fix(custom-model): core review fixes for context-length discovery and injection

- share one context-length resolution (discovered figure, endpoint default fallback) across the routes and boot recovery, with a recovery test
- record listed per-slot context figures with a slot count of 1 and force the slot-count fallback once per rediscovery
- open up the codex model launch token for qwen3-style ids (model-plain-colon), pinned by a spawn-golden case
- pass the full discovered window to opencode as limit.context
- translate the picker search strings and document the discovery precedence
This commit is contained in:
Devvyn committed 2026-11-01 21:26:54 +08:00
1 parent dbd1b6e587
commit 1b8ac40baf
16 files changed
+256 -47

No files matched your search

+5
View File
@@ -21,6 +21,7 @@ export type TokenPattern =
| 'model'
| 'model-claude'
| 'model-plain'
| 'model-plain-colon'
| 'model-pi'
| 'id'
| 'id-dotted'
@@ -47,6 +48,10 @@ const PATTERNS: Record<TokenPattern, RegExp> = {
// copilot --model. Same characters as `model`, but a leading alphanumeric: the value follows a
// flag, so `--yolo` must not pass as a model id and become its own flag (the allowAll clamp bypass).
'model-plain': /^[a-zA-Z0-9][a-zA-Z0-9._\-/]*$/,
// codex --model, and the value a custom-model `launchModel` is forced onto it. Same
// shape as `model-plain` (leading alphanumeric, so a flag cannot ride the flag) plus
// `:` — Ollama-style ids like `qwen3:32b` must survive onto the command line.
'model-plain-colon': /^[a-zA-Z0-9][a-zA-Z0-9._\-/:]*$/,
// buildPiCommand — `:` for a thinking suffix (`sonnet:high`), `/` for `provider/id`
'model-pi': /^[a-zA-Z0-9._\-/:]+$/,
// opencode --session, codex resume