mirror of
https://github.com/farion1231/cc-switch.git
synced 2026-07-25 13:45:03 +08:00
8d1b3306d09a27b9d8fc29694791d8421aba5f93
71 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Chenx Dust
|
1a0e8c7a44 |
fix: decompress body before forward and support zstd (#3817)
* 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 #3764 Fixes #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> |
||
|
Jianfeng Mei
|
6fd4e6f462 |
feat(proxy): 添加本地代理请求覆盖功能，支持自定义请求头和请求体 (#4589)
* feat(proxy): 添加本地代理请求覆盖功能，支持自定义请求头和请求体 * fix(proxy): harden local request overrides validation * feat(proxy): 添加受保护的本地代理请求头名称验证功能 * fix(i18n): 更新本地代理请求覆盖的错误提示信息格式 --------- Co-authored-by: jason.mei <jason.mei@ucloud.cn> |
||
|
chen-985211
|
36b557b2e6 |
fix(codex): restore cached tool call fields (#4160)
* 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> |
||
|
Jason
|
8b925c2f2f |
feat(proxy): honor custom User-Agent across stream check and model fetch
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). |
||
|
RoromoriYuzu
|
ff706e9e96 | feat: add provider user agent override | ||
|
Jason
|
feea81e5bb |
fix(proxy): bill route-takeover traffic by the real upstream model
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 |
||
|
Jason
|
3390fe7ea0 |
fix(proxy): extend image rectifier to Codex /responses text-only path
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. |
||
|
Dearli666
|
3cd9a0dec5 | fix(proxy): 规范化 Anthropic system 消息 (#3775) | ||
|
Jason
|
6692343d1e |
Add media fallback rectifier for text-only models
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. |
||
|
Q3yp
|
554e3b4875 |
fix(proxy): normalize DeepSeek Anthropic tool thinking history (#3203)
Fixes #3200 |
||
|
Jason
|
44d9aabbf3 |
feat: adaptive reasoning detection for Codex Chat providers
Auto-detect each Chat-routed Codex provider's reasoning interface from
its name, base URL, and model, then inject the matching thinking
parameter without manual configuration:
- Platform-first inference (OpenRouter, SiliconFlow) overrides model
rules, since the same model exposes different reasoning controls
depending on the hosting platform.
- Effort tiers are forwarded only to providers that support them
(DeepSeek, OpenRouter, and StepFun's step-3.5-flash-2603); on/off-only
providers (Kimi, GLM, Qwen, MiniMax, MiMo, SiliconFlow) drop the level
instead of sending a field the upstream rejects.
- OpenRouter uses the native reasoning:{effort} object, clamps max to
xhigh (its enum has no max), and forwards an explicit effort:"none" so
reasoning can be turned off.
- StepFun falls back to inference so per-model effort support is honored
(the static preset would have forced effort on step-3.5-flash too).
Includes the Codex provider-form reasoning controls, i18n strings
(zh/en/ja), and response-side reasoning extraction.
|
||
|
Jason
|
74acf1e387 |
Add Codex Chat-to-Responses bridge
- Add Codex provider API format selection and model mapping for Chat-only upstreams. - Convert Codex Responses requests to Chat Completions and rebuild Chat responses as Responses output. - Preserve reasoning_content across non-streaming, streaming, tool calls, and previous_response_id follow-ups. - Add a bounded Codex Chat history cache for restoring tool calls before tool outputs. - Cover Chat bridge, compact routing, streaming, and history recovery with focused tests. |
||
|
Jason
|
79d6486e16 |
Improve Codex Chat reasoning conversion
- Convert Chat reasoning_content and reasoning fields into Responses reasoning output items. - Emit Responses reasoning summary SSE events for streamed Chat reasoning deltas. - Preserve output ordering when reasoning, text, and tool calls are streamed together. - Add regression coverage for data-only Chat SSE errors, multiple tool calls, and compact routing. |
||
|
Jason
|
1c82b8a3fa |
Add Chat Completions routing for Codex providers
- Add a Codex API format selector and routing badge for Chat Completions providers. - Convert Codex Responses requests to upstream Chat Completions when routing is required. - Convert Chat Completions JSON and SSE responses back to Responses format. - Keep generated Codex wire_api values on Responses for Codex compatibility. - Add i18n labels, provider metadata handling, and focused conversion tests. |
||
|
Jason
|
61e68d754c |
fix(proxy): inject only ANTHROPIC_API_KEY for managed-account Claude takeover
- Provider: add uses_managed_account_auth / is_github_copilot helpers to identify managed-account providers (GitHub Copilot / Codex OAuth) - ProxyService: choose auth policy by provider type when taking over Claude Live config. Managed accounts drop token env keys and write only the ANTHROPIC_API_KEY placeholder; other providers keep the existing ANTHROPIC_AUTH_TOKEN fallback behavior - Forwarder: add outbound guard that refuses to send the PROXY_MANAGED placeholder upstream to *.githubcopilot.com and chatgpt.com /backend-api/codex - Add unit tests covering detection, injection, and the outbound guard |
||
|
Jason
|
9e6a7a0d81 |
- Fix proxy test helper clippy warning
- Mark `should_force_identity_encoding` as test-only. - Keep runtime forwarding behavior unchanged. - Verified with local CI checks and no-bundle Tauri build. |
||
|
Jason
|
b642ef0633 |
fix(failover): patch P1-P3 reliability gaps surfaced by team review
- Forwarder buffers non-streaming bodies and primes streaming first chunk before signaling success, so body timeouts and SSE first-chunk failures route through the circuit breaker instead of being recorded as success on response-header arrival - Atomic enable-failover: switch to P1 before persisting the flag, and roll back auto-added queue entries when the switch is rejected (e.g. official providers) - Hot-reload circuit breaker config on per-app proxy config change instead of waiting for a proxy restart - FailoverToggle / FailoverQueueManager / AutoFailoverConfigPanel require proxy takeover for the active app; the backend command also rejects enabling when takeover is off - ProviderHealthBadge consumes the backend is_healthy flag instead of hardcoding the 5-failure threshold Cleanup: - impl From<&AppProxyConfig> for CircuitBreakerConfig and use it from the command layer - Collapse three identical TabsContent blocks into a single map |
||
|
Jason
|
206125b4e3 |
fix(proxy): patch P0-P3 routing/lifecycle issues across forwarder paths
* stream_check: thread Result from get_auth_headers via map_err so the workspace builds again * forwarder: scope rectifier / budget-rectifier flags per-provider so failover can still apply rectification on the next attempt * forwarder: categorize before record_result; route NonRetryable and ClientAbort through release_permit_neutral so client-side failures don't pollute circuit breaker or DB health * handler_context: parse Gemini model from uri.path() and strip both ?query and :action verb defensively in extract_gemini_model_from_path * forwarder + response_processor + handlers: introduce ActiveConnectionGuard (RAII) so active_connections decrement covers the full streaming body lifetime, not just response headers * claude_desktop_config: use sort_by_key to clear the clippy gate |
||
|
Jason
|
85131d37d8 |
refactor(proxy): extract handle_rectifier_retry_failure helper
The signature (RECT-003) and budget (RECT-012) rectifier branches each
carried ~50 lines of identical "provider error -> record + continue /
client error -> release permit + return" handling. The only piece that
varied between them was a log label ("整流" vs "budget 整流").
Move the shared logic into RequestForwarder::handle_rectifier_retry_failure
that returns Option<ForwardError> — None means "continue to the next
provider", Some(err) means "terminal failure, return to the client".
Each call site shrinks from ~50 lines to ~17, drops one level of
indentation, and the two branches now provably cannot drift apart.
forwarder.rs nets ~40 lines smaller.
|
||
|
Jason
|
5d3d9067af |
feat(proxy): forward client HTTP method instead of hard-coding POST
The forwarder used to call client.post(&url) / http::Method::POST in both the reqwest and hyper paths, and the Gemini route table only registered POST /v1beta/*. As a result anything the Gemini SDK / CLI sent as GET (models list, models/<id> info) hit a 404 at the router and bypassed the local proxy's stats, rectifiers, and failover. Thread the request method end-to-end: - ProviderAdapter forwarder API now takes the http::Method by reference per attempt and dispatches client.request(method, &url) for reqwest and method.clone() for the hyper raw path. - All five callers in handlers.rs (handle_messages_for_app for Claude / Claude Desktop, handle_chat_completions, handle_responses, handle_responses_compact, handle_gemini) pull the method out of the incoming axum::extract::Request and pass it on. - handle_gemini tolerates an empty body (GET endpoints have none) and the forwarder skips serializing / sending a body for GET / HEAD — attaching JSON to a GET makes Gemini reject the request. - server.rs swaps the Gemini routes to any(handle_gemini) so the same handler handles GET / POST / PUT / DELETE, and adds /gemini/v1/* for the GA path version. |
||
|
Jason
|
f2ae9823cb |
fix(proxy): move client-request counters out of per-attempt loop
Three statistics-shape issues fixed together so the dashboard reflects
client requests, not provider attempts:
1. active_connections never moved off zero — the field had no caller in
the entire crate. Wrap forward_with_retry into a thin entry point
that saturating_add(1) on enter and saturating_sub(1) on exit; every
inner return path is covered automatically.
2. total_requests counted attempts, not requests. A single client call
that failed over P1 -> P2 -> success was recorded as
total=2 / success=1 -> 50% success rate. Move the increment and the
last_request_at refresh into the wrapper so they fire once per
client request regardless of how many providers were tried.
3. current_provider / current_provider_id stay inside the inner loop
because they are intentionally per-attempt ("what am I trying right
now?") — moving them would break the live-failover indicator.
Refactor: split forward_with_retry into a public wrapper + private
forward_with_retry_inner. Every existing `return Err(...)` inside inner
remains correct because the wrapper always runs the decrement on its
return.
|
||
|
Jason
|
b06e0fa538 |
fix(proxy): wire AppProxyConfig.max_retries into request forwarder
The UI has exposed "请求失败时的重试次数 (0-10, default 3)" since the auto-failover panel was added, but the value was silently dropped — RequestForwarder never received it and the per-provider loop walked the whole list regardless. From the user's perspective the setting was inert. Thread AppProxyConfig.max_retries through create_forwarder into RequestForwarder, derive max_attempts = max_retries + 1 (so max_retries=0 matches the UI copy "0 retries" = single attempt), and break the loop once attempts hit the cap. The check is placed before the circuit breaker allow-permit so an over-cap iteration does not waste a HalfOpen probe slot. When auto-failover is disabled we also force max_retries to 0, mirroring how timeouts already bypass in that mode — "no failover" should mean "one provider, one try", not "limited retries against the same list". |
||
|
Jason
|
cb4ecd3951 |
fix(proxy): refine failover decisions in forwarder
Two related changes to make per-provider failover behave correctly. 1. Bucket UpstreamError by status code in categorize_proxy_error. The old "every UpstreamError is Retryable" rule meant a malformed client request (400 / 422) would be replayed against every provider in the queue: errors amplified N-fold, the circuit breaker accrued unwarranted failure counts, and quota was burned. Now 400 / 405 / 406 / 413 / 414 / 415 / 422 / 501 are NonRetryable since the request itself is wrong and no provider will accept it. 401 / 403 / 404 / 408 / 409 / 429 / 451 and all 5xx remain Retryable because the next provider may carry a different key, quota, region, or model mapping. 2. Make the rectifier-retry path participate in failover. Both the signature (RECT-003) and budget (RECT-012) rectifier branches used to "return Err(...)" after the retry failed, short-circuiting the per-provider loop. A provider-side failure (5xx / Timeout / ForwardFailed) now records the circuit breaker, accumulates into last_error / last_provider, and "continue"s to the next provider — matching the normal Retryable arm. Client-side failures still return immediately since a different provider cannot fix a malformed payload. |
||
|
Jason
|
c9a6afc0b7 |
fix(proxy): return Result from get_auth_headers to avoid panic on bad credentials
User-pasted API keys can contain control chars or CR/LF that make HeaderValue::from_str return Err; the previous unwrap inside every adapter turned such input into a process-wide panic instead of a request error. The trait now returns Result<_, ProxyError>; Claude/Codex/Gemini impls propagate ProxyError::AuthError so the client sees a 401 with the underlying parse error instead of a crash. Adds a regression test that pastes a CRLF-containing key and asserts AuthError. |
||
|
Jason
|
4b57f7e113 |
feat(claude-code): role-based model mapping with display names and 1M flag
- Replace the four flat env inputs with a Sonnet/Opus/Haiku role table. Each row exposes ANTHROPIC_DEFAULT_*_MODEL plus a new display name field ANTHROPIC_DEFAULT_*_MODEL_NAME, and Sonnet/Opus gain a "Declare 1M" checkbox that toggles the [1M] suffix. - Strip the [1M] context-capability marker before forwarding non-Copilot requests upstream. Copilot keeps its existing [1m]->-1m normalization. - Claude Desktop import now consumes ANTHROPIC_DEFAULT_*_MODEL_NAME as label_override, closing the Claude Code -> Claude Desktop displayName pipeline; add_route's merge logic is shared between hashmap branches. - Unify the [1M] marker as ONE_M_CONTEXT_MARKER across claude_desktop_config and proxy::model_mapper; rename the strip helper to strip_one_m_suffix_for_upstream. - Collapse useModelState's seven duplicated useState initializers and the useEffect parse block into a single parseModelsFromConfig call. - Add tests/hooks/useModelState.test.tsx and a Claude Desktop import test covering Kimi K2 -> label_override. i18n (en/ja/zh) updated. |
||
|
Jason
|
4b384dfe55 |
perf(proxy): trim per-request hot-path work and db wait
- Guard debug body serialization with `log::log_enabled!`; previously
serialized the filtered body to a throwaway String on every forward,
even with debug logging off.
- Skip SSE parse + UTF-8 buffer loop when no usage collector and debug
is off; the per-chunk `serde_json::from_str::<Value>` ran even in
pure passthrough mode.
- Add cheap per-app SSE event pre-filter (string `contains`) so usage
collectors only parse events that could contain usage (e.g. Claude
`message_start` / `message_delta`).
- Skip non-streaming response body JSON parse when usage logging is
disabled.
- Move `ProviderRouter::record_result` off the success response path
via `tokio::spawn` for non-HalfOpen state; that call internally does
`get_proxy_config_for_app` + `update_provider_health`, two SQLite
ops that previously blocked TTFB.
Also: dedupe `usage_logging_enabled` (was duplicated in handlers.rs)
and merge `SseUsageCollector::{new, new_filtered}` into a single
constructor that takes `Option<StreamUsageEventFilter>`.
|
||
|
Jason
|
00a789e7a3 |
fix(proxy): improve cache hit rate for Codex/Responses requests
prompt_cache_key was falling back to provider.id when the client did not supply a session, which collapsed every conversation onto a single key and defeated upstream prefix caching. Only emit the key when a real client-provided session/thread identity is available; otherwise let the upstream use its default matching behaviour. Additional fixes that affect cache stability: - Canonicalise (sort) JSON keys in outgoing request bodies and in tool_call arguments / tool_result content so semantically identical requests produce identical byte sequences for upstream prefix caches. - Exempt JSON Schema property maps (properties, patternProperties, definitions, \$defs) from the underscore-prefix filter so user-defined schema keys like _id and _meta survive. - Add a [CacheTrace] debug log with stable hashes for instructions, tools, input and include to help diagnose cache misses. - Thread session_id into the usage logger for request correlation. |
||
|
Jason
|
292c117509 |
chore(backend): satisfy cargo fmt and clippy --all-targets
- Apply rustfmt diffs in claude_desktop_config.rs - Allow needless_return on current_platform_paths (cfg-mirrored arms) - Allow too_many_arguments on RequestForwarder::forward - Replace `let mut + reassign` with struct literals in tests (settings, backup, provider, response_processor) - Use Path::new instead of PathBuf::from to fix cmp_owned in misc tests - Replace 3.14 with 3.5 in config test to avoid approx_constant lint |
||
|
Jason
|
8b3ad9caf9 |
feat(claude-desktop): add 3P provider switching with proxy gateway
Adds a new ClaudeDesktop AppType that writes Claude Desktop's third-party
inference profile under configLibrary/, sharing _meta.json with other
launchers (Ollama-compatible) so cc-switch can coexist with them.
Two switch modes:
- direct: provider already exposes claude-* / anthropic/claude-* model
ids on Anthropic Messages, Claude Desktop connects to it directly.
- proxy: cc-switch's local proxy acts as the inference gateway,
presenting only claude-* route names to Claude Desktop and mapping
them to real upstream models. Required after Anthropic restricted
Claude Desktop to claude-family ids.
Backend:
- New module claude_desktop_config with snapshot/rollback, official seed
bypass, /claude-desktop/v1/{models,messages} routes, and a single
source of truth for default proxy routes.
- Gateway token persisted in SQLite, validated on every proxied request.
- get_claude_desktop_status surfaces drift signals (stale models,
missing routes, proxy stopped, base URL mismatch, missing token).
Frontend:
- Slim ClaudeDesktopProviderForm independent from ProviderForm,
controlled by a top-level appId guard.
- ProviderList banner consumes the status query (5s polling) and
renders actionable diagnostics.
- ClaudeDesktopRouteToggle in the header to start/stop the local
gateway without touching takeover state.
- Three-locale i18n synchronised.
|
||
|
Jason
|
e15bfbfe7a |
fix(proxy): reuse pooled HTTPS connections for non-Anthropic backends
The hyper raw-write path preserves original header casing but rebuilds TCP+TLS on every request — there is no connection pool — which was the root cause of slow reverse-proxy throughput. Only Anthropic-native requests actually need exact header-case preservation. Route OpenAI/Copilot/Codex/Gemini/codex_oauth requests through the pooled reqwest client (pool_max_idle_per_host=10, tcp_keepalive=60s) instead, so warm connections get reused. Streaming requests get a precise first-byte timeout via tokio::time::timeout around reqwest's send() (which resolves on response headers), with the body phase handed off to response_processor. The streaming-detection helper now also covers Gemini SSE endpoints and Accept: text/event-stream, not just body.stream. |
||
|
Jason
|
fcd83ee30d |
fix(copilot): resolve Claude model IDs against live /models list
Copilot upstream returns model_not_supported when the client sends dash-form Claude IDs (claude-sonnet-4-6, claude-sonnet-4-6[1m]) while /models only accepts dot form (claude-sonnet-4.6, -1m suffix). - Add copilot_model_map: syntax normalize (dash->dot, [1m]->-1m) plus live /models exact match and family-version fallback, reusing the existing 5 min auth cache. Returns None when the whole family is absent so upstream surfaces an explicit error instead of silently switching families. - Wire into forwarder Copilot hook; runs before anthropic_to_openai conversion. - Default Opus slot in the Copilot preset maps to Sonnet 4.6: Pro dropped all Opus on 2026-04-20 and Pro+ bills Opus 4.7 at 7.5x. Users who want real Opus can switch manually in the UI. Refs: https://github.com/farion1231/cc-switch/issues/2016 |
||
|
lif
|
444c123ad0 |
[codex] Stabilize Codex OAuth cache routing (#2218)
* Stabilize Codex OAuth cache routing Codex OAuth-backed Claude proxy requests now reuse a client-provided session identity for prompt cache routing and send Codex-like session headers when that identity exists. Generated proxy UUIDs are intentionally excluded so they do not fragment cache locality.\n\nThe same path exposed two runtime issues during validation: rustls needed an explicit process crypto provider, and Codex OAuth can return Responses SSE even when the original Claude request is non-streaming. Those are handled so cache-routed requests can complete instead of panicking or being parsed as JSON.\n\nConstraint: Official Codex uses conversation identity and Responses session headers for prompt cache routing.\nRejected: Always use generated proxy session IDs | generated IDs change per request and reduce cache reuse.\nConfidence: medium\nScope-risk: moderate\nDirective: Do not remove the client-provided-session guard unless generated session IDs become stable per conversation.\nTested: cargo test codex_oauth\nTested: Local dev app health check on 127.0.0.1:15721\nTested: Local proxy logs showed cache_read_tokens after restart\nNot-tested: Full cargo test without local cc-switch port conflict\nRelated: #2217 * feat(proxy): aggregate forced Codex OAuth SSE into JSON for non-streaming clients Narrow override on top of #2235's streaming fallback. Codex OAuth always forces upstream openai_responses into SSE, even when the original Claude request is stream:false. #2235 handles this by routing such responses through the streaming transform so the client receives text/event-stream — that avoids the 422 that JSON parsing would produce, and it also protects any other provider that unexpectedly returns SSE (the response.is_sse() guard). But for Claude SDK callers that sent stream:false, returning SSE still violates the Anthropic non-streaming contract. This commit adds an override on exactly one combination — non-streaming client + codex_oauth + openai_responses — to aggregate the upstream Responses SSE into a synthetic Responses JSON and then run the regular responses_to_anthropic non-streaming transform. All other paths, including the generic response.is_sse() fallback, remain on the streaming path from #2235. The aggregator reuses proxy::sse::take_sse_block / strip_sse_field, which support both \n\n and \r\n\r\n delimiters; a hand-rolled split("\n\n") would silently fail on real HTTPS upstreams. Tests cover the happy path, CRLF delimiters, response.failed errors, and the missing response.completed defensive branch. --------- Co-authored-by: Jason <farion1231@gmail.com> |
||
|
Jason
|
63aa310576 |
feat(copilot): strip thinking blocks before forwarding to save premium quota
Copilot routes through OpenAI-compatible endpoints that reject Anthropic's thinking and redacted_thinking blocks. Previously the request would fail upstream, burning one premium interaction, and only then trigger thinking_rectifier to retry. This adds a proactive strip_thinking_blocks pass in the Copilot optimization pipeline (step 3.5, after tool_result merging). Signature fields and top-level thinking are left alone — those are the reactive rectifier's job on the error path. Also fixes a default-value inconsistency where CopilotOptimizerConfig's Default impl used "gpt-4o-mini" while the serde default function returned "gpt-5-mini" (aligned to gpt-5-mini, matching the reference implementation). Aligned with yuegongzi/copilot-api's /v1/messages handler behavior. |
||
|
Dex Miller
|
03a0f9661b |
feat(proxy): Gemini Native API proxy integration (#1918)
* refactor(proxy): extract take_sse_block helper with CRLF delimiter support
Replace inline `buffer.find("\n\n")` SSE splitting logic across streaming,
streaming_responses, response_handler, and response_processor with a shared
`take_sse_block` function that handles both `\n\n` and `\r\n\r\n` delimiters.
* feat(proxy): add Gemini Native URL builder and full-URL resolver
Introduce gemini_url module that normalizes legacy Gemini/OpenAI-compatible
base URLs into canonical models/*:generateContent endpoints. Supports both
structured Gemini URLs (auto-normalized) and opaque relay URLs (pass-through
with query params only).
* feat(proxy): add Gemini Native schema, shadow store, transform, and streaming
- gemini_schema: Gemini generateContent request/response type definitions
- gemini_shadow: session-scoped shadow store for thinking signature and
tool-call state replay across streaming chunks
- transform_gemini: bidirectional Anthropic Messages ↔ Gemini Native
request/response conversion with thinking block and tool-use support
- streaming_gemini: Gemini SSE → Anthropic SSE streaming adapter with
incremental thinking/text/tool_use delta emission
* feat(proxy): wire Gemini Native format into proxy core and Claude adapter
Integrate gemini_native api_format throughout the proxy pipeline:
- ClaudeAdapter: detect Gemini provider type, Google/GoogleOAuth auth
strategies, and suppress Anthropic-specific headers for Gemini targets
- Forwarder: Gemini URL resolution, shadow store threading, endpoint
rewriting to models/*:generateContent with stream/non-stream variants
- Handlers: route Gemini streaming through streaming_gemini adapter and
non-streaming through transform_gemini converter
- Server/State: add GeminiShadowStore to shared ProxyState
- StreamCheck: support gemini_native health check with proper auth headers
* feat(ui): add Gemini Native provider preset and api format option
- Add gemini_native to ClaudeApiFormat type and ProviderMeta.apiFormat
- Add "Gemini Native" provider preset with default Google AI endpoints
- Show Gemini-specific endpoint hints and full-URL mode guidance
- Add gemini_native option to API format selector in ClaudeFormFields
- Add i18n strings for zh/en/ja
* feat(proxy): add Gemini Native tool argument rectification
* feat(proxy): update Gemini streaming and transformation logic
* fix(proxy): align shadow turns to tail on client history truncation
* fix: revert unrelated cache_key change in claude proxy transform
Restore .unwrap_or(&provider.id) fallback for cache_key to match main
branch behavior. Only gemini_native related changes should be in this branch.
* Prevent Gemini review regressions in streaming and tool rectification
PR #1918 review feedback exposed two correctness issues in the Gemini Native adapter path. Gemini SSE buffering was still using lossy UTF-8 decoding, which could corrupt split multibyte payloads and drop streamed output. Tool arg rectification also removed top-level parameters eagerly, which broke tools that legitimately define a parameters field.
This change moves Gemini SSE buffering onto the existing append_utf8_safe path and makes parameters flattening conditional on the schema actually expecting nested extraction. The old Skill rectification path stays intact, and new regression tests cover both the preserved parameters case and UTF-8-split JSON payloads.
Constraint: Existing PR #1918 review feedback must be fixed without staging unrelated local docs and artifact files
Rejected: Keep String::from_utf8_lossy in Gemini SSE buffering | corrupts split multibyte payloads and can drop JSON chunks
Rejected: Always preserve the parameters wrapper | regresses the existing nested-parameters rectification path for Skill-style tools
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep Gemini SSE buffering on the UTF-8-safe accumulator path and only unwrap parameters when the target schema does not declare it as a legitimate field
Tested: cargo fmt --manifest-path src-tauri/Cargo.toml --all; cargo test --manifest-path src-tauri/Cargo.toml preserves_utf8_boundaries_when_json_payload_spans_chunks; cargo test --manifest-path src-tauri/Cargo.toml gemini_to_anthropic_rectifies_tool_args_from_schema_hints; cargo test --manifest-path src-tauri/Cargo.toml rectifies_streamed_skill_args_from_nested_parameters; cargo test --manifest-path src-tauri/Cargo.toml gemini_to_anthropic_preserves_legitimate_parameters_arg
Not-tested: Full src-tauri test suite; live end-to-end Gemini relay traffic against upstream services
* Keep Gemini tool replay stable across Claude request boundaries
Claude Code follow-up requests were still falling back to locally reconstructed functionCall parts, which dropped Gemini thought signatures and triggered INVALID_ARGUMENT errors from the official Gemini API. The replay path needed to survive real Claude request boundaries, not just idealized in-process test flows.
This change makes Claude requests reuse X-Claude-Code-Session-Id as the shadow session key, records streamed Gemini tool turns before tool_use events are fully drained, and matches assistant tool_use turns to shadow state by tool_use id and normalized tool name before positional fallback. Together these fixes keep thoughtSignature-bearing Gemini tool calls available for the next request in the loop.
Constraint: Claude Code sends a stable X-Claude-Code-Session-Id header while metadata.session_id may be absent on follow-up requests
Rejected: Rely on metadata-only Claude session extraction | generated fresh session ids and broke cross-request shadow replay
Rejected: Record Gemini shadow only after streaming completes | loses the race when the client sends the next request immediately after tool_use
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Preserve Gemini shadow continuity across requests by keying Claude sessions from the header first and persisting tool-call shadow before yielding tool_use events downstream
Tested: cargo fmt --manifest-path src-tauri/Cargo.toml --all; cargo test --manifest-path src-tauri/Cargo.toml test_extract_session_from_claude_header; cargo test --manifest-path src-tauri/Cargo.toml test_extract_session_from_claude_header_precedes_metadata; cargo test --manifest-path src-tauri/Cargo.toml stores_tool_shadow_before_tool_use_events_are_fully_drained; cargo test --manifest-path src-tauri/Cargo.toml shadow_replay_matches_tool_use_turn_by_id_when_position_drifts; cargo test --manifest-path src-tauri/Cargo.toml shadow_replay_aligns_to_latest_turns_after_client_truncation
Not-tested: Full src-tauri test suite without test filters; live end-to-end Gemini relay after this exact commit hash
* style: apply cargo fmt to pass Backend Checks CI
Wrap prompt_cache_key chained call across lines per rustfmt default
formatting. Pure formatting change, no behavior difference.
* fix(proxy/gemini): synthesize unique ids for no-id tool calls + enforce object params schema
P1 — Parallel tool calls without Gemini-assigned ids no longer collapse.
Gemini 2.x native parallel `functionCall` entries may omit the `id` field.
The previous `merge_tool_call_snapshots` fell back to matching by `name`,
which silently merged two parallel calls to the same function into one
entry — dropping the first call's args. The non-streaming path and shadow
store further bottlenecked on empty-string ids: multiple `tool_use` blocks
shared the same id, and `tool_name_by_id.get("")` could only return one
mapping, causing later `tool_result` round-trips to fail with
`Unable to resolve Gemini functionResponse.name` or bind to the wrong tool.
Fix: introduce `synthesize_tool_call_id()` producing `gemini_synth_<uuid>`.
Both streaming and non-streaming response paths now guarantee every
Anthropic-visible tool_use carries a unique id. `merge_tool_call_snapshots`
matches by id first, falling back to the `parts` array position (for the
cumulative-streaming case) while preserving the synthesized id across
chunks. `convert_message_content_to_parts` detects the synthetic prefix
and strips the id from outbound `functionCall`/`functionResponse` so the
internal identifier never leaks upstream. `shadow_parts` performs the
same strip when replaying a recorded assistant turn.
P2 — Vertex AI rejects empty `parameters` schemas. When an Anthropic tool
arrives with missing or empty `input_schema`, the proxy used to emit
`"parameters": {}` (no `type`), which fails Vertex AI validation with
`functionDeclaration parameters schema should be of type OBJECT`.
Contrary to the automated-review suggestion, the fix is not to omit
`parameters` (that too is rejected) but to normalize to the canonical
empty-object form `{type: "object", properties: {}}`.
Refs: google-gemini/generative-ai-python#423, BerriAI/litellm#5055.
Fix: new `ensure_object_schema` helper in `gemini_schema` promotes
missing `type` to `"object"` and adds empty `properties` when absent,
while leaving atomic (non-object) schemas untouched.
Tests: seven new regressions covering parallel no-id calls, cumulative
chunk id reuse, synthetic-id round-trip both directions, shadow replay
id stripping, and the three Vertex-AI schema shapes.
The two existing wrapper functions (`gemini_to_anthropic` and
`gemini_to_anthropic_with_shadow`) gain `#[allow(dead_code)]` to clear
a pre-existing clippy -D warnings failure — they are part of the public
transform API surface and intentionally kept for future callers.
Addresses Codex review P1/P2 on #1918.
* fix(proxy/gemini): narrow URL normalization + guard empty OAuth access_token
P2a — Preserve opaque relay URLs that contain `/v1/models/` prefixes.
`should_normalize_gemini_full_url` previously flagged any full URL whose
path merely contained `/v1beta/models/` or `/v1/models/` as a structured
Gemini endpoint, forcing rewrite to `.../v1beta/models/{model}:method`.
This silently dropped legitimate relay route segments (e.g.
`https://relay.example/v1/models/invoke` → `.../v1beta/models/...:generateContent`,
losing `/invoke`) and sent traffic to the wrong upstream path.
Replace the bare `contains(...)` checks with
`matches_structured_gemini_models_path`, which requires the
`/models/` segment to be followed by a canonical Gemini method call
(`*:generateContent` or `*:streamGenerateContent`). The
`matches_bare_gemini_models_path` helper is generalized (and renamed) to
handle both `/v1beta/models/` and `/v1/models/` alongside the original
bare `/models/` shape.
P2b — Reject empty Gemini OAuth access_tokens before they reach the
bearer header.
`GeminiAdapter::parse_oauth_credentials` accepts refresh-token-only JSON
(and surfaces `{"access_token": "", ...}` for expired credentials) with
`access_token` defaulting to `""`. The Claude adapter's GeminiCli branch
then called `AuthInfo::with_access_token(key, creds.access_token)`
unconditionally, so the bearer-header builder at
`AuthStrategy::GoogleOAuth` resolved to `Authorization: Bearer ` — a
deterministic 401 from upstream.
CC Switch does not currently exchange the refresh_token for a fresh
access_token (`OAuthCredentials::needs_refresh` / `can_refresh` are
annotated `#[allow(dead_code)]`). Until that exists, only attach
`access_token` when it is non-empty; fall back to plain GoogleOAuth
strategy with the raw key and log a warn pointing users at
`~/.gemini/oauth_creds.json` so the failure mode is observable.
Tests:
- gemini_url.rs: three new regressions — opaque `/v1/models/invoke`,
opaque `/v1beta/models/route`, and the positive counter-case where a
structured `/v1/models/...:generateContent` path still normalizes.
- claude.rs: three new `test_extract_auth_gemini_cli_*` tests covering
refresh-only JSON, empty-string access_token JSON, and the valid-JSON
pass-through.
All 839 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex review P2 findings on #1918.
* fix(proxy/gemini): treat empty-string functionCall id as missing in streaming path
Follow-up to the earlier P1 fix: some Gemini relays serialize an absent
functionCall id as `"id": ""` instead of omitting the field. The
non-streaming `extract_tool_call_meta` already filters these via
`.filter(|s| !s.is_empty())`, but the streaming counterpart
`extract_tool_calls` passed the empty string straight through
`function_call.get("id").and_then(|v| v.as_str())` into
`GeminiToolCallMeta::new`, producing a `Some("")` id.
Downstream, `merge_tool_call_snapshots` would then match two parallel
no-id calls against each other on their shared empty-string id,
collapsing them into a single snapshot (silent data loss for the first
call) and emitting an Anthropic `tool_use.id: ""` that breaks tool_result
correlation on the Claude Code client.
Fix:
- `extract_tool_calls`: apply the same `filter(|s| !s.is_empty())` guard
used in the non-streaming path so empty strings become `None` before
reaching the shadow meta.
- `merge_tool_call_snapshots`: defensively collapse any incoming
`Some("")` to `None` up front — keeps the "missing vs present" invariant
local to the merge step for future callers that might build
`GeminiToolCallMeta` by hand.
Tests (2 new, both in streaming_gemini):
- `parallel_empty_string_id_calls_are_treated_as_missing_and_preserved`
covers two parallel calls with explicit `"id": ""` — asserts both
surface, no empty tool_use id leaks, and each gets a unique
`gemini_synth_` id.
- `single_empty_string_id_tool_call_gets_synthesized_id` covers the
non-parallel degraded-relay case.
All 841 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex follow-up P1 on #1918.
* fix(proxy/gemini): gate generic REST path suffixes behind Google host whitelist
`should_normalize_gemini_full_url` previously treated any full URL whose
path ends with `/v1`, `/v1/models`, `/models`, `/v1/openai`, or `/openai`
as a structured Gemini endpoint and rewrote it to
`/v1beta/models/{model}:generateContent`. These are ubiquitous REST
conventions — opaque relays such as `https://relay.example/custom/v1`
legitimately use them for fixed endpoints — so the rewrite silently
routed traffic to the wrong upstream path.
Split the predicate into two layers:
- **Unconditional**: `matches_structured_gemini_models_path` (i.e. a
`/models/...:generateContent` method call anywhere in the path), the
Google-specific `/v1beta*` family, and the deep OpenAI-compat paths
(`/v1beta/openai/chat/completions`, `/openai/chat/completions`, and
their `responses` siblings). These remain host-agnostic because the
path grammar itself is Gemini-specific.
- **Google-host gated**: `/v1`, `/v1/models`, `/models`, `/v1/openai`,
`/openai`. Only normalized when the host is one of
`generativelanguage.googleapis.com`, `aiplatform.googleapis.com`, or a
real `*-aiplatform.googleapis.com` Vertex regional endpoint. The match
is exact/suffix (not `contains`), so lookalike hosts like
`aiplatform.example.com` are correctly treated as opaque relays.
Tests (8 new in `gemini_url::tests`):
- Four opaque-relay cases: `/custom/v1`, `/custom/models`,
`/custom/v1/models`, `/custom/openai` — all preserved as-is.
- Three Google-host counter-cases: `/v1`, `/models`, and
`us-central1-aiplatform.googleapis.com/v1` still normalize.
- One lookalike safety case: `aiplatform.example.com/v1` is NOT
treated as Google.
All 849 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex review P2 on #1918.
* fix(proxy/gemini): align shadow id with client-visible id in non-streaming path
When Gemini returns a `functionCall` without an id (common in 2.x
parallel calls), `gemini_to_anthropic_with_shadow_and_hints` previously
generated TWO independent synthesized UUIDs:
1. Line 186-197 — synthesized id `A` used for the Anthropic-visible
`content[tool_use].id` returned to the client.
2. Line 850-881 — `extract_tool_call_meta` independently synthesized
id `B ≠ A`, which populated `shadow_turn.tool_calls[i].id`.
`shadow_content` (line 225-228, cloned from `rectified_parts`) retained
the original missing/empty id. Result: the client sees id `A`, the
shadow store holds id `B`.
On the next turn, `convert_messages_to_contents` builds
`tool_name_by_id` from `build_tool_name_map_from_shadow_turns`, which
uses `tool_calls[i].id` — so the map contains `B → name` but not
`A → name`. When the client sends back `tool_result(tool_use_id=A)`,
resolution fails with:
Unable to resolve Gemini functionResponse.name for tool_use_id `A`
This affects both truncated histories (client sends only the
tool_result) and full histories (shadow-replay branch at line 342-354
skips `convert_message_content_to_parts`, so the assistant tool_use
block never registers id `A` itself).
Fix: make `rectified_parts` the single source of truth. After
`rectify_tool_call_parts`, run a pre-pass that writes
`synthesize_tool_call_id()` back into any `functionCall` that lacks a
non-empty id. All three readers — the content builder (186-197), the
shadow_content clone (225-228), and `extract_tool_call_meta` — then
observe the same id. `shadow_parts()` already strips synthesized ids on
replay (line 616-628), so the internal identifier never leaks to
Gemini upstream.
This mirrors the streaming path, which already has single-source-of-
truth semantics via `tool_call_snapshots` in `streaming_gemini.rs` —
no change needed there.
Tests (5 new in `transform_gemini::tests`):
- `non_stream_shadow_id_matches_client_visible_id`: asserts
`response.content[0].id == shadow.tool_calls[0].id ==
shadow.assistant_content.parts[0].functionCall.id`.
- `non_stream_missing_id_scenario_a_truncated_history_resolves`: turn 2
sends only `[tool_result(id=A)]`; resolution must succeed.
- `non_stream_missing_id_scenario_b_full_history_replay_resolves`: turn 2
sends `[assistant(tool_use=A), tool_result(A)]`; shadow-replay branch
strips the synth id from outgoing `functionCall` while still
resolving the subsequent `tool_result`.
- `non_stream_preserves_original_gemini_id_when_present`: regression —
genuine Gemini ids flow through unchanged.
- `non_stream_synthesized_id_not_leaked_to_gemini_via_shadow_replay`:
defensive — shadow-replay path must strip synth ids from both
`functionCall.id` and `functionResponse.id`.
All 854 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex follow-up P1 on #1918.
* refactor(proxy/gemini): share build_anthropic_usage between stream and non-stream paths
`streaming_gemini::anthropic_usage_from_gemini` and
`transform_gemini::build_anthropic_usage` were byte-for-byte identical
(32 lines each) — both converting Gemini `usageMetadata` into the
Anthropic `usage` shape including `cache_read_input_tokens` mapping.
Promote the non-streaming version to `pub(crate)` and reuse it from the
streaming SSE converter. Removes ~30 lines of duplication and guarantees
the two paths cannot drift apart.
No behavioral change; all 854 lib tests pass; cargo fmt + clippy -D
warnings clean.
* fix(proxy/gemini): gate /v1beta behind Google host + normalize models/ model id prefix
Two related P2 corrections to the Gemini Native URL surface, both
folding into the existing Google-host-whitelist architecture.
## P2a — `/v1beta` suffix should not unconditionally trigger rewrite
`should_normalize_gemini_full_url` placed `/v1beta` and `/v1beta/models`
in the unconditional layer on the reasoning that `/v1beta` is
Google-specific. In practice an opaque relay fronting a non-Gemini
service at `https://relay.example/custom/v1beta` would still be
silently rewritten to `/v1beta/models/{model}:generateContent`,
breaking the deployment.
Move `/v1beta`, `/v1beta/models`, and `/v1beta/openai` into the
Google-host gated layer alongside `/v1`, `/models`, and friends. The
unconditional layer now only accepts paths whose grammar is
intrinsically Gemini — `/models/...:generateContent` method calls and
the deep OpenAI-compat endpoints like `/openai/chat/completions` and
`/openai/responses`. Pasted AI-Studio URLs such as
`https://generativelanguage.googleapis.com/v1beta` still normalize
because the host matches the whitelist.
## P2b — `model: "models/gemini-2.5-pro"` produced doubled path prefix
Gemini SDKs (and the official `list_models` response) commonly surface
model ids in resource-name form `models/gemini-2.5-pro`. Raw
interpolation into `format!("/v1beta/models/{model}:...")` produced
`/v1beta/models/models/gemini-2.5-pro:streamGenerateContent` which
upstream rejects — yielding false-negative health checks for otherwise
valid provider configs.
Introduce `normalize_gemini_model_id(&str) -> &str` in `gemini_url`
as the single source of truth: strips an optional leading `/` then an
optional `models/` prefix, leaving bare ids untouched. Apply in the
three call sites that build a Gemini method URL:
- `services/stream_check.rs::resolve_claude_stream_url` (unified path)
- `services/stream_check.rs::check_gemini_stream` (Gemini-only path)
- `proxy/forwarder.rs::rewrite_claude_transform_endpoint` (production)
Tests (9 new):
- `gemini_url`: 3 regressions for opaque vs Google-host `/v1beta*`
handling + 5 unit tests pinning `normalize_gemini_model_id` behavior
(strip prefix, leave bare id, preserve nested slashes past the one
stripped prefix, tolerate leading slash, pass through empty input).
- `stream_check`: one end-to-end regression confirming
`models/gemini-2.5-pro` collapses to the expected single-prefix URL.
- `forwarder`: one end-to-end regression on the production rewrite
path.
All 864 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex P2 feedback on #1918.
* fix(proxy/gemini): trim API key before provider-type detection and OAuth parsing
Leading whitespace on a copied oauth_creds.json (e.g. trailing newline
when the user copies the file content as-is) would slip past the
`starts_with("ya29.") || starts_with('{')` prefix check in
`ClaudeAdapter::provider_type`, causing the provider to be misclassified
as raw-API-key Gemini and fall back to `x-goog-api-key` with the raw
JSON as the key — which upstream rejects with 401.
The frontend's `handleApiKeyChange` already trims on keystrokes but
deep-link imports, the JSON editor, and live-config backfill all bypass
that path. Trim at every backend extraction point so the coverage is
uniform:
- `ClaudeAdapter::extract_key` (5 env / fallback branches) gets
`.map(str::trim)` before `.filter(|s| !s.is_empty())` so that
whitespace-only values are also treated as missing.
- `GeminiAdapter::extract_key_raw` gets the same chain (including
the `.filter` it was missing before).
- `GeminiAdapter::parse_oauth_credentials` gets a defensive
`let key = key.trim();` at the entry as a belt-and-suspenders guard.
Adds two regression tests covering JSON and bare `ya29.` keys with
leading newline/space.
* fix(proxy/gemini): gate generic REST suffix stripping behind Google host in non-full-URL mode
`build_gemini_native_url` unconditionally stripped `/v1`, `/v1beta`,
`/models`, and `/openai` suffixes from the base path regardless of
host. This worked for Google's own endpoints but silently rewrote
third-party relay URLs like `https://relay.example/custom/v1` to
`.../custom/v1beta/models/...`, breaking any relay that mounts its
Gemini-compatible namespace under a versioned prefix.
The result was also asymmetric with the previously-fixed full-URL
branch: toggling the "full URL" switch changed the outbound URL for
the same base_url, which is exactly the kind of invisible behavior
that makes debugging proxy deployments painful.
Align `normalize_gemini_base_path` with
`should_normalize_gemini_full_url`'s layered model:
- Unconditional: `/models/...:method` structured paths and deep
OpenAI-compat endpoints (`/openai/chat/completions`,
`/openai/responses` and their versioned variants) — these are
unambiguous Gemini-specific grammar on any host.
- Google-host gated: generic `/v1`, `/v1beta`, `/models`, `/openai`
suffixes only get stripped on `generativelanguage.googleapis.com`,
`aiplatform.googleapis.com`, or `*-aiplatform.googleapis.com`.
Other hosts preserve the prefix verbatim so relays keep their
intended routing.
Adds seven regression tests for the non-full-URL flow: opaque relay
preservation (v1 / v1beta / models / openai suffix variants), Google
host normalization (counter-case), and boundary cases (structured
method path and deep OpenAI-compat endpoint stripped regardless of
host).
Test count: 864 -> 873.
* Revert "fix(proxy/gemini): gate generic REST suffix stripping behind Google host in non-full-URL mode"
This reverts commit
|
||
|
Jason
|
4a0b5c3dec |
refactor: remove per-provider proxy config feature
The per-provider proxy configuration (meta.proxyConfig) is removed because its scope is too narrow and covered by global proxy settings and proxy takeover mode. Users can achieve the same result via the global proxy panel. Changes: - Remove ProviderProxyConfig type (frontend TS + backend Rust) - Remove ProviderAdvancedConfig proxy UI block, keep testConfig/pricingConfig - Simplify http_client: delete build_proxy_url_from_config, build_client_for_provider, get_for_provider - Simplify forwarder/stream_check/model_fetch to use global client - Remove i18n keys (en/zh/ja) - Fix pre-existing test bug in transform.rs (extra None arg) |
||
|
Jason
|
d13a8d7353 |
fix(clippy): remove redundant closure in session ID parsing
Replace `|uid| parse_session_from_user_id(uid)` with direct function reference to satisfy clippy::redundant_closure. |
||
|
Jason
|
0739b60341 |
fix(proxy): reduce unnecessary Copilot premium interaction consumption
- Fix request classification: treat messages containing tool_result as agent continuation instead of user-initiated, preventing false premium charges on every tool call - Add subagent detection via __SUBAGENT_MARKER__ and metadata._agent_ fallback, setting x-interaction-type=conversation-subagent - Add deterministic x-interaction-id derived from session ID to group requests into a single billing interaction - Add orphan tool_result sanitization to prevent upstream API errors that could cause retries and duplicate billing - Reorder pipeline: classify (on original body) → sanitize → merge → warmup, ensuring classification sees raw tool_result semantics - Enable warmup downgrade by default with gpt-5-mini model - Enhance session ID extraction priority chain for Copilot cache keys - Detect infinite whitespace bug in streaming tool call arguments |
||
|
Jason
|
6a34253934 |
feat: add Codex OAuth (ChatGPT Plus/Pro) reverse proxy support
Adds a new managed OAuth provider that lets Claude Code route requests through a user's ChatGPT Plus/Pro subscription via the chatgpt.com backend-api/codex endpoint. - CodexOAuthManager: OpenAI Device Code flow with multi-account support, JWT-based account identification, and automatic access_token refresh. - Reuses the generic managed-auth command surface (auth_start_login, auth_poll_for_account, etc.) via provider dispatch in commands/auth.rs. - ClaudeAdapter detects codex_oauth providers, forces the base URL to the ChatGPT backend, pins api_format to openai_responses, and emits Authorization + originator headers; the forwarder injects the dynamic access_token and ChatGPT-Account-Id per request. - transform_responses gains an is_codex_oauth path that aligns the body with OpenAI's codex-rs ResponsesApiRequest contract: sets store:false, appends reasoning.encrypted_content to include, strips max_output_tokens / temperature / top_p, injects default instructions/tools/parallel_tool_calls, and forces stream:true. Covered by 9 new unit tests plus regression guards for the non-Codex path. - Stream check reuses the same transform flag so detection matches the production request shape. - Frontend adds CodexOAuthSection + useCodexOauth hook, integrates it into ClaudeFormFields / ProviderForm / AuthCenterPanel, ships a new "Codex (ChatGPT Plus/Pro)" preset, and adds zh/en/ja i18n strings. |
||
|
Jason
|
2513687184 |
feat: add Copilot optimizer to reduce premium interaction consumption
Implement request classification, tool result merging, compact detection, deterministic request IDs, and warmup downgrade for Copilot proxy. The root cause was x-initiator being hardcoded to "user", making Copilot count every API request (including tool callbacks and agent continuations) as a separate premium interaction. The optimizer dynamically classifies requests as "user" or "agent" based on message content analysis. Closes #1813 |
||
|
Zhou Mengze
|
de49f6fbbe |
fix(copilot): 修复 GitHub Copilot 认证和代理问题 (#1854)
* fix(copilot): 修复 GitHub Copilot 400 认证错误 问题：使用 GitHub Copilot provider 时报错 400 bad request 根因：与 copilot-api 项目对比发现多处差异 修复内容： - 更新版本号 0.26.7 到 0.38.2 - 更新 API 版本 2025-04-01 到 2025-10-01 - 添加缺失的关键 headers - 修正 openai-intent 值 - 添加动态 API endpoint 支持 - 同步更新 stream_check.rs headers Closes #1777 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: flush stream after write_all in hyper_client proxy Add explicit flush() calls after write_all() for TLS stream, plain TCP stream, and CONNECT tunnel requests to ensure buffered data is sent immediately, preventing connection hangs in Copilot auth header flow. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * 修复登录时的剪切板在mac与linux端可能没复制验证码 * fix: flush stream after write_all in hyper_client proxy Add explicit flush() calls after write_all() for TLS stream, plain TCP stream, and CONNECT tunnel requests to ensure buffered data is sent immediately, preventing connection hangs in Copilot auth header flow. * 修复登录时的剪切板在mac与linux端可能没复制验证码 * 1、修复不同类型的个人商业等不同类型的copilot账号问题 2、将验证码复制改为异步操作 * fix: address PR review comments for Copilot auth │ │ │ │ - Fix clipboard blocking by using spawn_blocking for arboard ops │ │ - Implement dynamic endpoint routing for enterprise Copilot users │ │ - Add api_endpoints cache cleanup in remove_account() and clear_auth() │ │ - Change API endpoint log level from info to debug │ │ - Fix clear_auth() to continue cleanup even if file deletion fails │ │ - Add 9 unit tests for Copilot detection and api_endpoints cachin * style: fix cargo fmt formatting * Fix Copilot dynamic endpoint handling * fix: restore clear_auth() memory-first cleanup order and fix cache leaks - Restore clear_auth() to clean memory state before deleting the storage file. The previous order (file deletion first) caused a regression where users could get stuck in a "cannot log out" state if file removal failed. - Add missing copilot_models.clear() in clear_auth() — this cache was cleaned in remove_account() but never in the full clear path. - Add endpoint_locks cleanup in both remove_account() and clear_auth() to prevent minor in-process memory leaks. - Update test to assert the correct behavior: memory should be cleaned even when file deletion fails. --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: 周梦泽 <mengze.zhou@dafeng-tech.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Jason <farion1231@gmail.com> |
||
|
Dex Miller
|
67e074c0a7 |
refactor(proxy): transparent header forwarding via hyper client (#1714)
* style(frontend): reformat provider forms, constants and hooks
Apply prettier formatting across 5 frontend files. No logic changes.
Changed files:
- AddProviderDialog.tsx: reformat generic type annotation and callback
- ClaudeFormFields.tsx: consolidate multi-line useState and Collapsible props
- CodexConfigSections.tsx: expand single-line React imports to multi-line,
collapse removeCodexTopLevelField() call
- constants.ts: merge TemplateType into single line
- useSkills.ts: expand single-line TanStack Query imports to multi-line,
reformat uninstallSkill mutationFn chain
* deps(proxy): add hyper ecosystem crates and manual decompression libs
reqwest internally normalizes all header names to lowercase and does not
preserve insertion order, causing proxied requests to differ from the
original client requests. To achieve transparent header forwarding with
original casing and order, introduce lower-level hyper HTTP client libs.
New dependencies:
- hyper-util 0.1: TokioExecutor + legacy Client with
preserve_header_case support for HTTP/1.1
- hyper-rustls 0.27: rustls-based TLS connector for hyper
- http 1 / http-body 1 / http-body-util 0.1: HTTP type crates for
hyper 1.x request/response construction
- flate2 1: manual gzip/deflate decompression (replaces reqwest auto)
- brotli 7: manual brotli decompression
Changed dependencies:
- serde_json: enable preserve_order feature to keep JSON field order
- reqwest: drop gzip feature to prevent reqwest from overriding the
client's original accept-encoding header
* refactor(proxy): use hyper client for header-case preserving forwarding
Previously the proxy used reqwest for all upstream requests. reqwest
normalizes header names to lowercase and reorders them internally,
making proxied requests distinguishable from direct CLI requests.
Some upstream providers are sensitive to these differences.
This commit replaces reqwest with a hyper-based HTTP client on the
default (non-proxy) path, achieving wire-level header fidelity:
Server layer (server.rs):
- Replace axum::serve with a manual hyper HTTP/1.1 accept loop
- Enable preserve_header_case(true) so incoming header casing is
captured in a HeaderCaseMap extension on each request
- Bridge hyper requests to axum Router via tower::Service
New hyper client module (hyper_client.rs):
- Lazy-initialized hyper-util Client with preserve_header_case
- ProxyResponse enum wrapping both hyper::Response and reqwest::Response
behind a unified interface (status, headers, bytes, bytes_stream)
- send_request() builds requests with ordered HeaderMap + case map
Request handlers (handlers.rs):
- Switch from (HeaderMap, Json<Value>) extractors to raw
axum::extract::Request to preserve Extensions (containing the
HeaderCaseMap from the accept loop)
- Pass extensions through the forwarding chain
Forwarder (forwarder.rs):
- Remove HEADER_BLACKLIST array; replace with ordered header iteration
that preserves original header sequence and casing
- Build ordered_headers by iterating client headers, skipping only
auth/host/content-length, and inserting auth headers at the original
authorization position to maintain order
- Handle anthropic-beta (ensure claude-code-20250219 tag) and
anthropic-version (passthrough or default) inline during iteration
- Remove should_force_identity_encoding() — accept-encoding is now
transparently forwarded to upstream
- Use hyper client by default; fall back to reqwest only when an
HTTP/SOCKS5 proxy tunnel is configured
Provider adapters (adapter.rs, claude.rs, codex.rs, gemini.rs):
- Replace add_auth_headers(RequestBuilder) -> RequestBuilder with
get_auth_headers(AuthInfo) -> Vec<(HeaderName, HeaderValue)>
- Adapters now return header pairs instead of mutating a reqwest builder
- Claude adapter: merge Anthropic/ClaudeAuth/Bearer into single branch;
move Copilot fingerprint headers into get_auth_headers
Response processing (response_processor.rs):
- Add manual decompression (gzip/deflate/brotli via flate2 + brotli)
for non-streaming responses, since reqwest auto-decompression is now
disabled to allow accept-encoding passthrough
- Add compressed-SSE warning log for streaming responses
- Accept ProxyResponse instead of reqwest::Response
HTTP client (http_client.rs):
- Disable reqwest auto-decompression (.no_gzip/.no_brotli/.no_deflate)
on both global and per-provider clients
Streaming adapters (streaming.rs, streaming_responses.rs):
- Generalize stream error type from reqwest::Error to generic E: Error
Misc:
- log_codes.rs: add SRV-005 (ACCEPT_ERR) and SRV-006 (CONN_ERR)
- stream_check.rs: reformat copilot header lines
- transform.rs: fix trailing whitespace alignment
* fix(lint): resolve 35 clippy warnings across Rust codebase
Fix all clippy warnings reported by `cargo clippy --lib`:
- codex_config.rs: fix doc_overindented_list_items (3 spaces -> 2)
- commands/copilot.rs: inline format args in 2 log::error! calls
- commands/provider.rs: inline format args in 3 map_err closures
- proxy/hyper_client.rs: inline format arg in log::debug! call
- proxy/providers/copilot_auth.rs: inline format args in 16 locations
(log macros, format! in headers, error constructors)
- proxy/thinking_optimizer.rs: inline format args in 2 log::info! calls
- services/skill.rs: inline format args in log::debug! call
- services/webdav_sync.rs: inline format args in 6 format! calls
(version compat messages, download limit messages)
- services/webdav_sync/archive.rs: inline format args in 2 format! calls
- session_manager/providers/opencode.rs: inline format args in
source_path format!
All fixes use the clippy::uninlined_format_args suggestion pattern:
format!("msg: {}", var) -> format!("msg: {var}")
* deps(proxy): add raw HTTP write and native TLS cert dependencies
Add crates required for the raw TCP/TLS write path that bypasses
hyper's header encoder to preserve original header name casing:
- httparse: parse raw TCP peek bytes to capture header casings
- tokio-rustls + rustls: direct TLS connections for raw write path
- webpki-roots: Mozilla CA bundle baseline
- rustls-native-certs: load system keychain CAs (trusts proxy MITM
certificates from Clash, mitmproxy, etc.)
* fix(proxy): address code review feedback on response handling
Fixes from PR #1714 code review:
- Extract `read_decoded_body()` and `strip_entity_headers_for_rebuilt_body()`
in response_processor to properly clean content-encoding/content-length
headers after decompression
- Reuse `read_decoded_body()` in handlers.rs for Claude transform path,
ensuring compressed responses are decoded before format conversion
- Make `build_proxy_url_from_config()` public so forwarder can pass proxy
URL to the hyper raw write path
- Add `has_system_proxy_env()` utility with test coverage
- Add 50ms backoff after accept() failures in server.rs to prevent
tight-loop CPU spin on transient socket errors
* feat(proxy): implement raw TCP/TLS write with HTTP CONNECT tunnel
Rewrite hyper_client with a two-tier strategy for header case preservation:
Primary path (raw write):
- Peek raw TCP bytes in server.rs to capture OriginalHeaderCases before
hyper lowercases them
- Build raw HTTP/1.1 request bytes with exact original header name casing
- Write directly to TLS stream, then use WriteFilter to let hyper parse
the response while discarding its duplicate request writes
- Support HTTP CONNECT tunneling through upstream proxies, so header case
is preserved even when a proxy (Clash, V2Ray) is configured
Fallback path (hyper-util Client):
- Used when OriginalHeaderCases is empty or raw write fails
- Configured with title_case_headers(true) for best-effort casing
TLS improvements:
- Load native system certificates alongside webpki roots so proxy MITM
CAs (installed in system keychain) are trusted through CONNECT tunnels
Key types added:
- OriginalHeaderCases: maps lowercase name → original wire-casing bytes
- WriteFilter<S>: AsyncRead+AsyncWrite wrapper that discards writes
- connect_via_proxy(): HTTP CONNECT tunnel establishment
- ExtensionDebugMarker: diagnostic marker for extension chain debugging
* refactor(proxy): route requests through hyper with proxy-aware forwarding
Rework forwarder request dispatch to always prefer the hyper raw write
path (header case preservation) over reqwest:
Request routing:
- HTTP/HTTPS proxy: hyper raw write through CONNECT tunnel (case preserved)
- SOCKS5 proxy: reqwest fallback (CONNECT not supported for SOCKS5)
- No proxy: hyper raw write direct connection
Header handling improvements:
- Replace host header in-place at original position instead of
skip-and-append, preserving client's header ordering
- Preserve client's original accept-encoding for transparent passthrough;
only force identity encoding when transform path needs decompression
- Add should_force_identity_encoding() to centralize the decision
- Remove hardcoded 'br, gzip, deflate' override that masked client values
Proxy URL resolution (priority order):
1. Provider-specific proxy config (if enabled)
2. Global proxy URL configured in CC Switch
3. Direct connection (no proxy)
* chore(proxy): remove dead code, redundant tests and debug scaffolding
- Inline should_force_identity_encoding() (was just `needs_transform`)
and delete its 5 test cases
- Remove ExtensionDebugMarker diagnostic type
- Remove unused has_system_proxy_env() and its test
- Remove strip_entity_headers test
- Simplify hyper path: remove redundant is_socks_proxy ternary
- Update hyper_client module doc to reflect CONNECT tunnel support
* fix(proxy): block direct-connect fallback and complete CONNECT tunnel support
* feat(hooks): improve proxy requirement warnings with specific reasons
- Remove redundant OpenAI format hint toast messages
- Add detailed reason detection for proxy requirements (OpenAI Chat, OpenAI Responses, full URL mode)
- Update i18n files with new reason-specific keys
* style(*): format code with prettier
- Remove extra whitespace in http_client.rs
- Fix formatting issues in useProviderActions.ts
* fix(proxy): post-merge fixes for forward return type and clippy warnings
- Restore forward() return type to (ProxyResponse, Option<String>)
to pass claude_api_format through to callers
- Inline format args in log::warn! macro (clippy::uninlined_format_args)
- Suppress too_many_arguments for check_claude_stream
* refactor(proxy): preserve original header wire order and add non-streaming body timeout
- Rewrite build_raw_request to emit headers in original
client-sent sequence instead of hash-map order
- Remove unused OriginalHeaderCases::get_all method
- Add body_timeout to read_decoded_body to prevent
requests hanging when upstream stalls after headers
|
||
|
Zhou Mengze
|
8d5f72757e |
fix: 修复 Copilot 作为 Claude 时 OpenAI 模型的 Responses 分流 (#1735)
* fix: route copilot claude openai models to responses * fix(i18n): add copilotProxyHint translation key for all locales The copilotProxyHint message was using inline defaultValue with Chinese text, which would show Chinese to English and Japanese users. Added proper translation keys in zh/en/ja locale files and removed the hardcoded defaultValue fallback. --------- Co-authored-by: Jason <farion1231@gmail.com> |
||
|
Dex Miller
|
8cae7b7b73 |
feat(proxy): add full URL mode and refactor endpoint rewriting (#1561)
* feat(proxy): add full URL mode and refactor endpoint rewriting - Add `isFullUrl` provider meta to treat base_url as complete API endpoint - Remove hardcoded `?beta=true` from Claude adapter, pass through from client - Refactor forwarder endpoint rewriting with proper query string handling - Block provider switching when proxy is required but not running - Add full URL toggle UI in endpoint field with i18n (zh/en/ja) * refactor(proxy): remove beta query handling * fix(proxy): strip beta query when rewriting Claude endpoints * feat(codex): complete full URL support * refactor(ui): refine full URL endpoint hint |
||
|
Jason
|
82c75de51c |
fix(copilot): unify request fingerprint across all Copilot API calls
- Make header constants in copilot_auth.rs public, add COPILOT_INTEGRATION_ID - Unify User-Agent across 4 internal methods (eliminate "CC-Switch" leakage) and version string - claude.rs add_auth_headers now references shared constants, adds user-agent / api-version / openai-intent - forwarder.rs filters all 6 fixed fingerprint headers for Copilot requests to prevent reqwest append duplication - stream_check.rs health check pipeline aligned with new fingerprint |
||
|
Zhou Mengze
|
8ccfbd36d6 |
feat(copilot): add GitHub Copilot reverse proxy support (#930)
* refactor(toolsearch): replace binary patch with ENABLE_TOOL_SEARCH env var toggle
- Remove toolsearch_patch.rs binary patching mechanism (~590 lines)
- Delete `toolsearch_patch.rs` and `commands/toolsearch.rs`
- Remove auto-patch startup logic and command registration from lib.rs
- Remove `tool_search_bypass` field from settings.rs
- Remove frontend settings ToggleRow, useSettings hook sync logic, and API methods
- Clean up zh/en/ja i18n keys (notifications + settings)
- Add ENABLE_TOOL_SEARCH toggle to Claude provider form
- Add checkbox in CommonConfigEditor.tsx (alongside teammates toggle)
- When enabled, writes `"env": { "ENABLE_TOOL_SEARCH": "true" }`
- When disabled, removes the key; takes effect on provider switch
- Add zh/en/ja i18n key: `claudeConfig.enableToolSearch`
Claude Code 2.1.76+ natively supports this env var, eliminating the need for binary patching.
* feat(claude): add effortLevel high toggle to provider form
- Add "high-effort thinking" checkbox to Claude provider config form
- When checked, writes `"effortLevel": "high"`; when unchecked, removes the field
- Add zh/en/ja i18n translations
* refactor(claude): remove deprecated alwaysThinking toggle
- Claude Code now enables extended thinking by default; alwaysThinkingEnabled is a no-op
- Thinking control is now handled via effortLevel (added in prior commit)
- Remove state, switch case, and checkbox UI from CommonConfigEditor
- Clean up alwaysThinking i18n keys across zh/en/ja locales
* feat(opencode): add setCacheKey: true to all provider presets
- Add setCacheKey: true to options in all 33 regular presets
- Add setCacheKey: true to OPENCODE_DEFAULT_CONFIG for custom providers
- Exclude 2 OMO presets (Oh My OpenCode / Slim) which have their own config mechanism
Closes #1523
* fix(codex): resolve 1M context window toggle causing MCP editor flicker
- Add localValueRef to short-circuit duplicate CodeMirror updateListener callbacks,
breaking the React state → CodeMirror → stale onChange → React state feedback loop
- Use localValueRef.current in handleContextWindowToggle and handleCompactLimitChange
to avoid stale closure reads
- Change compact limit input from type="number" to type="text" with inputMode="numeric"
to remove unnecessary spinner buttons
* feat(codex): add 1M context window toggle utilities and i18n keys
- Add extractCodexTopLevelInt, setCodexTopLevelInt, removeCodexTopLevelField
TOML helpers in providerConfigUtils.ts
- Add i18n keys for contextWindow1M, autoCompactLimit in zh/en/ja locales
* feat(claude): collapse model mapping fields by default
- Wrap 5 model mapping inputs in a Collapsible, collapsed by default
- Auto-expand when any model value is present (including preset-filled)
- Show hint text when collapsed explaining most users need no config
- Add zh/en/ja i18n keys for toggle label and collapsed hint
- Use variant={null} to avoid ghost button hover style clash in dark mode
* feat(claude): merge advanced fields into single collapsible section
- Merge API format, auth field, and model mapping into a unified "Advanced Options" collapsible
- Extend smart-expand logic to detect non-default values across all advanced fields
- Preserve model mapping sub-header and hint with a separator line
- Update zh/en/ja i18n keys (advancedOptionsToggle, advancedOptionsHint, modelMappingLabel, modelMappingHint)
* feat(copilot): add GitHub Copilot reverse proxy support
Add GitHub Copilot as a Claude provider variant with OAuth device code
authentication and Anthropic ↔ OpenAI format transformation.
Backend:
- Add CopilotAuthManager for GitHub OAuth device code flow
- Implement Copilot token auto-refresh (60s before expiry)
- Persist GitHub token to ~/.cc-switch/copilot_auth.json
- Add ProviderType::GitHubCopilot and AuthStrategy::GitHubCopilot
- Modify forwarder to use /chat/completions for Copilot
- Add Copilot-specific headers (Editor-Version, Editor-Plugin-Version)
Frontend:
- Add CopilotAuthSection component for OAuth UI
- Add useCopilotAuth hook for OAuth state management
- Auto-copy user code to clipboard and open browser
- Use 8-second polling interval to avoid GitHub rate limits
- Skip API Key validation for Copilot providers
- Add GitHub Copilot preset with claude-sonnet-4 model
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
* fix(copilot): remove is_expired() calls from tests
Remove references to deleted is_expired() method in test code.
Only is_expiring_soon() is needed for token refresh logic.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
* feat(copilot): add real-time model listing from Copilot API
- Add fetch_models() to CopilotAuthManager calling GET /models endpoint
- Add copilot_get_models Tauri command
- Add copilotGetModels() frontend API wrapper
- Modify ClaudeFormFields to show model dropdown for Copilot providers
- Fetches available models on component mount when isCopilotPreset
- Groups models by vendor (Anthropic, OpenAI, Google, etc.)
- Input + dropdown button combo allows both manual entry and selection
- Non-Copilot providers keep original plain Input behavior
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(copilot): add usage query integration
- Add Copilot usage API integration (fetch_usage method)
- Add copilot_get_usage Tauri command
- Add GitHub Copilot template in usage query modal
- Unify naming: copilot → github_copilot
- Add constants management (TEMPLATE_TYPES, PROVIDER_TYPES)
- Improve error handling with detailed error messages
- Add database migration (v5 → v6) for template type update
- Add i18n translations (zh, en, ja)
- Improve type safety with TemplateType
- Apply code formatting (cargo fmt, prettier)
* 修复github 登录和注销问题 ，模型选择问题
* feat(copilot): add multi-account support for GitHub Copilot
- Add multi-account storage structure with v1 to v2 migration
- Add per-account token caching and auto-refresh
- Add new Tauri commands for account management
- Integrate account selection in Proxy forwarder
- Add account selection UI in CopilotAuthSection
- Save githubAccountId to ProviderMeta
- Add i18n translations for multi-account features (zh/en/ja)
* 修复用量查询Reset字段出现多余字符
* refactor(auth-binding): introduce generic provider auth binding primitives
- add shared authBinding types in Rust and TypeScript while keeping githubAccountId as a compatibility field\n- resolve Copilot token, models, and usage through provider-bound account lookup instead of only the implicit default account\n- fix the Unix build regression in settings.rs by restoring std::io::Write for write_all()\n- remove the accidental .github ignore entry and drop leftover Copilot form debug logs\n- keep the first migration step non-breaking by writing both authBinding and the legacy githubAccountId field from the form
* refactor(auth-service): add managed auth command surface and explicit default account state
- introduce generic managed auth commands and frontend auth API wrappers for provider-scoped login, status, account listing, removal, logout, and default-account selection\n- store an explicit Copilot default_account_id instead of relying on HashMap iteration order, and use it consistently for fallback token/model/usage resolution\n- sort managed accounts deterministically and surface default-account state to the UI\n- refactor the Copilot form hook to wrap a generic useManagedAuth implementation while preserving the existing component contract\n- add default-account controls to the Copilot auth section and extend Copilot auth status serialization/tests for the new state
* feat(auth-center): add a dedicated settings entrypoint for managed OAuth accounts
- add an Auth Center tab to Settings so managed OAuth accounts are no longer hidden inside individual provider forms\n- introduce a first AuthCenterPanel that hosts GitHub Copilot account management as the initial managed auth provider\n- keep the provider form experience intact while establishing a global account-management surface for future providers such as OpenAI\n- validate that the new settings tab works cleanly with the generic managed auth hook and existing Copilot account controls
* feat(add-provider): expose managed OAuth sources alongside universal providers
- add an OAuth tab to the Add Provider flow so managed auth sources sit beside app-specific and universal providers\n- reuse the new Auth Center panel inside the dialog, keeping account management discoverable during provider creation\n- make the dialog footer adapt to the OAuth tab so account setup does not pretend to create a provider directly\n- align the add-provider UX with the new architecture where OAuth accounts are global assets and providers bind to them later
* fix(auth-reliability): harden managed auth persistence and refresh behavior
- replace direct Copilot auth store writes with private temp-file writes and atomic rename semantics, and document the local token storage limitation\n- add per-account refresh locks plus a double-check path so concurrent requests do not stampede GitHub token refresh\n- surface legacy migration failures through auth status, expose them in the UI, and add translated copy for the new account-state labels\n- stop writing the legacy githubAccountId field from the provider form while keeping compatibility reads in place\n- add logout error recovery and Copilot model-load toasts so auth failures are no longer silently swallowed
* refactor(copilot-detection): prefer provider type before URL fallbacks
- update forwarder endpoint rewriting to treat providerType as the primary GitHub Copilot signal\n- keep githubcopilot.com string matching only as a compatibility fallback for older provider records without providerType\n- reduce one more path where Copilot behavior depended purely on URL heuristics
* fix(copilot-auth): add cancel button to error state in CopilotAuthSection
- 错误状态下仅有"重试"按钮，用户无法退出（如不可恢复的 403 未订阅错误）
- 新增"取消"按钮，复用已有的 cancelAuth 逻辑重置为 idle 状态
* 修复打包后github账号头像显示异常
* 修复github copilot 来源的模型测试报错
* feat(copilot-preset): add default model presets for GitHub Copilot
- 补充 Copilot 预设的默认模型配置，用户选完预设即可直接使用
- ANTHROPIC_MODEL: claude-opus-4.6
- ANTHROPIC_DEFAULT_HAIKU_MODEL: claude-haiku-4.5
- ANTHROPIC_DEFAULT_SONNET_MODEL: claude-sonnet-4.6
- ANTHROPIC_DEFAULT_OPUS_MODEL: claude-opus-4.6
---------
Co-authored-by: Jason <farion1231@gmail.com>
Co-authored-by: 周梦泽 <mengze.zhou@dafeng-tech.com>
Co-authored-by: Claude Haiku 4.5 <noreply@anthropic.com>
|
||
|
Jason
|
28afbea917 |
fix(proxy): enable gzip compression for non-streaming proxy requests
Non-streaming requests were forced to use `Accept-Encoding: identity`, preventing upstream response compression and increasing bandwidth usage. Now only streaming requests conservatively keep `identity` to avoid decompression errors on interrupted SSE streams. Non-streaming requests let reqwest auto-negotiate gzip and transparently decompress responses. |
||
|
Jason
|
1573474e3a | Fix proxy forwarder failure logs | ||
|
Jason
|
a30e2096bb |
feat: add OpenAI Responses API format conversion (api_format = "openai_responses")
Support Anthropic ↔ OpenAI Responses API format conversion alongside existing Chat Completions conversion. The Responses API uses a flat input/output structure with lifted function_call/function_call_output items and named SSE lifecycle events. |
||
|
Keith Yu
|
8217bfff50 |
feat: add Bedrock request optimizer (PRE-SEND thinking + cache injection) (#1301)
* feat: add Bedrock request optimizer (PRE-SEND thinking + cache injection) Add a PRE-SEND request optimizer that enhances Bedrock API requests before forwarding, complementing the existing POST-ERROR rectifier system. New modules: - thinking_optimizer: 3-path model detection (adaptive/legacy/skip) - Opus 4.6/Sonnet 4.6: adaptive thinking + effort max + 1M context beta - Legacy models: inject extended thinking with max budget - Haiku: skip (no modification) - cache_injector: auto-inject cache_control breakpoints (max 4) - Injects at tools/system/assistant message positions - TTL upgrade for existing breakpoints (5m → 1h) Gate: only activates for Bedrock providers (CLAUDE_CODE_USE_BEDROCK=1) Config: stored in SQLite settings table, default OFF, user opt-in UI: new Optimizer section in RectifierConfigPanel with 3 toggles + TTL 18 unit tests covering all paths. Verified against live Bedrock API. * chore: remove docs/plans directory * fix: address code review findings for Bedrock request optimizer P0 fixes: - Replace hardcoded Chinese with i18n t() calls in optimizer panel, add translation keys to zh/en/ja locale files - Fix u64 underflow: max_tokens - 1 → max_tokens.saturating_sub(1) - Move optimizer from before retry loop to per-provider with body cloning, preventing Bedrock fields leaking to non-Bedrock providers P1 fixes: - Replace .map() side-effect pattern with idiomatic if-let (clippy) - Fix module alphabetical ordering in mod.rs - Add cache_ttl whitelist validation in set_optimizer_config - Remove #[allow(unused_assignments)] and dead budget decrement --------- Co-authored-by: Keith (via OpenClaw) <keithyt06@users.noreply.github.com> Co-authored-by: Jason <farion1231@gmail.com> |
||
|
Dex Miller
|
62fa5213bf |
feat(proxy): fix thinking rectifiers and resolve clippy warnings (#1005)
* feat(proxy): align thinking rectifiers and resolve clippy warnings - add thinking budget rectifier flow with single retry on anthropic budget errors - align thinking signature rectification behavior with adaptive-safe handling - expose requestThinkingBudget in settings/ui/i18n and default rectifier config to disabled - fix clippy warnings in model_mapper format args and RectifierConfig default derive * fix(proxy): thinking rectifiers |