abbccc1ba2
`/models` now returns only deepseek-v4-pro and deepseek-v4-flash;
deepseek-chat / deepseek-reasoner sunset 2026-07-24 and the
deepseek-v3.2 hard-coded in the ark-coding fallback list never
existed. Both v4 models default to thinking enabled and the API
toggles via `{"thinking":{"type":"disabled"}}` — keep
`thinkingMode: 'disabled'` so the app's fast/non-thinking default
stays intact (server reasoning paths honor it; the Zig openai-compat
path doesn't emit the toggle yet, so calls through that path still
get provider-default thinking until it's wired). v4-pro promoted to
full tier; legacy aliases pinned to an exact RegExp so future
deepseek-* variants don't inherit a forced disabled mode.
Bandaid for the unwired toggle: v4-pro gets `timeoutMultiplier: 2`
because its default-on reasoning blows past the orchestrator's
planning timeout on long system prompts (observed in dev: planning
phase falls back, sub-agent then succeeds — UX degraded but
functional). Drop the multiplier once the Zig path actually sends
`thinking:{type:disabled}`.
Don't add a BUILTIN_MODEL_LISTS.deepseek entry — DeepSeek exposes
/v1/models, so let `fetchProviderModels` pull the live catalog
through `/api/ai/provider-models` instead of pinning a snapshot
(the ark-coding `deepseek-v3.2` ghost above shows what those
snapshots drift into).
28 lines
280 B
Plaintext
28 lines
280 B
Plaintext
node_modules
|
|
.DS_Store
|
|
*.local
|
|
count.txt
|
|
.env
|
|
.nitro
|
|
.tanstack
|
|
.wrangler
|
|
.vinxi
|
|
__unconfig*
|
|
todos.json
|
|
.openpencil-tmp/
|
|
.superpowers/
|
|
|
|
docs/
|
|
|
|
# Build outputs
|
|
out/
|
|
dist/
|
|
apps/cli/src/commands/skill-bundle.json
|
|
dist-ssr/
|
|
electron-dist/
|
|
dist-electron/
|
|
.claude
|
|
.omx
|
|
.worktrees/
|
|
.omx/
|