847eaff test: skip opencode alpha GLM in live suite 2026-01-24 14:08:16 +00:00
Peter Steinberger
92694492cb fix: sync tests with config normalization 2026-01-24 13:32:26 +00:00
Peter Steinberger
233ce4c8aa fix: drop opencode alpha GLM model 2026-01-24 13:19:55 +00:00
Peter Steinberger
dd5375883a fix: normalize session keys and outbound mirroring 2026-01-24 11:57:11 +00:00
Luke
f4b0648a50 fix(agents): treat provider request-aborted as timeout for fallback (#1576)
* fix(agents): treat request-aborted as timeout for fallback

* test(e2e): add provider timeout fallback
2026-01-24 11:27:24 +00:00
Peter Steinberger
26147b37f4 fix: resolve session ids in session tools 2026-01-24 11:09:11 +00:00
Peter Steinberger
826814aebe feat: add TTS hint to system prompt 2026-01-24 10:25:42 +00:00
Peter Steinberger
5f5a6aa6a5 fix: show tool error fallback for tool-only replies 2026-01-24 08:17:50 +00:00
Peter Steinberger
668cd829b5 fix: gate openai reasoning downgrade on model switches (#1562) (thanks @roshanasingh4) 2026-01-24 08:16:42 +00:00
Peter Steinberger
70a4b1046b feat: move TTS into core (#1559) (thanks @Glucksberg) 2026-01-24 08:00:44 +00:00
Roshan Singh
730be8b617 Fix OpenAI Responses transcript after model switch 2026-01-24 07:58:25 +00:00
Tak hoffman
b0a1b19360 Agents: drop bash tool alias 2026-01-24 07:44:04 +00:00
Peter Steinberger
6ee24fe6cc fix: guard tool allowlists with warnings 2026-01-24 07:38:42 +00:00
Peter Steinberger
2306a321a6 fix: cover slack open policy gating (#1563) (thanks @itsjaydesu) 2026-01-24 07:09:26 +00:00
Andrii
6c9c8a5f1a anthropic-payload-log mvp
Added a dedicated Anthropic payload logger that writes exact request
JSON (as sent) plus per‑run usage stats (input/output/cache read/write)
to a
  standalone JSONL file, gated by an env flag.

  Changes

  - New logger: src/agents/anthropic-payload-log.ts (writes
logs/anthropic-payload.jsonl under the state dir, optional override via
env).
  - Hooked into embedded runs to wrap the stream function and record
usage: src/agents/pi-embedded-runner/run/attempt.ts.

  How to enable

  - CLAWDBOT_ANTHROPIC_PAYLOAD_LOG=1
  - Optional:
CLAWDBOT_ANTHROPIC_PAYLOAD_LOG_FILE=/path/to/anthropic-payload.jsonl

  What you’ll get (JSONL)

  - stage: "request" with payload (exact Anthropic params) +
payloadDigest
  - stage: "usage" with usage
(input/output/cacheRead/cacheWrite/totalTokens/etc.)

  Notes

  - Usage is taken from the last assistant message in the run; if the
run fails before usage is present, you’ll only see an error field.

  Files touched

  - src/agents/anthropic-payload-log.ts
  - src/agents/pi-embedded-runner/run/attempt.ts

  Tests not run.
2026-01-24 06:43:51 +00:00
Peter Steinberger
ad0777754d perf: stabilize system prompt time 2026-01-24 06:24:04 +00:00
Peter Steinberger
fd75fcc349 fix: trigger fallback on auth profile exhaustion 2026-01-24 06:14:23 +00:00
Peter Steinberger
b200328adf fix: enforce group tool policy inheritance for subagents (#1557) (thanks @adam91holt) 2026-01-24 05:49:39 +00:00
Adam Holt
e080b88808 Channels: add per-group tool policies 2026-01-24 05:49:39 +00:00
Peter Steinberger
6a4d478791 fix: ignore identity template placeholders 2026-01-24 05:35:50 +00:00
Peter Steinberger
7815392069 fix: gate diagnostic logs behind verbose 2026-01-24 05:06:42 +00:00
Peter Steinberger
67b9b0ef1f fix: honor tools.exec ask/security in approvals 2026-01-24 04:53:44 +00:00
Peter Steinberger
e74768b428 feat: add node browser proxy routing 2026-01-24 04:21:47 +00:00
Peter Steinberger
857ae47203 fix: align service path tests with platform delimiters 2026-01-24 02:34:54 +00:00
Peter Steinberger
9f4c893785 fix: add readability fallback extraction 2026-01-24 02:15:13 +00:00
Peter Steinberger
76313f7e5e fix: stabilize embedded runner queueing 2026-01-24 02:05:41 +00:00
Peter Steinberger
b9cbce9f4b fix: publish llm-task docs and harden tool 2026-01-24 01:44:51 +00:00
Peter Steinberger
2cecf28971 fix: honor wildcard tool allowlists 2026-01-24 01:30:44 +00:00
Peter Steinberger
77bb342301 fix: refine bedrock discovery defaults (#1543) (thanks @fal3) 2026-01-24 01:18:33 +00:00
Alex Fallah
212b602921 feat: add dynamic Bedrock model discovery
Add automatic discovery of AWS Bedrock models using ListFoundationModels API.
When AWS credentials are detected, models that support streaming and text output
are automatically discovered and made available.

- Add @aws-sdk/client-bedrock dependency
- Add discoverBedrockModels() with caching (default 1 hour)
- Add resolveImplicitBedrockProvider() for auto-registration
- Add BedrockDiscoveryConfig for optional filtering by provider/region
- Filter to active, streaming, text-output models only
- Update docs/bedrock.md with auto-discovery documentation
2026-01-24 01:15:06 +00:00
google-labs-jules[bot]
ec23a856fe chore(tests): remove reproduction test
Removed the test file `src/agents/sandbox/docker.test.ts` as requested in code review.
2026-01-24 00:30:24 +00:00
google-labs-jules[bot]
ff233678a6 fix(sandbox): simplify docker image check
Simplify the stderr check in `dockerImageExists` to only look for "No such image", as requested in code review.
2026-01-24 00:30:24 +00:00
google-labs-jules[bot]
8d797d4a2b fix(sandbox): improve docker image existence check error handling
Previously, `dockerImageExists` assumed any error from `docker image inspect` meant the image did not exist. This masked other errors like socket permission issues.

This change:
- Modifies `dockerImageExists` to inspect stderr when the exit code is non-zero.
- Returns `false` only if the error explicitly indicates "No such image" or "No such object".
- Throws an error with the stderr content for all other failures.
- Adds a reproduction test in `src/agents/sandbox/docker.test.ts`.
2026-01-24 00:30:24 +00:00
Peter Steinberger
c60cedaafc fix: stabilize tests and sync protocol models 2026-01-24 00:25:58 +00:00
Peter Steinberger
f3029e1e3a fix: silence probe timeouts 2026-01-24 00:11:04 +00:00
Peter Steinberger
11469046f1 fix: align compaction summary message types 2026-01-23 23:03:04 +00:00
Peter Steinberger
333df812a3 test(compaction): cover staged pruning 2026-01-23 22:25:07 +00:00
Peter Steinberger
ee341fa491 feat(compaction): apply staged pruning 2026-01-23 22:23:23 +00:00
Peter Steinberger
56c0dc21ab feat(compaction): add staged helpers 2026-01-23 22:23:23 +00:00
Peter Steinberger
a530eebe29 fix: quiet auth probe diagnostics 2026-01-23 19:53:01 +00:00
Peter Steinberger
885b9f4fbc test: stub heavy tools in agent tests 2026-01-23 18:34:33 +00:00
Peter Steinberger
1c51871903 fix: normalize session lock path 2026-01-23 18:34:33 +00:00
Peter Steinberger
a42f924a14 chore: speed up tests and update opencode models 2026-01-23 11:36:32 +00:00
Peter Steinberger
d5a382a8d9 fix: stabilize ci tests 2026-01-23 09:52:22 +00:00
Peter Steinberger
d6d36df9a0 Merge origin/main into fix-discord-accountId 2026-01-23 09:15:44 +00:00