bridge.py is now a small splitter with no features: a request for one of
Codex's own models goes to chatgpt.com byte for byte, a request for an added
model goes to kopru.py, which runs as its own process. Codex's own models no
longer pass through the feature code at all, and restarting or losing the
bridge process does not touch them.
Measured with real Codex on spare ports: own model answers; forced compaction
on the own model completes (twice) while the bridge process is restarted;
added model answers; no own-model request reaches the bridge process.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From ten independent read-only audits (11 Oct 2026), verified against the code:
- a permanent gateway error (no tools, 401/402/403, bare upstream 400) ends the turn with a visible
assistant message instead of a silent retry and an empty turn;
- "modeli ... yapma", "X modeli için test yap" and general "hangi model ..." questions are no longer
commands; a name whose version does not fit, or that several models share, is asked back;
- the stream is forwarded as it arrives (read1) and an upstream drop is no longer logged as a client
stop nor saved as an interrupted answer;
- a lone "." joining a running turn is removed without the hook messages after it;
- the interrupted-answer note finds the user message behind hook messages and detects completion
by event type; a per-minute rate limit is not learned as a context window.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A 607 KB Codex request was estimated at 189776 tokens (window 200000), sent untrimmed and rejected by
Claude; the gateway only said "upstream 400", so Codex saw a dropped stream. Claude targets now use
2.6 bytes/token, and that bare 400 on a request filling most of the window becomes context_length_exceeded.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
