8 Commits

Author SHA1 Message Date
Luis Pater
291cfb87ef feat(codex): support orphan delegation compatibility via orphan-delegation-compatibility
- Add `codex.orphan-delegation-compatibility` configuration option and mirror it to SDK configuration.
- Convert orphan Codex delegation outputs into standard user messages for requests with `X-Openai-Subagent: collab_spawn`.
- Integrate orphan delegation rewriting into OpenAI responses request handling pipeline.

Closes: #5401
2026-09-03 20:21:24 +08:00
Luis Pater
b08fe3b492 fix(codex): preserve multi-agent-v2 namespace handling across incremental websocket turns
Closes: #4909
2026-08-12 15:04:17 +08:00
sususu
5fa66293db fix(antigravity): preserve request plugin hook semantics 2026-08-11 16:07:42 +08:00
sususu
cf8c27fe90 perf(antigravity): translate each upstream request once
Execute, executeClaudeNonStream and ExecuteStream all assign the validated
original payload to the request and then translate both values. Since both
translations saw the same bytes, every Antigravity request paid for a second
full scan of the client payload. On a captured 24MB tool-history request that
second pass cost roughly 0.9s of CPU and 651MB of allocations.

Translate once when both inputs share a backing array and hand the caller an
independent duplicate, because later stages edit the working copy in place.
Payloads that genuinely differ still get two translations.
2026-08-11 16:07:42 +08:00
Luis Pater
0a95fa62a1 feat(compat): preserve Claude thinking/tool-call content for is-compat OpenAI compatibility models
- Add `is-compat` support to OpenAI compatibility model config, capabilities, hashing, and example config.
- Propagate `IsCompat` through API-key model resolution and switch OpenAI-compat executor translation to compatibility-aware routing.
- Keep Claude assistant thinking content in compatibility mode while keeping default behavior unchanged when `is-compat` is disabled.

Closes: #4776
2026-08-07 06:26:33 +08:00
Luis Pater
dcee14dd3c feat(compat): preserve compat-mode thinking/signature blocks for API-key models
- Added `is-compat` model metadata plumbing from config through executor and helpers, including hash computation.
- Introduced a compatibility-aware translation path (`TranslateRequestWithAPIKeyModelCompatibility`) and wired it into Claude/Gemini/Codex/Interactions request flows.
- Updated Claude message sanitization/translation behavior to keep empty-thinking compatibility blocks (including signatures) when `is-compat` is enabled, while keeping default behavior unchanged.
2026-08-06 17:19:24 +08:00
Luis Pater
e5ea945ed9 feat(codex): add model-level is-compat flag to rewrite MultiAgentV2 agent_message for Responses-compatible endpoints
Closes: #4801
2026-08-06 04:49:28 +08:00
Luis Pater
84bf9376e5 feat(executor): replace sdktranslator.TranslateRequest with helps.TranslateRequestWithCodexMultiAgentV2
- Updated Kimi and Gemini executors to use `TranslateRequestWithCodexMultiAgentV2` for improved multi-agent v2 optimization.
- Enhanced configuration and API server to support `CodexOptimizeMultiAgentV2`.
- Added codex multi-agent V2 optimizations in `config`, `executor`, and `watcher` modules.
2026-07-25 00:32:37 +08:00