The routing-required toast for Anthropic-format Codex providers only had
a Chinese defaultValue in code; non-Chinese locales showed a mixed-language
message. Add the reason string to zh/en/ja/zh-TW following the phrasing of
the sibling proxyReason* keys.
The forced 1-hour cache_control TTL (schema v14) was a mistake. Injected
breakpoints return to Anthropic's standard 5-minute TTL, caller-owned
markers are preserved verbatim instead of having their TTLs rewritten,
and the 5m/1h cache-write buckets are removed from usage parsing and
pricing (back to the single aggregate cache-creation rate). The cache
TTL selector is removed from the rectifier settings panel along with its
i18n keys in all four locales.
SCHEMA_VERSION returns to 13: the unreleased cache_creation_1h_tokens
column and the v13->v14 migration are removed. The feature never shipped
in a release and the introducing commit was never pushed, so no
databases were stamped v14 outside this machine (local DB verified at
user_version 13).
Mapped GPT models were rejected by Codex clients with "model does not
support image inputs". Two root causes:
- Catalog entries for native-Responses/Anthropic providers cloned a
template whose input_modalities defaulted to ["text"], so every mapped
model was advertised text-only. model_catalog_json replaces Codex's
built-in model table wholesale, and both the TUI and the IDE extension
block images pre-send when the current model is found without "image".
- Editing the current Codex provider during proxy takeover only refreshed
the DB backup, so removing the mapping left a stale model_catalog_json
pointer (and its text-only catalog file) active in live config.
Changes:
- New shared model_capabilities module: explicit row declaration first,
then a confirmed text-only registry (exact tail match only — prefix
matching removed, variants enumerated so future -vl/-vision models fail
open), everything else unknown.
- Catalog generation writes input_modalities from that inference for all
tool profiles: unknown models fail open to ["text","image"]; only
confirmed text-only models are advertised as ["text"], giving users a
clear client-side prompt instead of silent image stripping.
- Live catalog reverse-import collapses modalities that match current
inference, so registry corrections are not frozen into hidden row
overrides and the rectifier's heuristic opt-out keeps working.
- Saving the current Codex provider while takeover owns live now
re-projects the live config (mirrors the hot-switch path), so mapping
edits and removals take effect immediately.
- Media rectifier delegates to the shared module; its preflight toggle is
documented (4 locales) as proxy-request-only, never affecting catalog
capability declarations.
Replace the legacy sudocode.us provider (a name collision) with the new
paid sponsor SudoCode on sudocode.chat, updated in place across six
clients: Claude Code, Codex, Claude Desktop, OpenCode, OpenClaw, Hermes.
- Switch endpoints to api.sudocode.chat, add isPartner +
partnerPromotionKey, and add four-locale partnerPromotion copy
- Claude Code / Desktop use direct passthrough (no model mapping)
- Codex / OpenCode / OpenClaw / Hermes use gpt-5.6-sol
- Remove the Gemini entry (outside sponsor scope)
- Replace the provider icon with the new brand PNG
Drop the Max Context Tokens / Auto Compact Window template inputs from
the Codex and Kimi For Coding presets and hardcode the values in the
preset env (372000 / 262144). The rare user who wants different numbers
can edit them directly in the JSON editor.
Both keys stay on purpose: the compact window resolves as
min(model window, value), so matching the window is behavior-neutral
today, but the explicit env pins compaction locally against
remote-config experiments dialing it down.
Claude Code caps unknown model ids at 200K, so the preset's standalone
CLAUDE_CODE_AUTO_COMPACT_WINDOW=262144 was clamped by min(window, value)
and never took effect. Pair it with CLAUDE_CODE_MAX_CONTEXT_TOKENS and
route the endpoint's kimi-for-coding alias on every tier, since both
context envs are ignored for claude-* prefixed model ids.
Saved providers get the same context defaults injected into effective
live settings at switch time, with a mirror-inverse strip on backfill so
injected values never harden into provider config. Explicit user values
always win over the injected defaults.
- Update Codex OAuth presets to the gpt-5.6 family (haiku -> gpt-5.6-luna)
and bump the custom Codex template default model
- Inject CLAUDE_CODE_MAX_CONTEXT_TOKENS / CLAUDE_CODE_AUTO_COMPACT_WINDOW
(372000, the ChatGPT Codex catalog window with a ~353K effective budget,
openai/codex#31860) into effective live settings so Claude Code stops
assuming a 200K window and compacts before the upstream rejects the prompt
- Gate the injected defaults on every configured model being gpt-5.6*:
gpt-5.5's upstream catalog oscillates between 272K and 372K and must not
inherit them; explicit user values always win
- Strip the injected values on switch-away backfill (mirror-inverse of the
injection conditions) so program defaults never harden into per-provider
explicit values, and keep both keys out of the shared common-config snippet
Let users switch between the built-in OpenAI provider and third-party Codex providers directly from the provider panel while takeover mode remains active.
Centralize the frontend capability predicate so only the fixed codex-official seed receives native-login routing support, and keep copied UUID-based official entries clearly marked as unsupported.
Add an idempotent backend command that recreates the deleted official seed, wire it into the add-provider flow, refresh localized guidance, and add mutation and provider-action regression coverage.
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.
Add a show/hide toggle for the header project profile switcher under
the Homepage Display section in settings. Defaults to visible so
existing users keep the current behavior.
Expose the top-level `model` key of config.toml as an editable field in
the Codex provider form, so users can switch to newly released models
(e.g. gpt-5.6) without waiting for a preset update — preset updates only
affect newly added providers, existing ones keep their saved TOML.
The field syncs bidirectionally with the TOML editor (mirroring the
base-URL pattern), suggests models from the mapping catalog plus the
provider's /models endpoint, and offers a one-click "add to mapping"
action when the value is outside a non-empty catalog. Hidden for
official providers.
Details:
- Save-time catalog sync now only backfills the first mapping row into
the top-level model when the field was left empty, so the explicit
field wins over the implicit row-0 sync
- Escape model names (and base_url) with TOML basic-string escaping and
strip control characters from field input: /models ids are remote
data and unescaped interpolation could inject config.toml lines
(e.g. a forged [mcp_servers.*] command)
- The strict model-line matcher now recognizes escaped output, empty
strings and single-quoted literals, keeping extract/set round-trips
stable; deliberately no key-only loose matching (it would misfire on
assignment-looking text inside multiline strings)
- Invalidate the fetched model list whenever the request identity
changes (base URL, full-URL toggle, API key, custom UA) and discard
in-flight responses via a sequence guard, so the dropdown never shows
a previous provider's models
- i18n for zh/en/ja/zh-TW
* feat(codex): support native Anthropic Messages protocol as upstream
Allow gateways that only expose the native Anthropic Messages protocol
(/v1/messages) to be used by Codex: the local proxy performs bidirectional
request/response/streaming conversion between Responses and Anthropic.
Backend:
- Add two conversion modules: transform_codex_anthropic / streaming_codex_anthropic
- codex.rs: add routing detection and auth: ANTHROPIC_AUTH_TOKEN→Bearer (default),
ANTHROPIC_API_KEY→x-api-key, mutually exclusive
- handlers.rs: add handle_codex_anthropic_to_responses_transform
- forwarder.rs: support optional Claude Code client fingerprint impersonation
(User-Agent / anthropic-beta / x-app / system prompt first-line injection)
and /responses→/v1/messages rewriting
- codex_config: the anthropic format reuses the NativeResponses profile to strip
custom tools
- ProviderMeta: add impersonateClaudeCode
Frontend:
- CodexApiFormat: add "anthropic"; the form adds auth field selection and an
impersonation toggle
- Add en/ja/zh/zh-TW copy
Robustness:
- Downgrade when tool history / forced tool_choice conflicts with extended
thinking, avoiding upstream 400s
- Emit cache_creation_input_tokens in usage and use saturating_add to guard
against overflow
- Append a unique suffix to non-streaming/streaming output-item ids to avoid
multi-segment text/thinking overwriting each other
* fix(codex): harden Anthropic bridge against empty text blocks and truncated streams
- Drop empty/whitespace-only text content blocks when rebuilding Anthropic
messages from Responses history; Anthropic 400s on empty text blocks (e.g. an
empty assistant text emitted alongside a tool_use), which broke follow-up and
tool-result requests. Also drop messages left without content.
- Do not report a truncated Anthropic stream as completed: when the SSE
connection ends before message_stop with no stop_reason, emit an incomplete
response if partial output exists, or a failed (stream_truncated) response
otherwise, mirroring the chat converter's EOF handling.
* fix(codex): resolve Anthropic-bridge review findings
Blocking:
1. Defer stripping the [1m] long-context marker until after catalog matching and model write-back, re-stripping it on the final Codex→Anthropic body and setting a flag to emit the context-1m-2025-08-07 beta header, so the marker is no longer lost or overridden by the default model.
2. Gate Anthropic thinking on the trailing turn only (via trailing_turn_allows_thinking) instead of scanning full history, so a Codex session that resends history each round no longer permanently loses thinking after the first tool call.
3. Inject 5m ephemeral cache_control on the Codex→Anthropic body by reusing cache_injector (handling the system string→array conversion), so system/tools/history are cached instead of re-sent at full price every round.
4. Add a shared base_url_is_full_endpoint helper (normalizing whitespace/query/fragment/trailing slash) used by both the Anthropic and Chat paths, so a base URL already ending in /v1/messages is treated as a full endpoint instead of double-appending to /v1/messages/v1/messages.
5. Align the catalog tool-profile predicate with the routing predicate so resolve_codex_catalog_tool_profile returns the Anthropic profile whenever the request converts to Anthropic, preventing freeform tools like apply_patch from being silently filtered by a ProxyChat catalog.
6. Explicitly disable native web_search for the Anthropic profile (including the no-catalog branch) via set_codex_native_web_search_field, so Codex no longer treats it as available while the transform silently drops it.
7. Only forward tool_choice when tools survive filtering, dropping it otherwise, to avoid a non-retryable 400 from upstream when tool_choice is sent with no tools.
8. Lower the fallback default to max_tokens=8192 (only when max_output_tokens is omitted) and clamp the thinking budget to max_tokens/2, disabling thinking below the 1024 floor, to avoid hard 400s on low-output-ceiling models/gateways.
Minor:
9. Centralize the Codex/OpenAI fingerprint-header denylist in is_codex_client_fingerprint_header so impersonating Claude Code uniformly drops originator/session_id/conversation_id/chatgpt-account-id/x-client-request-id/openai-* and the x-stainless-*/x-codex-* prefixes.
10. Retain content_block_start.input as start_input and fall back to it at block close when no input_json_delta arrived, so a gateway that carries the full tool input on the start event no longer yields empty tool arguments.
11. Extract a shared codex_responses_sse module as the single Responses SSE envelope builder that both the chat and anthropic streaming emitters delegate to, with byte-for-byte-unchanged wire output, so future event-format fixes touch one place instead of two.
* fix(codex): add per-provider max_output_tokens override for Codex→Anthropic path
Codex does not forward model_max_output_tokens in the request body,
causing the proxy to fall back to a conservative 8192 default. This
truncates long or thinking-heavy responses (stop_reason=max_tokens).
- Add maxOutputTokens field to ProviderMeta (Rust + TypeScript)
- Inject the value into the Anthropic request body before transform,
taking precedence over request-supplied and default values
- Add numeric input in Codex form fields (Anthropic format only)
- Add i18n entries for label, placeholder, and hint (en/zh/zh-TW/ja)
- Include roundtrip and omission unit tests for the new field
* fix(codex): harden Anthropic protocol bridge
* fix(codex): address Anthropic bridge review
* fix(codex): preserve flattened Anthropic inputs
* fix(codex): harden Anthropic recovery paths
* fix(ci): satisfy Rust clippy
---------
Co-authored-by: Jason <farion1231@gmail.com>
The fallback model (ANTHROPIC_MODEL) field was missing the 1M checkbox
that the role-specific model rows already have. Added the checkbox with
the same strip/set marker logic used by role rows.
Fixes#3679
updateTomlCommonConfigSnippet re-serialized the whole document through
smol-toml (parse -> deepMerge -> stringify): comments dropped, keys
reordered, and empty parent table headers synthesized -- the
long-standing "config.toml keeps getting reordered" symptom (audit C5,
introduced in 083e48bf).
Replace it with a backend command backed by the same
merge_toml_table_like / remove_toml_table_like used when writing live
configs, so the form preview and the live write share one merge
semantic and user formatting survives edit-time merges. The frontend
sync helper is deleted outright to keep the pattern from coming back.
Making the form operations async exposes them to interleaving, so a
result is discarded unless it is still current when it lands:
- a per-hook sequence number (last operation wins) covers rapid
toggle/save races where an earlier merge resolves after a later
removal and would flip the switch back;
- a config-baseline check covers the user hand-editing the TOML while
a merge is in flight -- the stale result must not clobber their edit.
The checkbox state self-heals via the existing inference effect.
Regression tests pin both by resolving a suspended merge after a newer
operation / an external edit, plus backend tests locking comment and
key-order preservation, scalar override, and value-matched removal.
import_mcp_from_apps swallowed every importer error with unwrap_or(0),
so a corrupt config.toml surfaced as "imported 0 servers" with no hint
that anything went wrong.
Move the aggregation into McpService::import_from_all_apps: each app
imports best-effort (one bad file doesn't block the rest), and failures
are collected into a single error naming the failing apps alongside the
count that did import. The frontend now refreshes the server list on
settle rather than success, since a partial failure still means new
servers were persisted.
The websiteUrl for 火山Agentplan, DouBaoSeed and BytePlus is intentionally the ccswitch-attributed apiKeyUrl link, per the Volcengine partner's request. Restore the invite/attribution links across all six app preset files.
This reverts the websiteUrl changes from 56248087; apiKeyUrl was already left intact there.
Remove the 'OpenAI Compatible' custom-template preset from the OpenCode
and OpenClaw preset lists. It was a duplicate entry point: the built-in
'custom' provider flow already exposes an interface-format selector whose
default (@ai-sdk/openai-compatible / openai-completions) produces a
byte-identical starting config. Having both left two list items pointing
to the same place.
Existing providers are unaffected — presets only seed form defaults on
creation; saved providers store concrete npm/baseUrl/apiKey/models values.
The '@ai-sdk/openai-compatible' dropdown label is intentionally kept; it
is the format option users pick in the custom flow, not the deleted preset.
Usage/quota queries frequently showed spurious "query failed" states that
manual refresh could not clear (#3820). Root cause: all transport-level
failures were folded into Ok(success:false), so react-query's retry never
fired and the failure body poisoned the cache as regular data.
Backend:
- balance/coding_plan/subscription services now return Err for send
failures and body-read failures (read body via bytes() before
serde_json::from_slice; reqwest's json() wraps read errors as Decode,
making error-kind checks on it dead code). Auth/4xx/parse errors stay
Ok(success:false) and surface immediately.
- Script path maps transient AppError keys (request_failed /
read_response_failed) to Err; Volcengine adds a Transient call variant.
- Command layer skips snapshot persistence, usage-cache-updated emit and
tray refresh on Err so the cache bridge cannot overwrite retained data.
- Expired-credential retry propagates transient errors instead of
rewriting them as "OAuth token has expired".
Frontend:
- resolveDisplayUsage generalized to subscription quotas; 5th param is now
an options object with a `rejected` flag: stale success data retained by
react-query across rejections is re-anchored to dataUpdatedAt and expires
through the same 10-minute keep-last-good window instead of being shown
indefinitely (a total outage used to mask longer than a single 5xx).
- useSubscriptionQuota / useCodexOauthQuota gain keep-last-good with
per-scope snapshot reset; rejected queries with no displayable value
synthesize a failure placeholder carrying the real error message so
footers keep rendering a retry entry point.
- HTTP 429 is classified transient (retry-later) alongside 5xx.
- UsageScriptModal surfaces string rejections via extractErrorMessage.
Tests: 6 backend behavior tests drive real HTTP against a local listener
to pin the Err/Ok channel semantics; frontend suite extends
keepLastGoodUsage coverage (405 passing).
Replace the ?source=ccswitch referral with the new agent register invite
link (https://code0.ai/agent/register/B2XHxGjGmRvqgznY) on code0's
apiKeyUrl across all seven presets and the sponsor rows in all four
READMEs. API endpoints stay bare per the referral red-line.
Since switching projects automatically saves the current configuration
back to the project being left, the per-project "update from current"
button is redundant and even harmful: it allowed overwriting another
project's snapshot with the current state, breaking the invariant that
a project holds the state you last left it in.
- Remove the resnapshot button and confirm dialog from the manage
dialog; drop the now-unused scope prop and PROFILE_SCOPE_LABELS
- Add a footer Close button to the manage dialog (overlay click is
disabled app-wide, so it previously could only be closed via Esc)
- Update manageDescription in all four locales to describe the
autosave behavior; remove the two dead i18n keys
- Fix a shadowed `warnings` vec in ProfileService::apply that silently
dropped autosave-failure warnings before they reached the frontend
- Mention auto-capture on next switch in the "no snapshot for this
scope yet" warning and doc comments
The backend update command keeps its resnapshot parameter; it is now
only exercised by the pre-switch autosave path.
Projects are now global shared entities; Claude and Codex groups switch
independently via scoped current pointers and scoped payload slots.
- Remove scope column from profiles; keep current_profile_id_<scope>
- Use Option<Vec<String>> for mcp/skills to distinguish 'never captured'
from 'captured empty', preventing cross-side accidental disable
- Update/apply operations scoped to the active group via merge_scope_from
- Tray menu nests same shared list under Claude Code/Codex groups
- Add i18n for per-scope tooltips and 'not saved for this side' hint
Refs: profile P1 shared-entity redesign
Claude Desktop's only dimension managed by cc-switch is its provider
(MCP/Skills are hardcoded unsupported and prompts have no live file),
so snapshots capture just the current desktop provider while the empty
MCP/Skills sets and None prompt make apply a natural no-op for the
other dimensions - no per-dimension special casing needed.
- Add claude-desktop slot to PROFILE_APPS and PerApp (serde key uses
the hyphenated app id); old payloads without the key deserialize to
None and leave Claude Desktop untouched on apply
- Gate the tray Projects submenu by iterating PROFILE_APPS instead of
hardcoding Claude/Codex visibility
- Show the profile switcher on the Claude Desktop tab, mirror the
PerApp type, invalidate the claude-desktop providers cache on apply,
and extend the switcher tooltip in all four locales
- Extend the roundtrip integration test with the desktop provider
dimension; the desktop switch is cfg-gated to macOS/Windows because
desktop live writes error on Linux where CI runs cargo test
- Render the profile switcher only when the active tab is Claude or
Codex (frontend mirror of backend PROFILE_APPS), so viewing an
unsupported app no longer suggests its config was switched
- Move the switcher from beside the logo to the right of the route
toggles, where the flexible spacer absorbs its appearance and other
header controls no longer shift when switching tabs
Add a profile feature that captures the current provider, MCP,
skills and prompt state for Claude Code and Codex as a named
snapshot, and re-applies it in one click from the header switcher
or the tray Projects submenu.
- New profiles table (schema v12) with current marker in settings
- ProfileService orchestrates the four existing switch primitives
(provider first, then MCP diff, skills diff, prompt enable)
- Best-effort apply: dangling references become warnings, no rollback
- Header combobox switcher + snapshot-style manage dialog
- Tray Projects submenu shared with the UI apply/event pipeline
- i18n for zh/en/ja/zh-TW under the new profiles domain
- Integration tests covering roundtrip, dangling refs and clear
* feat: add Claude subagent takeover config
* feat: add Claude subagent model field
* i18n: add Claude subagent model labels
* fix(proxy): preserve configured subagent model mapping
* fix(providers): exclude subagent model from Claude common config
* style: format rust code
* fix(subscription): display Codex free-plan 30-day quota window (#3651)
Codex free accounts are metered on a rolling 30-day secondary window
(limit_window_seconds = 2,592,000) instead of the weekly window used by
paid plans. The backend already maps this correctly to the tier name
"30_day", but the frontend TIER_I18N_KEYS whitelist had no entry for it,
so SubscriptionQuotaView filtered the tier out. When that was the only
surviving tier (as happens for free accounts), the whole quota footer
rendered nothing — free accounts showed no remaining quota or reset time
while paid accounts worked.
- Add "30_day" -> subscription.thirtyDay to TIER_I18N_KEYS
- Add the thirtyDay label to all four locales (zh/en/ja/zh-TW)
- Add a unit test locking in window_seconds_to_tier_name mappings,
including the 30-day case
Fixes#3651
* fix(tray): render Codex free-plan 30-day window in tray menu
The tray keeps its own tier-name whitelist (TIER_LABEL_GROUPS) independent
of the frontend TIER_I18N_KEYS. Its month group only listed "monthly", so a
free Codex account whose only tier is "30_day" produced empty labeled parts
→ format_subscription_summary returned None → the tray showed no quota, even
though the footer now does. That breaks the invariant the existing
gemini_summary_lite_only_still_renders test guards: any tier visible in the
footer must not leave the tray blank.
- Add TIER_THIRTY_DAY ("30_day") constant so the string is single-sourced
across backend mapping, tray grouping, and the frontend whitelist
- Map 2_592_000s explicitly to it in window_seconds_to_tier_name
- Add TIER_THIRTY_DAY to the tray month ("m") group
- Add codex_summary_thirty_day_only_still_renders regression test
Follow-up to the review on #3651 / PR for the 30-day footer fix.
* feat(universal-provider): Auto-sync after adding and drop unused addSuccess i18n key
Signed-off-by: Hu Butui <hot123tea123@gmail.com>
* fix(i18n): sync zh-TW universal provider strings
---------
Signed-off-by: Hu Butui <hot123tea123@gmail.com>
Co-authored-by: Jason <farion1231@gmail.com>
* 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>
Partner aggregator (New API gateway) across Claude Code, Claude Desktop,
Codex, OpenCode, OpenClaw, and Hermes -- no Gemini, since its /v1beta
surface falls through to the web app. Claude Code and Claude Desktop use
the bare host https://nekocode.ai; Codex, OpenCode, OpenClaw, and Hermes
use /v1 with gpt-5.5.
Marks isPartner with the ?aff=CCSWITCH referral on apiKeyUrl only (the
website URL and every API endpoint stay bare, so the attribution param
never rides on a real request). Adds the partnerPromotion blurb in all
four locales and a sponsor row appended to the end of all four READMEs,
surfacing the CC Switch offer: 10% off top-ups with promo code cc-switch.
Registers the logo-derived nekocode-icon.png via URL import; the README
banner is normalized to the standard 1920x798 aspect ratio.
Partner aggregator (New API gateway) across Claude Code, Claude Desktop,
Codex, Gemini, OpenCode, OpenClaw, and Hermes. Claude Code, Claude
Desktop, and Gemini use the bare host (gemini-3.1-pro-preview for
Gemini); Codex, OpenCode, OpenClaw, and Hermes use /v1 with gpt-5.5.
Marks isPartner with ?source=ccswitch attribution on apiKeyUrl only
(website URL stays clean). Adds the partnerPromotion blurb in all four
locales and a sponsor row in all four READMEs. Positioned after
ClaudeAPI in the Claude Code and Claude Desktop lists (the two apps
that carry a ClaudeAPI preset). Registers the favicon-derived code0.png
icon via URL import; the README banner is normalized to the standard
1920x798 aspect ratio.
Bump every claude-sonnet-4-6/claude-sonnet-4.6 default pin to claude-sonnet-5 across all provider presets (claude, claudeDesktop, hermes, openclaw, opencode, universal NEWAPI_DEFAULT_MODELS) and the Claude Desktop DEFAULT_PROXY_ROUTES sonnet route id. Update route-derivation test expectations accordingly. Non-Anthropic pins (gpt/gemini/glm/sonnet-4-5) left untouched.
Non-partner aggregator across Claude Code, Claude Desktop, Codex,
OpenCode, OpenClaw, and Hermes. Claude Code uses bare host
api.amux.ai; Codex uses /v1 native Responses; the other three apps
default to gpt-5.5. No Gemini preset. Registers the amux inline icon
(currentColor) in the icon index and metadata.
The custom date-range picker switched to its two-column layout (date
fields | calendar) based on the viewport width via Tailwind `sm:`
(640px). But the popover is clamped to `100vw - 2rem` and anchored to
its trigger with `align="end"`, so its actual available width is not the
viewport width. On narrow windows the wide two-column layout could
activate while the popover only had room for one column, pushing the
calendar column off the right edge of the window where it was clipped
and unusable (month header and 4 of 7 weekday columns cut off).
Gate the two-column layout on the popover's own inline size via a CSS
container query instead of the viewport, and let the popover width
shrink to fit the viewport. When the popover is genuinely wide it shows
two columns; when it is clamped narrow it stacks vertically so the
calendar stays fully visible. The base stacked layout is the safe
fallback for engines without container-query support.
Closes#4669
* fix(i18n): rename "Write Common Config" checkbox to "Apply Common Config"
The original label "Write Common Config" (写入通用配置) was ambiguous
about data flow direction — it read as "write current config INTO the
common config" when the actual behavior is the reverse: merge the
saved common config snippet INTO this provider's config.
Rename to "Apply Common Config" across zh/zh-TW/en/ja, including all
hint/guide/notice references and component defaultValue fallbacks, to
make the action unambiguous. Also aligns the Gemini hint wording with
the claude/codex "when checked" phrasing.
* docs(ja): sync Japanese docs with renamed 'Apply Common Config' label
Codex review on #4829 pointed out the Japanese user manual and README
still referenced the old checkbox label after the rename.
- docs/user-manual/ja/2-providers/2.1-add.md: 共通設定を書き込み → 共通設定を適用
- README_JA.md: 共有設定を書き込む → 共有設定を適用
Add TeamoRouter (enterprise Agentic LLM gateway) as a sponsor partner
across Claude Code, Claude Desktop, Codex, OpenCode, OpenClaw and Hermes.
- Claude Code uses bare host https://api.teamorouter.com; Codex uses
https://api.teamorouter.com/v1 (native Responses); OpenCode/OpenClaw/
Hermes use gpt-5.5 over the OpenAI-compatible /v1 endpoint. No Gemini.
- apiKeyUrl uses the English referral link with UTM params (in-app stays
English; README links are per-language).
- Add localized in-app promo blurb (zh/en/ja/zh-TW).
- Add README sponsor rows below PatewayAI in all four READMEs.
- Register the teamorouter provider icon and pad the README banner to the
standard 2.40 aspect ratio.
dds.svg (1.4MB genuine vector, 2222 paths) was not imported in index.ts
nor referenced anywhere in src/, so it never shipped in the app or
appeared in the icon system — it only bloated the repo. Remove it.
All three shipped well above their ~32px render size (hermes/claudecn at
512x512, atlascloud at 3525x3300). Downscale to a 256px max dimension:
hermes 125KB->38KB, claudecn 109KB->46KB, atlascloud 105KB->9KB. Same
filenames, no code change.
Both were "fake vector" SVGs wrapping a single oversized base64 PNG
(ccsub embedded 1446x1328 / 1.16MB, shengsuanyun 720x720 / 212KB),
rendered at ~32px. Downscale the embedded bitmap to a 256px max dimension
and re-embed, keeping the SVG wrapper, filename, and import unchanged
(no code change). Result: ccsub 1.16MB -> 60KB, shengsuanyun 212KB -> 51KB.
Both shipped far larger than their on-screen render size: relaxcode was
1462x1076 / 1.16MB and sudocode 2048x2048 / 432KB. Downscale to a 256px
max dimension (aspect ratio preserved; ProviderIcon renders via <img>
object-contain), cutting them to ~41KB and ~36KB. Same filenames.
The ZetaAPI icon shipped as a 1254x1254 / 940KB PNG, roughly 30x larger
than its on-screen render size (~32px in ProviderIcon). Downscale to
256x256, cutting it to ~40KB (-96%) so it no longer bloats the bundle.
Same filename, so no import/code change.
Jason