Commit Graph
4 Commits
Author SHA1 Message Date
yilsemandClaude Opus 5.5 1e2b8e2b9c fix(codex-bridge): flatten top-level oneOf/anyOf/allOf in tool schemas for external models
Since bridge 7 external models get Codex's classic tools. One desktop tool has a top-level union schema,
which Claude rejects ("input_schema does not support oneOf, allOf, or anyOf at the top level"), so every
Opus request from the desktop app failed with a bare "upstream 400". The earlier context-size diagnosis
was wrong: the request still failed after compaction (239 KB).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 01:08:27 +03:00
yilsemandClaude Opus 5.5 1445e204da feat(codex-bridge): handoff instruction for Codex Desktop only (off by default)
User decision: the "larger work goes to AITURK" instruction lives only in what Codex IDE sees; the CLI must
not know it exists. The bridge adds it in flight by the originator header (measured: Codex Desktop, codex-tui,
codex_exec) and only when a send command is configured.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 01:05:00 +03:00
yilsemandClaude Opus 5.5 acf88f8314 feat(codex-link): bridge 7 - external models work like subscription models
Measured with the unmodified Codex binary on 10 Oct 2026:
- real context windows per model (NanoGPT list, local table, combo = its
  smallest member, capped at the summarizer's window) so Codex compacts by
  itself when switching to a smaller model; an overflow guard trims
  oversized old parts and reports what still does not fit
- classic tools instead of code mode for external models: GLM 0/3 -> 3/3,
  Qwen 0/3 -> 2/3 on simple tool tasks, Claude/cx/Gemini unchanged
- phase (commentary / final_answer) on external assistant messages
- an answer cut by the client is carried to the next turn once
- images stay for vision-capable targets
- summary brake stops tight loops, not frequent compaction
- permanent gateway errors and tool-less targets fail at once with a
  readable message instead of five reconnects
- a lone "." (used to apply a model change in voice) is answered locally
- the bridge listens within seconds; the IDE waits 45 s for it

Release: AITURK IDE 1.0.0-beta.26.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-10 22:04:58 +03:00
yilsemandClaude Opus 5.5 1ce5ab82cf feat(codex-bridge): ship the local Codex bridge with the IDE
Adds the IDE's models and combos to Codex's model list and keeps conversation
summaries readable across providers, so switching models in Codex no longer
drops the conversation. Standard-library Python, run on the agent venv.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HRDGW1LiKcDUZYUdKBoWYW
2026-10-09 15:46:10 +03:00