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).
* fix(hermes): resolve config dir via HERMES_HOME and platform defaults
On Windows, CC Switch hardcoded `~/.hermes` as the Hermes config directory,
but Hermes resolves it through `get_hermes_home()`: `HERMES_HOME` env var,
then a platform default (Windows `%LOCALAPPDATA%\hermes`, mac/Linux
`~/.hermes`). So CC Switch wrote configs where Hermes never reads them and
provider changes had no effect (refs #3178).
`get_hermes_dir()` now mirrors Hermes' own resolution order:
1. `settings.hermes_config_dir` — CC Switch explicit override
2. `HERMES_HOME` env var — trimmed, non-empty, taken as-is (no `~`
expansion, matching Hermes' `Path(val)`)
3. platform default — Windows reads the `LOCALAPPDATA` env var (the exact
value Hermes reads, not a re-derived Known-Folder path) and falls back
to `~\AppData\Local\hermes`; mac/Linux keep `~/.hermes`
Relation to #3470: that PR dropped `HERMES_HOME` for "consistency with
Codex/Claude". But unlike those tools Hermes treats `HERMES_HOME` as a
first-class mechanism (its own Windows installer sets it), so ignoring it
reintroduces the same mismatch for relocated installs. This keeps it.
Tests cover HERMES_HOME precedence, settings-override > HERMES_HOME, blank
HERMES_HOME fall-through, the platform-correct default, and a pure
`windows_local_hermes_dir` helper exercising the LOCALAPPDATA-set and
LOCALAPPDATA-empty fallback paths on every host.
* test(hermes): isolate config-dir tests from ambient HERMES_HOME/LOCALAPPDATA
`get_hermes_dir()` now consults `HERMES_HOME` (all platforms) and `LOCALAPPDATA`
(Windows). The `with_test_home` helper only neutralized `CC_SWITCH_TEST_HOME`,
so an ambient `HERMES_HOME` — which Hermes' own Windows installer sets — would
make tests that write `get_hermes_config_path()` escape the temp home and touch
a real Hermes config (and the same hazard exists via `LOCALAPPDATA` on Windows).
Clear and restore both env vars in `with_test_home`. This is safe: only this
module reads those env vars, and `dirs` uses the Known-Folder API rather than the
env var. Adds a test asserting both are neutralized inside `with_test_home`.
Addresses the Codex review comment on #4680.
* fix(hermes): trim LOCALAPPDATA to match Hermes' .strip()
`windows_local_hermes_dir` checked `OsStr::is_empty()` on the raw value, but
Hermes does `os.environ.get("LOCALAPPDATA", "").strip()`. A whitespace/padded
`LOCALAPPDATA` would make CC Switch write under the literal padded path while
Hermes trims and falls back, hiding the config from Hermes. Trim before the
empty check, matching the existing `HERMES_HOME` handling. Adds
`windows_local_hermes_dir_trims_localappdata`.
Addresses the Codex review comment on #4680.
---------
Co-authored-by: thisTom <19346741+thisTom@users.noreply.github.com>
- Add v3.16.4 release notes in zh/en/ja.
- Add a trilingual FAQ explaining why custom models don't show in the Codex desktop model picker (upstream Codex Desktop login-identity gating, not a cc-switch bug) and the keep-official-login mitigation; cross-linked both ways with the official-auth preservation guide.
- Align the CHANGELOG 3.16.4 release date to 2026-06-27.
Add a Changed entry for the removed Fable 5 Verified commemorative banner (16922917) and refresh the stats line to the content-scoped count (53 commits | 126 files | +8,149 / -1,016), excluding the changelog meta commits.
Summarize the commits since v3.16.3 across Added/Changed/Fixed/Docs: the SubRouter and OpenCode Go partner presets, native Codex Responses migration for CN providers, proxy hardening (zstd decompression, OAuth-over-proxy, DeepSeek effort strip), and usage/pricing tooling (Volcengine Ark AK/SK queries, models.dev import, live date ranges, GLM-5.2/Doubao pricing).
The Claude Desktop OpenCode Go preset was missed by the referral/promo update that landed for Claude Code / Codex / OpenCode, so its websiteUrl pointed at the bare opencode.ai domain with no apiKeyUrl or partnerPromotionKey. Align it with the other three: websiteUrl -> /go, apiKeyUrl -> the ref=2YTRG2NGTX referral link, and partnerPromotionKey "opencode_go" so the in-app promo banner shows. All four OpenCode Go presets now carry the referral link and promo copy.
Swap the SubRouter apiKeyUrl across all 7 client presets from the
neutral console/token page to the affiliate registration link
(?aff=l3ri), matching the project's referral-link convention.
Sync the preset test constant accordingly.
Decouple the in-app promotion banner from isPartner so a preset can show a
promo phrase plus referral link without earning the paid-partner star.
- ApiKeySection: gate the banner on partnerPromotionKey alone; the star is
still driven solely by isPartner. This also un-suppresses the existing
MiniMax cn/en promos, which already carried copy without isPartner.
- OpenCode Go (claude/codex/opencode): point apiKeyUrl at the referral
link and add partnerPromotionKey "opencode_go" (no isPartner set).
- i18n: add the opencode_go promo string across zh/en/ja/zh-TW.
Add OpenCode Go (opencode.ai/zen/go) provider presets across clients:
- Codex: openai_chat conversion with model catalog (GLM/Kimi/DeepSeek/MiMo), no static codexChatReasoning so per-model capability is inferred
- OpenCode: @ai-sdk/openai-compatible against /zen/go/v1
- Claude: add apiKeyUrl (opencode.ai/auth) and align websiteUrl to /go
Auth is a plain pasteable API key (no OAuth). Go splits wire format by model: OpenAI /chat/completions for GLM/Kimi/DeepSeek/MiMo, Anthropic /messages for MiniMax/Qwen; these presets target the chat-format models.
Refresh the Kimi sponsor blurb to the K2.7 Code release (coding-focused
agentic model, ~30% lower thinking-token usage vs K2.6) and bump the
banner alt text from K2.6 to K2.7 Code. EN/ZH copy provided by the
vendor; JA/DE translated to match.
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).
Switch the Kimi K2.6 sponsor banner from the Moonshot CDN URL to
in-repo assets. Chinese README uses kimi-banner-zh.png; English,
Japanese and German use kimi-banner-en.png.
Several Chinese providers now expose a native OpenAI Responses API
endpoint, so Codex can reach them directly without the Responses->Chat
route-takeover conversion. Switch these presets to apiFormat
"openai_responses" and drop the now-unused codexChatReasoning and
modelCatalog (removing modelCatalog also keeps the "local route mapping"
toggle unchecked by default):
- Qwen / DashScope Bailian (/compatible-mode/v1/responses)
- Xiaomi MiMo + Token Plan (api.xiaomimimo.com/v1)
- Volcengine Doubao (/api/v3/responses)
- Meituan LongCat (/openai/v1)
- MiniMax CN + intl (/v1/responses, confirmed in the official API reference)
SiliconFlow-hosted MiniMax stays openai_chat (third-party endpoint, not
MiniMax's own base_url).
Also refresh stale model ids on the remaining chat-only providers:
GLM 5.1->5.2, StepFun 3.5-flash-2603->3.7-flash, Ling 2.5-1T->2.6-1T.
- Add an optional `enabled` flag to useScanUnmanagedSkills; the Skills panel
scans once on mount (enabled:true), with 30s staleTime + keepPreviousData to
dedupe disk IO across navigations.
- App subscribes to the shared query (enabled:false) and renders a green dot +
tooltip on the top-bar Import button when unmanaged skills are available.
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.
The account-level AccessKey is buried in the Volcengine console menus,
so surface a clickable, visible link to the IAM key management page
(https://console.volcengine.com/iam/keymanage) right under the AK/SK
hint. Opens via settingsApi.openExternal; adds the volcengineKeyConsoleLink
label across all four locales.
Point DouBaoSeed at doubao-seed-2-1-pro across all six clients (claude, claude-desktop, codex, opencode, openclaw, hermes), replacing doubao-seed-2-0-code-preview-latest. Sync display names to "Doubao Seed 2.1 Pro" and correct the openclaw cost field (0.002/0.006 -> 0.84/4.2 USD/1M) to match the new model.
* fix(proxy): decompress Codex request body before forward, support zstd
Codex Desktop sends zstd-compressed request bodies when authenticated
against the Codex backend, which broke local proxy routing because the
handlers parsed the raw bytes with serde_json directly.
Reworked on top of current main so it preserves the response_processor
behavior that landed after this PR was first opened:
- Extract content-encoding helpers into a shared proxy::content_encoding
module. decompress_body keeps returning Option<Vec<u8>> so unknown
encodings stay pass-through with their content-encoding header intact,
and keeps the deflate zlib-then-raw fallback (RFC 9110).
- Add zstd/zst support (zstd 0.13) and disable reqwest's auto zstd
decompression via .no_zstd() for parity with gzip/br/deflate.
- Decompress the request body before JSON parsing in the three Codex
handlers (chat_completions / responses / responses_compact) and strip
the stale content-encoding / content-length / transfer-encoding headers
so the forwarder regenerates them.
- Support stacked codings (e.g. "gzip, zstd") by decoding in reverse
order and merge repeated Content-Encoding headers via get_all.
Fixes#3764Fixes#3696
Co-authored-by: chenx-dust <16610294+chenx-dust@users.noreply.github.com>
* fix(proxy): decompress upstream error bodies before reading them
The forwarder error branch consumes non-2xx responses via String::from_utf8
directly, bypassing read_decoded_body. reqwest has no auto-decompression
feature enabled, so a compressed error body (gzip/br/deflate/zstd) arrives
as raw bytes, fails from_utf8, and gets dropped, hiding upstream rate-limit
and auth details from the client.
Decode the error body with the shared proxy::content_encoding helper,
mirroring the success path. Falls back to the raw bytes when the encoding is
unsupported or decoding fails.
Co-authored-by: chenx-dust <16610294+chenx-dust@users.noreply.github.com>
---------
Co-authored-by: Jason <farion1231@gmail.com>
Co-authored-by: chenx-dust <16610294+chenx-dust@users.noreply.github.com>
* feat(db): in-app recovery screen with upgrade button when DB version is too new
When the SQLite user_version is newer than the app supports (SCHEMA_VERSION),
Database::init() fails and previously dead-ended in a native Retry/Exit dialog
(Retry just fails again). The app now boots a dedicated recovery screen instead.
- Detect the recoverable "version too new" case and surface it via init_status
(kind="db_version_too_new" + db_version/supported_version); force-show the main
window and skip normal AppState boot (recovery commands need only AppHandle).
- The recovery screen first checks for an available update:
- update available -> "Upgrade app" runs the updater (download + install +
restart) with a download progress bar.
- no update (already latest) -> warns that the DB is too new even for the latest
build (likely a third-party client), so upgrading cannot help.
- install_update_and_restart now emits `update-download-progress` events; new
`check_app_update_available` command.
- i18n: en / ja / zh / zh-TW.
Verified: pnpm typecheck + format:check + test:unit (351) green; cross-model
review of Rust correctness and recovery-mode safety (no AppState panic).
* fix(db): pre-check too-new DB before schema writes; exit on close in recovery mode
Addresses review feedback on the too-new-DB recovery flow.
- P1: stored_user_version_exceeds_supported() is now checked BEFORE
Database::init(), so create_tables()'s DDL (incl. the unconditional
DROP INDEX/DROP TABLE IF EXISTS failover_queue) never runs against a
database whose user_version we cannot understand. The earlier
post-init-failure recovery branch is removed; the pre-check is the
single authoritative guard, so "don't write to a DB we can't read"
now holds from the very first DB access.
- P2: the window CloseRequested handler now detects recovery mode
(init_error kind = db_version_too_new) and exits the app instead of
honoring minimize_to_tray_on_close. Recovery mode returns before the
tray is created, so hiding the window would leave the app running with
no tray to bring it back; native-close now quits cleanly.
Verified: cargo fmt --check clean; cross-model Rust review of both fixes
(compile-correctness + no normal-startup/close regression).
* add glm-5.2 pricing
* feat(usage): add live end time option for custom date range
Add a "End time follows current time" checkbox in the custom date range
picker. When enabled, the end time becomes read-only and automatically
tracks the current moment, so usage data always reflects up-to-the-second
consumption from the chosen start time.
This is especially useful under the Coding Plan 5-hour quota window —
users can set the start time to when their 5h window began and keep
the end time live to monitor real-time token consumption.
* style(usage): fix prettier formatting for UsageDashboard
* fix(usage): include liveEndTime in React Query cache keys
Without liveEndTime in the query key, a live custom range and a fixed
custom range with the same stored endpoints share the same cache entry.
After the live range refreshes (endDate = now), switching to the fixed
range shows stale data fetched through "now" instead of the original
end time.
* ci: add Windows ARM64 release artifacts
* ci: keep release matrix jobs independent
* ci: fix pnpm cache path on Windows runners
* ci: setup pnpm with corepack on Windows ARM64
* ci: fix Windows ARM64 release build
* ci: retry transient release bundler downloads
* ci: remove non-minimal release workflow changes
* ci: keep release matrix jobs independent
macOS signing fails in forks without Apple secrets and, with default
matrix fail-fast, cancels the sibling jobs (including Windows ARM64)
before they finish. Disable fail-fast so each platform runs to completion.
---------
Co-authored-by: MoonDreamStars <moondreamstar1@gmail.com>
Set the default Claude Code auto-compact window to 262144 for the
Kimi For Coding provider preset, matching the official Kimi docs:
https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html
Use templateValues so users can customize the value (e.g. for future
models or performance tuning) while keeping 262144 as the default.
Append a clickable CTA hook to the end of the Kimi K2.6 slogan in all
four README locales (en/zh/ja/de), pointing to the existing
aff=cc-switch Moonshot console link.
CI cargo fmt --check failed on transform_codex_chat.rs (the wrapping
introduced upstream did not match rustfmt 1.95.0). Apply cargo fmt so the
chat_legacy_function_call_to_response_item call uses the expected layout.
The official-first/prime-partner sort changed Original mode order, but the
selector tests still asserted the old raw array order. Update the three
stale assertions and add a dedicated case covering the prime-partner group
and the exclusivity rule (an official preset also flagged primePartner
stays only in the official group).
Query coding-plan / agent-plan usage for Volcengine Ark via the
control-plane OpenAPI (open.volcengineapi.com), which requires
account-level AccessKey signing rather than the inference API key.
- Implement Volcengine Signature V4 (an AWS SigV4 variant: fixed
canonical header order, "HMAC-SHA256" algorithm without the AWS4
prefix, scope ending in "request", service "ark") in
services/coding_plan.rs
- Auto-detect the plan by probing GetAFPUsage (Agent Plan, AFP
five-hour/weekly/monthly quotas) first, falling back to
GetCodingPlanUsage (Coding Plan, session/weekly/monthly percentages);
a single credential covers whichever plan the account holds
- Parse the real response shape: the window label lives in the `Level`
field; guard ResetTimestamp <= 0 (session returns -1)
- Store account-level credentials on UsageScript (accessKeyId /
secretAccessKey), threaded through both the test command and the
TOKEN_PLAN auto-refresh path
- Add an independent AK/SK input block with a detailed hint pointing to
the Volcengine console -> API Access Keys
- Add the `monthly` tier label (frontend TIER_I18N_KEYS + tray
TIER_LABEL_GROUPS + subscription service)
- Sync zh / en / ja / zh-TW locales and the usage-query docs
- Reduce title->tabs and tabs->card vertical gaps from 24px to 12px
- Add an always-visible footer hint guiding users to fill the fields
below after choosing a preset (pinned footer, never scrolls off)
- FullScreenPanel: add optional contentClassName prop to scope content
padding overrides without affecting the other panels that share it
- i18n: add provider.addFooterHint in zh/en/ja/zh-TW
The OpenCode and OpenClaw presets were labeled "Kimi K2.7 Code", unlike
the plain "Kimi" used by the other apps. Rename the preset (and the
OpenCode provider display name) to "Kimi" for consistency; the model
label stays "Kimi K2.7 Code" since it describes the actual model.
In the default (Original) sort mode, float official-category presets to
the very top, followed by prime partners (Kimi), then the rest in their
original array order. Implemented as a three-way partition+concat so each
group keeps its internal order and no preset is listed twice.
Replace the inline Kimi placeholder mark with the vendor's refreshed
logo. The K glyph uses `currentColor` so it follows the theme text color
(dark in light mode, white in dark mode), while the brand accent dot is
pinned to the new #1783FF. Align the metadata fallback color accordingly.
The vendor renamed its domain, API endpoints, and trademark from CTok to
ETok. Update all user-facing branding accordingly:
- Presets (claude, claude-desktop, codex, gemini, hermes, openclaw,
opencode): ctok.ai -> etok.ai, api.ctok.ai -> api.etok.ai, internal
provider id ctok -> etok, display name CTok.ai -> ETok.ai
- Icons: replace inline placeholder SVG with the new ETok brand PNG,
moved from `icons` to `iconUrls`; key ctok -> etok; banner logo
ctok.png -> etok.png
- README (en/zh/ja/de) partner banner: new logo, links, and copy
- i18n (en/ja/zh/zh-TW): partnerPromotion key ctok -> etok
Keep "ctok" in the Codex history-migration whitelist as a legacy id and
add "etok", so existing users' local session history stays correctly
bucketed after the rename.
* Chat API: skip tool calls with missing function names
Some providers send empty or absent function names in streaming
tool call deltas. Previously these produced invalid output items.
- Don't overwrite accumulated state.name with empty deltas
- Skip tool calls that never received a valid name (instead of
falling back to 'unknown_tool')
- Apply the same defensive guard in finalize_tools and the
non-streaming path
* Address review: defer empty-name skip to finalization
Require both call_id and name before triggering should_add,
instead of skipping eagerly when name is absent in the first
delta. This handles providers that send id before name,
as suggested in the Codex review.
* Guard legacy function_call against empty name
Return Option<Value> from chat_legacy_function_call_to_response_item,
returning None when function_call.name is missing or empty. This covers
the legacy message.function_call path that the original guard missed.
* Remove unreachable unknown_tool fallback
---------
Co-authored-by: Jason <farion1231@gmail.com>
Introduce an optional primePartner flag on all provider preset interfaces.
Regular partners keep the gold star badge; prime partners render a solid
gold heart (no badge frame). Mark the first-party Moonshot Kimi presets
(Kimi / Kimi For Coding / Kimi K2.7 Code) across claude, codex, claude
desktop, opencode, openclaw and hermes as prime partners.
Replace the low-res ccsub.jpg with a vector SVG. Letterbox it from
2046x648 (3.157:1) to 2046x850 (~2.406:1) so it matches the other
sponsor-table banners and renders at the same height (62px @ width=150).
Point all four README locales at the new asset.
Jason