* 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>
Fixes#5025. The rectifier's media fallback missed Volcano Coding Plan's
GLM 5.2 on both paths:
- Preventive: known_text_only_model had glm-5.1 but not glm-5.2, so image
blocks were forwarded verbatim. Added glm-5.2 as an exact tail match
(not a prefix, to avoid stripping images from a future glm-5.2v
multimodal variant following Zhipu's 4v/5v naming).
- Reactive: the upstream error "Model only support text input" never
mentions image/media, so the mentions_image gate rejected it before
hints ran; and the existing "only supports text" hint misses the
gateway's missing third-person "s". Added a self-evident phrase list
("only support text" / "only supports text") that asserts a modality
rejection on its own and bypasses the image-mention gate.
Includes regression tests using the verbatim #5025 error body and the
glm-5.2[1M] mapped-model form, plus a glm-5.2v negative assertion.
* 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
* 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>
* 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>
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.
* 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>
* fix(codex): restore cached tool call fields
* refactor(codex): merge duplicate enrich loops in chat history
enrich_call_item_from_cache copied the fill-if-empty loop for
reasoning_content/reasoning. The two loops are identical and key
order is irrelevant, so fold both key sets into a single loop.
Pure refactor, no behavior change; codex_chat_history tests pass.
---------
Co-authored-by: Jason <farion1231@gmail.com>
DeepSeek's Anthropic-compatible endpoint rejects requests where
thinking.type=disabled coexists with effort parameters, returning
HTTP 400. This breaks Claude Code 2.1.166+ sub-agents (Workflow/Dynamic
Workflow), which hardcode thinking:disabled.
Rather than overriding thinking:disabled, remove the conflicting effort
parameters (output_config.effort / reasoning_effort) to respect Claude
Code's intent — sub-agents don't need to display reasoning.
Fixes: https://github.com/deepseek-ai/DeepSeek-V3/issues/1397
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The provider panel health check sent a real streaming model request, which many third-party providers block (401/403/WAF), causing false negatives while only stable official endpoints passed. Replace it with a lightweight reachability probe: GET the provider base_url and treat any HTTP response (200/4xx/5xx) as reachable; only DNS/connect/TLS/timeout count as failure. Latency is the probe's TTFB.
Backend (services/stream_check.rs): rewrite ~2200 -> ~350 lines, dropping real-request building, format conversion, auth and API-path resolution while keeping per-app base_url extraction. Defaults: 8s timeout, 1 retry, 1500ms degraded threshold.
Failover invariant: the reachability check must never reset the circuit breaker (reachable != usable; a 403 host is reachable but broken for real traffic). Remove the resetCircuitBreaker call from useStreamCheck; failover failure detection stays driven solely by real proxy traffic (forwarder/circuit_breaker untouched). useResetCircuitBreaker is kept dormant for a future manual-recovery entry.
Open the check to all providers: drop the official/copilot/codex-oauth/third-party gating and the 'sends a real request' confirm dialog. For official providers whose base_url is intentionally empty, fall back to the endpoint the client actually uses (Claude -> api.anthropic.com, Codex -> chatgpt.com/backend-api/codex, Gemini -> generativelanguage). Non-official providers with a missing base_url still error to avoid a false green light. Claude Desktop Official is native 1P mode (talks to claude.ai, cc-switch not in the request path, no reliable endpoint) so its button stays hidden.
Slim StreamCheckConfig and per-provider testConfig to timeout/threshold/retries (drop test model + prompt); sync zh/en/ja/zh-TW. Retain the now-unused anthropic_to_openai/anthropic_to_gemini transform utilities and their test suites.
- Wire claude-fable-5 as a fourth tier on both proxy paths, with a
fable -> opus -> default fallback mirroring the official downgrade.
- Whitelist the fable- prefix for the Desktop 1.12603.1+ validator.
- Clarify fallbackModelHint (zh/en/ja/zh-TW): a blank tier on
third-party endpoints forwards the literal model name and 404s.
Refs #3980, #4026, #4049.
The Claude/Codex format-transform non-stream branch returned an opaque 422
"Failed to parse upstream response" whenever a 2xx upstream body was not
valid JSON. The common case: MaaS gateways force-stream a stream:false
request and return an SSE body with a non-SSE Content-Type, defeating the
header-only is_sse() check.
On serde failure, sniff for SSE and aggregate the chunks into a single
JSON, then run the existing converter so clients still receive a valid
non-stream response.
- chat_sse_to_response_value: aggregate chat.completion.chunk SSE
(content / reasoning / refusal / tool_calls / legacy function_call),
tool_calls index-keyed via BTreeMap to avoid unbounded densification,
first-wins finish_reason, message-snapshot override, completeness and
error-event guards; synthesize an id when the upstream omits one
- responses_sse_to_response_value: process the residual trailing block,
tolerating truncation and skipping it once a completed event was seen
- enrich remaining parse failures with content-type / content-encoding /
body-snippet diagnostics
- deflate: try zlib (RFC 9110) before raw; keep the content-encoding
header for unsupported encodings
- gate zero-usage rows on the Claude transform path
Extract a shared `parse_custom_user_agent` helper in provider.rs returning
`Result<Option<HeaderValue>>`, and reuse it in the forwarder, stream check,
and model fetch paths so detection, forwarding, and model listing all apply
the same provider-level User-Agent. Previously only the forwarder honored it,
so stream check could fail (or model listing 403) on UA-gated upstreams that
the proxy itself handled fine.
- stream_check injects the provider's custom UA on the claude/codex paths and
still skips the GitHub Copilot fingerprint UA.
- model_fetch service + command and the model-fetch.ts wrapper thread an
optional UA through to GET /v1/models.
- runtime callers silently ignore invalid values via `.ok().flatten()`
(no save-time block, so deeplink imports stay lenient).
The model mapped for takeover (env mapping, Claude Desktop routes,
Copilot normalization, Codex chat override) was discarded inside the
forwarder, so usage attribution depended entirely on the upstream
echoing it back. When the upstream omitted the model or mirrored the
client alias, kimi/glm tokens were recorded and priced as claude-*
(roughly 5-25x overstatement).
- capture the final outbound model in forward(), return it via
ForwardResult, and store it on the request context
- attribution fallback order is now: upstream echo (empty string
treated as missing) -> outbound model -> client-requested model
- 'request' pricing mode anchors to the outbound model instead of the
pre-mapping client alias; unchanged when no mapping applies
- persist the resolved pricing_model on every usage row
- Claude Desktop rows now log app_type "claude-desktop" on streaming
and transform paths too (was hardcoded "claude", silently dropping
desktop provider pricing overrides and splitting the cost basis by
the stream flag); its global pricing defaults inherit the claude
config since proxy_config only allows claude/codex/gemini rows
Codex /responses requests routed to text-only OpenAI-chat upstreams
(e.g. DeepSeek deepseek-v4-flash) failed with HTTP 400 "unknown variant
image_url" when images were sent: the responses->chat conversion turns
input_image items into image_url blocks the model rejects. The media
rectifier previously covered only the Claude adapter, so neither the
proactive strip nor the reactive retry fired for Codex.
- media_retry_should_trigger: accept "Codex" adapter, not just "Claude"
- contains_image_blocks / replace_images: also scan responses `input`
(input_image) in addition to chat `messages`
- is_image_block_type: match image | image_url | input_image
- is_unsupported_image_error: add "unknown variant" hint for the
deserialize error
- forward(): proactively run apply_media_prevention for Codex after the
responses->chat conversion
Proactively strips images for known text-only models (heuristic on by
default) and reactively retries with images replaced on upstream
image-unsupported errors. Adds tests for chat image_url, codex
input_image, the reactive trigger, and the deserialize error match.
Builds on #2774 (which fixed cache_read for the streaming openai_chat path).
Two gaps remained, both double-counting cache tokens when a Claude client
meters as app_type="claude" (input_includes_cache_read=false):
1. cache_read was still added to input on the non-streaming openai_chat path
(transform.rs openai_to_anthropic) and the whole openai_responses family
(transform_responses.rs build_anthropic_usage_from_responses, covering the
non-streaming call site and both streaming_responses call sites).
2. cache_creation was never subtracted on any converted path, including the
streaming openai_chat path #2774 had already touched. Claude billing treats
cache_creation as a separate bucket, so an inclusive upstream carrying a
direct cache_creation_input_tokens field billed it twice.
All four metering points now compute:
input = prompt_tokens - cache_read - cache_creation
restoring the invariant input + cache_read + cache_creation == prompt_tokens.
Pure OpenAI upstreams are unaffected (no cache_creation concept/field).
Tests: update direct-cache assertions (40->20), add a streaming conservation
regression test, and pin prompt<cache underflow (saturating clamp to 0) for all
three metering functions. cargo test 1573 pass, clippy clean.
Note: fix is forward-only; historical rows are not recomputed (cost is frozen at
log time and app_type="claude" mixes native + converted rows).
Audited all proxy format-conversion paths (Chat<->Message, Chat<->Response,
Gemini<->Message) for usage/cache metering. Five issues found and fixed.
The dedup mechanism (request_id PK, proxy/session source isolation) is
untouched, so no double-counting is introduced.
- A (Claude + openai_chat, streaming): inject stream_options.include_usage
so OpenAI-compatible upstreams emit usage in the SSE tail. Without it the
converted Anthropic message_delta was all-zero and the whole request's
input/output/cache was dropped. Same root cause as the already-fixed
Codex Chat path; the injection is extracted into a shared helper
(transform::inject_openai_stream_include_usage) reused by both paths.
- C (Claude + gemini_native): subtract cachedContentTokenCount from
input_tokens in build_anthropic_usage so input becomes fresh input
(Anthropic semantics). Previously the cache-hit tokens were billed twice
because this path meters as app_type="claude" (input_includes_cache_read
= false) while Gemini's promptTokenCount includes the cache.
- D (Codex + openai_chat, streaming): gate log_usage on
has_billable_tokens() to skip the synthetic all-zero usage the converter
emits when a non-compliant upstream omits usage, preventing empty-row
request-count inflation.
- P2 (from_claude_stream_events): use has_billable_tokens() for the return
gate instead of input>0||output>0, so a fully-cached streamed request
(cache_read>0, input==output==0) is still recorded. Affects all
Claude-streaming paths, not just Gemini.
- P3 (Codex Chat->Responses, non-streaming): apply the same
has_billable_tokens() filter the streaming branch got, since the
synthesized all-zero usage makes from_codex_response return Some and
bypass the `if let Some` guard.
Add TokenUsage::has_billable_tokens() as the unified predicate. New tests
cover include_usage injection, gemini input subtraction, the gate itself,
cache-only stream recording, and synthetic all-zero codex usage.
Full lib suite: 1569 passed.
* fix(proxy): strip cache_control from OpenAI format conversion (#3805)
- Remove cache_control passthrough from system messages, text blocks,
and tools to prevent 400 errors on strict OpenAI-compatible endpoints
- Always simplify single text block content to plain string format
- Fixes two format conversion bugs reported in issue #3805
* fix(proxy): apply cargo fmt to fix CI formatting check
Convert Responses input_file (requiring file_id or file_data, never file_url which Chat file parts do not support) and input_audio parts into their Chat Completions equivalents, and handle top-level input_* items that previously fell through and were dropped, clearing stale pending reasoning for non-assistant messages.
Replace the unconditional finalize at chat-to-responses stream end with a three-way guard: complete normally when finish_reason or [DONE] arrived, emit an incomplete response when substantive output exists without a finish_reason, and emit a failed (stream_truncated) event for empty truncation instead of masking it as completed. Also propagate late-arriving reasoning_content onto still-active tool-call items.
Generalize the cross-turn reasoning cache in codex chat history from function_call only to the full tool-call triad (function_call, custom_tool_call, tool_search_call) and their *_output counterparts, so apply_patch and tool-search calls keep their reasoning_content when restored via previous_response_id.
When listen_port is 0 the OS assigns the port at bind time, so the
configured value can no longer be trusted for building takeover URLs.
- server: read listener.local_addr() after bind and propagate the
actual port to the global proxy port, status, and ProxyServerInfo
- services: start the proxy before takeover when port is 0 so live
configs get the real port instead of :0, and persist the resolved
port back to the DB for DB-only URL paths; stop the pre-started
server on any takeover failure
- claude_desktop: reject an unresolved :0 port instead of emitting a
broken gateway URL
- build_proxy_urls: prefer the running server's port and error out if
the port is still 0
Add tests for takeover with an ephemeral port and the claude_desktop
:0 rejection; switch existing codex takeover tests to an ephemeral
port for isolation.
* feat(proxy): add GET /v1/models endpoint for Codex CLI reachability check
Codex CLI probes GET /v1/models at startup. Without this endpoint the proxy
returns 404, causing Codex to fail before any request reaches the upstream
LLM.
Return an OpenAI-compatible model list derived from the cc-switch–managed
model catalog file.
Fixes#3812
* fix(proxy): return Codex catalog schema from /v1/models
Codex deserializes the response as a catalog with a top-level `models`
field, not the OpenAI `{"object":"list","data":[...]}` envelope.
Return the catalog file content directly so the format matches what
Codex expects.
Co-authored-by: Codex review bot
* fix(proxy): guard /v1/models against serving stale catalog
Only return the model catalog when config.toml still references it via
`model_catalog_json`. After switching to a provider without a custom
catalog, the old file lingers on disk — serving it unconditionally
would advertise the previous provider's models to Codex.
Co-authored-by: Codex review bot
* fix(proxy): match relative model_catalog_json in stale-guard
cc-switch writes `model_catalog_json = "cc-switch-model-catalog.json"`
(relative) via set_codex_model_catalog_json_field. Match on the
filename constant rather than the absolute path so the guard works
with both relative and absolute paths.
Co-authored-by: Codex review bot
* fix(proxy): parse model_catalog_json field instead of substring match
Replace raw config_text.contains() with proper TOML field parsing so
commented-out lines and stray mentions of the filename in other fields
don't defeat the stale guard. Also switch from contains() to exact
filename match (Path::new(val).file_name() == Some(...)) to stay
consistent with resolve_cc_switch_catalog_path in codex_config.rs.
Add log::debug! when the guard blocks serving so the operator can
distinguish "no models configured" from "guard blocked stale catalog".
* refactor(proxy): reuse resolve_cc_switch_catalog_path in handle_models
Replace the inline config.toml parsing and filename match in
handle_models with the existing resolve_cc_switch_catalog_path helper
(now pub(crate)). This removes the duplicated stale-guard logic, keeps
a single source of truth for catalog-path ownership, and makes the
handler honor absolute model_catalog_json paths the same way Codex
live-setting import does.
---------
Co-authored-by: Jason <farion1231@gmail.com>
Some Anthropic-compatible SSE providers (e.g. qwen, minimax) report the
full context (fresh + cached) as input_tokens in message_start, double
counting the cached portion that is also reported in
cache_read_input_tokens. This inflated the cacheable-input denominator
and pushed the displayed cache hit rate artificially low.
When a message_delta carries a smaller positive input_tokens, prefer it
over the message_start value and adopt the cache counts from the same
usage block to avoid double counting; fall back to the start cache
values when the delta omits them. Native Claude (no input in delta) and
OpenRouter-converted (input only in delta) paths are unchanged.
Refs #3580
Strict OpenAI-compatible upstreams (vLLM, enterprise gateways) reject
requests that carry tool_choice or parallel_tool_calls without a
non-empty tools array, returning 503/400 with:
"When using `tool_choice`, `tools` must be set."
The Responses→Chat Completions converter unconditionally forwarded
tool_choice and parallel_tool_calls even when tools ended up absent
or empty after conversion. This commit adds a guard that removes both
fields when the resulting tools array is missing or empty.
Added 9 regression tests covering:
- tool_choice dropped when tools absent
- tool_choice dropped when tools is empty array
- parallel_tool_calls dropped when tools absent
- tool_choice dropped when all tools filtered (e.g., missing name)
- tool_choice preserved when tools present (auto + function type)
- clean output when neither tool_choice nor tools present
- tool_choice 'none' dropped when no tools
- tool_search_output providing tools keeps tool_choice
Refs #3557
Co-authored-by: yueqi.guo <guo_yueqi@qq.com>
An upstream gateway (e.g. nginx client_max_body_size) rejecting an oversized request body with HTTP 413 was wrapped as "CC Switch local proxy failed ..." with the full nginx HTML page echoed as the cause. This misled users into thinking CC Switch imposed the limit, when the local DefaultBodyLimit is already 200MB and the real cap lives on the provider's server.
413 now gets a dedicated message that points at the upstream gateway, states it is the provider's server-side limit (not CC Switch), and gives actionable recovery steps (/compact, drop large logs/images, ask the provider to raise its limit). Structured fields (upstream_status, provider, model, endpoint) are preserved; other error paths are unchanged.
Refs #666
Replace unsupported Anthropic image blocks with an [Unsupported Image] marker when routed models are text-only or upstream rejects image input.
Add rectifier settings for media fallback and heuristic model detection, wire the controls into the settings UI, and cover the sanitizer and forwarder gates with regression tests.
* fix(copilot): raise infinite-whitespace threshold from 20 to 500
The previous threshold of 20 falsely aborted legitimate tool calls whose
arguments contain indented code (write_file / edit_file with 4-8 levels
of indentation in Python / YAML / Rust / Markdown easily exceed 20
consecutive whitespace chars, especially when newlines are counted).
The real infinite-whitespace bug emits hundreds to thousands of
consecutive whitespace characters, so 500 keeps the safety net while
drastically reducing false positives.
Refs #2646
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs: clarify whitespace threshold comment
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Jason <farion1231@gmail.com>
Custom (freeform) Codex tools are bridged through Chat Completions as
JSON `{"input": "..."}` functions, but the Chat->Responses stream still
re-emitted them via `response.function_call_arguments.*`, leaking the
JSON wrapper and using event types the Codex client does not route for
freeform tools.
Emit `response.custom_tool_call_input.delta`/`.done` (with the unwrapped
input text) for custom tool calls instead, suppressing the intermediate
function-argument deltas since a partial `{"input":` fragment cannot be
safely unwrapped mid-stream. Custom tool call items now use a `ctc_`
item-id prefix (matching the input events' item_id) consistently across
the streaming and non-streaming paths via a shared
response_tool_call_item_id_from_chat_name helper.
Covered by new streaming and non-streaming custom-tool tests.
When proxying Codex Responses requests through the Chat Completions
format (api_format=openai_chat), the request transform only forwarded
plain `function` tools and silently dropped `tool_search`, `namespace`
(MCP), and `custom` tools, so third-party APIs never saw the official
Codex plugins and could not call them.
Introduce CodexToolContext, built from the original Responses request,
which flattens all four tool kinds into Chat functions and keeps a
chat_name -> CodexToolSpec map. The response path (streaming and
non-streaming) looks names up in this map to restore the original
tool_search_call / custom_tool_call / namespaced function_call items
instead of reparsing the flattened name. Long namespaced names are
truncated with a sha256 suffix to fit the 64-char Chat tool-name limit.
Covered by new round-trip tests for all four tool kinds across both
streaming and non-streaming paths.
* fix(usage): resolve per-app credentials for native balance/coding-plan queries
The native usage-query paths (balance + coding_plan) in
`query_provider_usage_inner` read credentials only from `env.ANTHROPIC_*`.
That matches Claude providers, but Codex stores its key in
`auth.OPENAI_API_KEY` with the base URL inside a TOML `config` string,
Hermes/OpenClaw flatten them at the top level, and OpenCode nests them under
`options`. So the card "refresh usage" / auto-query returned empty
credentials and failed ("查询失败") for those apps, even though the
config-page "Test" button worked (the frontend extracts per-app correctly).
Introduce a single per-app resolver `Provider::resolve_usage_credentials`
that mirrors the frontend `getProviderCredentials`, and route both native
branches through it. Add `extract_codex_base_url` to `codex_config` as the
canonical Codex TOML base-URL parser and make the proxy adapter delegate to
it (removing a duplicate copy). Align the frontend `getProviderCredentials`
to cover OpenCode and Claude Desktop and to use the same OpenRouter/Google
key fallbacks as the backend.
Fixes#3158Fixes#3100Fixes#2625
* refactor(usage): explicit AppType arms + frontend trailing-slash trim
Address two review nits on the per-app credential resolver:
- provider.rs: replace the catch-all `_` arm in resolve_usage_credentials with an explicit `AppType::Claude | AppType::ClaudeDesktop` arm, so a new AppType variant fails to compile here instead of silently defaulting to the Anthropic env shape.
- UsageScriptModal.tsx: normalize getProviderCredentials baseUrl through a single trailing-slash trim so the frontend 'Test' path matches the backend resolver (trim_end_matches), keeping front/back truly in lockstep.
No behavior change for well-formed configs; tests/typecheck/fmt/clippy clean.
* fix(usage): skip empty primary credential fields in fallback chain
`obj.get(key)` returns `Some` for a present-but-empty field, so the
`.or_else()` fallback chains for the Claude/ClaudeDesktop and Gemini api-key
lookups only skipped *absent* keys, not empty ones. Presets seed fields like
`ANTHROPIC_AUTH_TOKEN` as present-but-empty placeholders, so a provider whose
real key lives in a fallback field (`ANTHROPIC_API_KEY` / `OPENROUTER_API_KEY`
/ `GOOGLE_API_KEY`, or `GOOGLE_API_KEY` for Gemini) resolved to an empty key on
the native balance/coding-plan path — while the frontend `a || b` (which skips
empty strings) still found it, reproducing the same Test-works / refresh-fails
divergence this PR removes.
Add a `first_non_empty` helper that skips present-but-empty values, matching
the frontend `||` semantics, and use it for both fallback chains. Tests cover
empty primary + populated fallback for Claude and Gemini.
* fix: add kimi/moonshot to Anthropic tool thinking history normalizer
Kimi's Anthropic-compatible endpoint requires reasoning_content in
assistant tool call messages when thinking is enabled, same as DeepSeek.
The is_reasoning_content_compatible_identifier already included kimi/moonshot
but is_anthropic_tool_thinking_history_identifier was missing them, causing
400 errors on multi-turn conversations with tool calls.
Closes#3351
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor: unify reasoning vendor hints into a single SSOT list
Replace the two separately-maintained vendor identifier lists with one
shared REASONING_VENDOR_HINTS constant and a single
is_reasoning_vendor_identifier predicate. The Anthropic
tool-thinking-history matcher and the openai_chat reasoning_content
matcher previously kept independent lists, which is exactly how
kimi/moonshot ended up in one but not the other (#3351). A single source
of truth keeps the two from drifting apart again.
Also add a Kimi regression test for the Anthropic tool-history
normalization path.
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Jason <farion1231@gmail.com>
When forward_with_retry fails for Codex endpoints (/chat/completions, /responses, /responses/compact), the handlers previously returned the bare ProxyError, surfacing a terse body to the client. Build a richer JSON error instead: the message embeds provider, model, endpoint and upstream status, and the error object carries those as structured fields alongside a stable cc_switch_* code.
Align map_proxy_error_to_status with ProxyError::into_response so the manually built responses use the canonical status codes (AuthError->401, Config/InvalidRequest->400, TransformError->422, StreamIdleTimeout->504, AlreadyRunning->409, NotRunning->503); previously these forwarder-level errors collapsed to 500.
Bump the default Opus route/model from claude-opus-4-7 to claude-opus-4-8
across provider presets (claude, claudeDesktop, hermes, openclaw, opencode,
universal), i18n locales (zh/en/ja/zh-TW), pricing seed data, and the
user-manual docs.
- Add claude-opus-4-8 pricing row ($5/$25/$0.50/$6.25); keep the 4-7 row
for historical usage stats (seeded via INSERT OR IGNORE).
- Claude Desktop proxy: accept bidirectional opus 4-7 <-> 4-8 route alias
during rollout so previously saved routes keep resolving.
- thinking_optimizer: route opus-4-8 through adaptive thinking and normalize
dotted model ids (also fixes dotted 4-6/4-7 falling back to legacy).
- usage_stats: normalize Bedrock/Vertex/aggregator opus-4-8 ids to base
pricing.
Also merge role:"system" messages into the Gemini systemInstruction in the
Anthropic->Gemini transform.
The usage dashboard previously only refreshed on app restart for users
who don't route through the cc-switch proxy. Two issues were involved:
1. The session-sync background task panicked when a Codex model name
contained non-ASCII characters (e.g. `【官】glm-5.1`), because
`normalize_codex_model` sliced `&name[name.len() - 11..]` without
verifying char boundaries. Once the task panicked, no session logs
were imported until the app was restarted (where startup-time
`rollup_and_prune` happened to flush pending data).
2. Even with sync working, the dashboard only polled every 30s and
skipped polling when the window was unfocused, so freshly-imported
data was invisible until the next poll or window refocus.
Fixes
-----
* `normalize_codex_model`: guard the 11-byte ISO-date suffix slice with
`is_char_boundary` + `is_ascii` checks. ASCII-only suffix means the
date-stripping logic is correct, and non-ASCII names (which can never
be valid date suffixes anyway) now bypass the slice safely.
* New `usage_events` module that emits `usage-log-recorded` to the
frontend whenever `proxy_request_logs` actually gains a new row.
Sources covered: proxy `log_request`, Claude/Codex/Gemini session
sync, and startup `rollup_and_prune`. Notifications use a global
`OnceLock<AppHandle>` so call sites that don't already hold an
`AppHandle` (e.g. `UsageLogger`) can notify without signature churn.
* 200ms debounce in `notify_log_recorded` collapses bursts (a single
Codex sync importing 3000+ entries triggers ~2 emits, not 3000) so
the frontend's `invalidateQueries` is never spammed.
* Frontend `useUsageEventBridge` listens for the event and invalidates
`usageKeys.all`. Hook is mounted only on `UsageDashboard`, so the
listener is unsubscribed automatically when the user navigates away.
Verification
------------
* `cargo check` passes (existing 25 dead-code warnings in
`commands/misc.rs` are pre-existing and unrelated).
* `tsc --noEmit` passes.
* Manually verified end-to-end: a Codex sync run that imported 3145
entries produced 2 debounced emits, both logged as `emit
usage-log-recorded 成功`, and the dashboard updated within ~200ms.
Behaviour notes
---------------
* `INSERT OR IGNORE` paths (Claude/Codex session sync) only notify when
the row is actually inserted, so dedup-skipped writes don't trigger
empty refreshes.
* Gemini's `INSERT … ON CONFLICT … DO UPDATE` path reuses the existing
`conn.changes() > 0` check and only notifies when token counts truly
changed.
* `rollup_and_prune` notifies once per pruning cycle (at most once per
app start) so the dashboard reflects the new aggregate state.
Co-authored-by: in30mn1a <in30mn1a@users.noreply.github.com>
* feat: add MiMo reasoning_content support for Claude Code proxy
MiMo requires reasoning_content to be passed back in multi-turn
conversations with tool calls. Add "mimo" and "xiaomimimo" to the
preserve_reasoning_content whitelist so thinking blocks are converted
to reasoning_content when proxying Claude Code → MiMo.
Also handle redacted_thinking blocks (encrypted by Claude Code across
turns) by injecting a placeholder to prevent MiMo 400 errors.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: support MiMo reasoning histories
- Fix the PR CI clippy failure for redacted thinking handling.
- Preserve MiMo reasoning content on the OpenAI Chat proxy path.
- Normalize Claude Desktop Anthropic thinking history for MiMo local routes.
- Reject unsupported Claude Desktop direct model remaps.
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Jason <farion1231@gmail.com>
Codex provider switches now only write config.toml for third-party providers,
injecting the API key as experimental_bearer_token. The user's auth.json
(ChatGPT OAuth tokens) is preserved. Official providers with login material
still write auth.json normally. Backfill restores bearer tokens into stored
provider auth.OPENAI_API_KEY to maintain canonical shape.
Harden the proxy module against panics by removing optimistic
unwrap()/expect() calls in favor of pattern matching and graceful
fallbacks:
- copilot_optimizer/cache_injector: bind Value::Array/String directly
instead of is_array()+as_array().unwrap(); use is_none_or and in-place
string mutation
- hyper_client: gate the raw-write path with if-let + filter instead of
has_cases + unwrap()
- gemini_shadow: recover poisoned RwLock via into_inner() rather than
panicking, with warn logging
- streaming_codex_chat: replace expect("tool state exists") with
let-else (return/continue)
- merge_tool_results: early-return when messages is absent
- sse: fall back to from_utf8_lossy on the UTF-8 boundary slice
No behavior change on the happy path; all proxy tests pass.
No-argument tool calls produced empty argument strings that passed
through both the streaming response path and the request transform
verbatim. Strict OpenAI-compatible upstreams (e.g. Minimax) reject
`arguments: ""` with a 400 "invalid function arguments json string",
while lenient ones (OpenAI, Kimi) silently treat it as an empty object.
Add canonicalize_tool_arguments / canonicalize_tool_arguments_str helpers
that coerce empty/whitespace arguments to "{}" and apply them at the four
tool-call argument sites (streaming finalize + three request/response
transform paths). Leave function_call_output content untouched, where an
empty string is valid.
Komi