Add kimi-k3 (1M context, 131K max output) to the Kimi provider preset
model lists for Codex, Hermes, OpenClaw, and OpenCode, appended after
kimi-k2.7-code so the catalog-first-row default backfill is unchanged.
The Kimi For Coding plan presets keep the kimi-for-coding endpoint
alias and are intentionally untouched.
Codex always sends prompt_cache_key in its Responses requests, but the
Responses -> Chat Completions conversion dropped it, breaking session
cache affinity on upstreams that route by key (e.g. Kimi Coding).
- Re-inject prompt_cache_key after conversion in the forwarder: an
explicit client key wins, otherwise a client-provided session ID;
generated per-request UUIDs are never sent upstream.
- Provider-aware gating: "auto" enables only known-compatible upstreams
(api.openai.com, api.kimi.com/coding) because strict gateways reject
unknown fields with HTTP 400 (e.g. Fireworks); an advanced
Auto/Enabled/Disabled override is available on the Codex form in all
four locales.
- Kimi For Coding preset opts in explicitly.
* Update Longcat presets to LongCat-2.0
* fix(proxy): classify LongCat-2.0 as text-only for media sanitizer
The Longcat presets now use LongCat-2.0, but the known_text_only_model
allowlist still only matched the retired longcat-flash-chat tail. Without
this, images pasted into a text-only LongCat-2.0 session are forwarded
upstream instead of being replaced with the unsupported-image marker,
causing a hard rejection. Add longcat-2.0 (keeping the retired name for
saved configs) and a regression test.
---------
Co-authored-by: chengzifeng <chengzifeng@meituan.com>
Co-authored-by: Jason <farion1231@gmail.com>
Volcengine Ark rejects the bare model name doubao-seed-2-1-pro with a 404
("model does not exist or you do not have access to it") even after the
model is activated; the API requires the full dated id
doubao-seed-2-1-pro-260628. Update the Doubao preset model id across all
apps (config default, generated catalog, and OpenClaw namespaced refs).
Pricing lookup only stripped 8-digit (YYYYMMDD) and ISO date suffixes, not
the 6-digit YYMMDD format Volcengine uses (-260628, -250615), so real
Doubao usage never matched the bare-name pricing seed and showed $0 cost.
Extend strip_model_date_suffix to also strip 6-digit YYMMDD (with
month/day validation to avoid eating non-date version suffixes), keeping
the bare-name pricing seed as the canonical identity. This also fixes
pricing for every other Volcengine Doubao model. Add unit and end-to-end
regression tests.
- Add `qwen3-coder` to the web_search reject model-prefix blacklist so the
native qwen3-coder-plus direct-connect preset suppresses the built-in tool
(百炼 rejects it for the coder series), while general Qwen models sharing the
DashScope host keep web_search enabled. Matched on the model axis, not host.
- Correct LongCat-2.0-Preview context window from 128K to its real 1M
(1048576), aligning with the MiMo/Qwen 2^20 convention.
- Tighten native Responses preset tests to assert exact model→contextWindow
catalogs instead of only checking catalog presence.
Codex providers can now run in two modes per provider:
- Proxy-Chat (route takeover): apiFormat=openai_chat, existing Responses<->Chat conversion. Unchanged.
- Native-Responses (direct): apiFormat=openai_responses, no proxy. cc-switch generates ~/.codex/cc-switch-model-catalog.json so Codex shows the custom models and tools work without the freeform apply_patch (type=custom) tool that native gateways like MiMo reject; editing falls back to shell_command.
Catalog generation is keyed on apiFormat (CodexCatalogToolProfile), decoupled from the takeover toggle, so native providers persist a catalog without enabling local route mapping.
Codex's catalog parser requires base_instructions on every entry; the native template carries a neutral default and per-vendor official text overrides it (MiMo, MiniMax). Synthesized catalogs for Qwen/Doubao/LongCat use the neutral default.
Existing native providers must be re-saved once to regenerate a valid catalog (no DB migration).
Commit 273cc48c migrated 7 CN providers from openai_chat to native
openai_responses and refreshed model ids on the remaining chat-only
providers, but the codexChatProviderPresets snapshot was not updated,
breaking the unit tests on main.
Drop the migrated providers (DouBaoSeed, Bailian, Longcat, MiniMax,
MiniMax en, Xiaomi MiMo x2) from the chat list, sync GLM/StepFun/Ling
model ids, and add a test locking the migrated presets to
openai_responses with no modelCatalog (so the local route-mapping
toggle stays unchecked).
The Codex provider form tied Chat-format conversion and route takeover (model
mapping) to one toggle, so a provider serving a native Responses API could not
use model mapping without forcing Chat Completions conversion.
- Promote the upstream format (Chat Completions / Responses) to an independent,
always-visible selector that triggers no sub-menus on its own.
- The local-routing toggle now solely gates the advanced sub-sections: model
mapping catalog, plus reasoning capability when the format is Chat.
- Persist modelCatalog / codexChatReasoning based on the takeover toggle and
derive its initial state from saved catalog presence (no new persisted field).
- Refresh codexConfig i18n (zh/en/ja/zh-TW): add upstreamFormat* keys and reword
the routing/advanced hints to reflect the decoupling.
- Fix codexChatProviderPresets test expectation for the Doubao Seed 2.1 Pro rename.
Update the Codex chat preset test's Kimi expectation (kimi-k2.6 -> kimi-k2.7-code) after the Kimi K2.7 upgrade, update the Claude Desktop form test for the four-tier (Sonnet/Opus/Fable/Haiku) routes, and reformat UsageDateRangePicker imports (prettier).
* fix(presets): update Zhipu coding plan endpoints
* fix(model-fetch): probe /models on versioned /vN base URLs
The model-list probe assumed any base URL not ending in /v1 needs /v1/models appended. For providers whose base URL already ends in a version segment like /v4 (Zhipu/Z.AI GLM Coding Plan at .../api/coding/paas/v4), this produced .../v4/v1/models which 404s, so the "Fetch models" button always failed.
Detect a trailing /v{N} version segment and probe {base}/models first, keeping /v1/models as a fallback candidate for non-/v1 versions. Fixes Codex/OpenCode/OpenClaw/Hermes GLM presets and any other vN-style endpoint, with no behavior change for /v1 or non-versioned URLs.
---------
Co-authored-by: Jason <farion1231@gmail.com>
Bump default model names project-wide: gpt-5.4 -> gpt-5.5,
gemini-3.x -> gemini-3.5-flash, glm-5 -> glm-5.1, and
grok-code-fast-1 -> grok-build-0.1 across all provider presets
(claude, codex, gemini, hermes, openclaw, opencode, universal),
Gemini config, and stream check defaults.
Pricing:
- Seed gemini-3.5-flash, gemini-3.1-flash-lite, step-3.5-flash-2603,
doubao-seed-2.0-code, mimo-v2.5(/pro), qwen3-coder-480b, grok-build-0.1.
- Correct deepseek-v4-flash/pro, glm-5/5.1, grok pricing.
- Add repair_current_model_pricing: idempotent pass that fixes only
rows still equal to the outdated built-in values, preserving any
user-customized prices (seed uses INSERT OR IGNORE and cannot update
existing rows).
Fixes from review:
- opencode: drop duplicate gemini-3.5-flash variant (unreachable via
.find), keep the entry with the full minimal/low/medium/high set.
- Align stale display names/costs to gemini-3.5-flash (hermes, openclaw,
opencode); openclaw cost -> {1.5, 9, 0.15} to match seed.
- i18n (zh/en/ja/zh-TW): refresh OMO category tooltips for new model
names; fix writing tooltip to Kimi K2.5 to match its recommended.
Update tests accordingly and add a regression test asserting unique
model ids in the Google opencode preset variants.
CI on main was red because two tests did not follow intentional changes
that were already merged into the codebase:
- codexChatProviderPresets.test.ts still expected the "Kimi For Coding"
preset, which was removed in 16c3ef3f. Drop the corresponding entry
from the expected presets map.
- import_export_sync.rs still asserted the legacy per-provider
model_provider id ("rightcode"), but 9fac15b8 unified Codex
third-party providers into the stable "custom" history bucket. Mirror
the assertion update already applied to provider_service.rs.
No production code changed; both fixes only update test expectations.
Enable openai_chat routing with explicit model catalogs across the major
Chinese/Asian providers (DeepSeek, Zhipu GLM, Kimi, MiniMax, Baidu Qianfan,
Bailian, StepFun, Volcengine Agent Plan, BytePlus, DouBaoSeed, ModelScope,
Longcat, BaiLing, Xiaomi MiMo, SiliconFlow, Novita AI, Nvidia, etc.). Each
preset declares its context window so the UI can size catalog rows when the
preset is picked.
Also lands two consistency fixes uncovered along the way:
- Include setCodexCatalogModels in resetCodexConfig's useCallback deps to
match the new third parameter it consumes.
- Realign TheRouter Codex test to the "custom" model_provider bucket
established by the recent third-party unification; the previous assertion
predated that refactor and had been failing on HEAD.
Jason