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>

apps/desktop/electron/codex-link.ts

@@ -79,7 +79,7 @@ export interface CodexLinkDeps {
 
 // The single wait this feature owns: how long a freshly spawned bridge gets to
 // answer its status endpoint before the apply gives up.
-export const CODEX_BRIDGE_START_BUDGET_MS = 10_000
+export const CODEX_BRIDGE_START_BUDGET_MS = 45_000
 const START_POLL_INTERVAL_MS = 500
 // A probe of an already-running (or absent) local bridge. Loopback answers or
 // refuses at once; the bound only keeps Settings from hanging on a wedged port.