Commit Graph

24 Commits

Author SHA1 Message Date
Peter Steinberger
c97bf23a4a fix: gate openai reasoning downgrade on model switches (#1562) (thanks @roshanasingh4) 2026-01-24 08:16:42 +00:00
Roshan Singh
202d7af855 Fix OpenAI Responses transcript after model switch 2026-01-24 07:58:25 +00:00
Dave Lauer
d03c404cb4
feat(compaction): add adaptive chunk sizing, progressive fallback, and UI indicator (#1466)
* fix(ui): allow relative URLs in avatar validation

The isAvatarUrl check only accepted http://, https://, or data: URLs,
but the /avatar/{agentId} endpoint returns relative paths like /avatar/main.
This caused local file avatars to display as text instead of images.

Fixes avatar display for locally configured avatar files.

* fix(gateway): resolve local avatars to URL in HTML injection and RPC

The frontend fix alone wasn't enough because:
1. serveIndexHtml() was injecting the raw avatar filename into HTML
2. agent.identity.get RPC was returning raw filename, overwriting the
   HTML-injected value

Now both paths resolve local file avatars (*.png, *.jpg, etc.) to the
/avatar/{agentId} endpoint URL.

* feat(compaction): add adaptive chunk sizing and progressive fallback

- Add computeAdaptiveChunkRatio() to reduce chunk size for large messages
- Add isOversizedForSummary() to detect messages too large to summarize
- Add summarizeWithFallback() with progressive fallback:
  - Tries full summarization first
  - Falls back to partial summarization excluding oversized messages
  - Notes oversized messages in the summary output
- Add SAFETY_MARGIN (1.2x) buffer for token estimation inaccuracy
- Reduce MIN_CHUNK_RATIO to 0.15 for very large messages

This prevents compaction failures when conversations contain
unusually large tool outputs or responses that exceed the
summarization model's context window.

* feat(ui): add compaction indicator and improve event error handling

Compaction indicator:
- Add CompactionStatus type and handleCompactionEvent() in app-tool-stream.ts
- Show '🧹 Compacting context...' toast while active (with pulse animation)
- Show '🧹 Context compacted' briefly after completion
- Auto-clear toast after 5 seconds
- Add CSS styles for .callout.info, .callout.success, .compaction-indicator

Error handling improvements:
- Wrap onEvent callback in try/catch in gateway.ts to prevent errors
  from breaking the WebSocket message handler
- Wrap handleGatewayEvent in try/catch with console.error logging
  to isolate errors and make them visible in devtools

These changes address UI freezes during heavy agent activity by:
1. Showing users when compaction is happening
2. Preventing uncaught errors from silently breaking the event loop

* fix(control-ui): add agentId to DEFAULT_ASSISTANT_IDENTITY

TypeScript inferred the union type without agentId when falling back to
DEFAULT_ASSISTANT_IDENTITY, causing build errors at control-ui.ts:222-223.
2026-01-23 06:32:30 +00:00
Peter Steinberger
0396b678fa docs: note transcript hygiene sync 2026-01-23 01:38:05 +00:00
Peter Steinberger
2424404fb4 docs: add transcript hygiene reference 2026-01-23 01:34:21 +00:00
Peter Steinberger
db0235a26a fix: gate transcript sanitization by provider 2026-01-23 00:42:45 +00:00
Peter Steinberger
870bfa94ed fix: skip tool id sanitization for openai responses 2026-01-22 23:51:59 +00:00
Peter Steinberger
e344b7df9c fix: preserve antigravity thinking block types 2026-01-22 08:31:07 +00:00
Peter Steinberger
acdfbee4f9 fix: detect antigravity claude by provider 2026-01-22 08:26:08 +00:00
Peter Steinberger
ff69a9bd9c fix: sanitize antigravity thinking signatures 2026-01-22 08:17:49 +00:00
Peter Steinberger
0704fe7dbb fix: enforce Mistral tool call ids (#1372) (thanks @zerone0x) 2026-01-22 00:43:15 +00:00
Peter Steinberger
41c9c214fc fix: drop obsolete pi-mono workarounds 2026-01-21 19:58:19 +00:00
Peter Steinberger
10a0c96ee6 fix: drop reasoning-only openai-responses history 2026-01-19 06:22:46 +00:00
Peter Steinberger
4965727f39 chore: run format and fix sandbox browser timeouts 2026-01-16 09:18:58 +00:00
Muhammed Mukhthar CM
cd409e5667
fix: exclude google-antigravity from history downgrade hack (#894)
* Agent: exclude google-antigravity from history downgrade hack

* Lint: fix formatting in test

* Lint: formatting and unused vars in test

* fix: preserve google-antigravity tool calls (#894) (thanks @mukhtharcm)

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-01-16 08:14:56 +00:00
Matthieu Bizien
ef36e24522 Agents: sanitize OpenRouter Gemini thoughtSignature 2026-01-16 07:51:49 +00:00
Peter Steinberger
dfa6c5c2b3 fix(google): scrub tool schemas for gemini 2026-01-16 06:57:54 +00:00
Peter Steinberger
3dddbe1053 fix: ignore properties in google tool schema warnings 2026-01-16 02:35:55 +00:00
Peter Steinberger
36292d3fbb fix: preserve Antigravity Claude signatures (#959) (thanks @rdev) 2026-01-15 17:06:39 +00:00
Max
1ae344d8a6 Fix antigravity claude 2026-01-15 17:06:39 +00:00
Peter Steinberger
cd2af64860 fix: cap tool call IDs for OpenAI/OpenRouter (#875) (thanks @j1philli) 2026-01-15 05:25:45 +00:00
Peter Steinberger
5fdaef3646 fix: downgrade unsigned gemini thinking 2026-01-15 04:51:21 +00:00
Peter Steinberger
c379191f80 chore: migrate to oxlint and oxfmt
Co-authored-by: Christoph Nakazawa <christoph.pojer@gmail.com>
2026-01-14 15:02:19 +00:00
Peter Steinberger
bcbfb357be refactor(src): split oversized modules 2026-01-14 01:17:56 +00:00