* fix(session): 修复session log模式下子Agent token统计遗漏
collect_jsonl_files() 只扫描了两层目录，遗漏了子Agent的JSONL日志文件，
导致子Agent的独立token使用数据完全未统计到session费用中。
（仅影响session log模式，proxy代理模式不受影响）
* refactor(session): optimize collect_jsonl_files logic
- Replace two independent if statements with if-else for mutually exclusive conditions
- Remove unnecessary clone() when pushing file paths
- Add clarifying comments for main session vs subagent files
- Apply cargo fmt for consistent formatting
Performance improvement: Eliminates redundant clone() operations when
processing .jsonl files, as a path cannot be both a file and a directory.
---------
Co-authored-by: Jason <farion1231@gmail.com>
- Mark `should_force_identity_encoding` as test-only.
- Keep runtime forwarding behavior unchanged.
- Verified with local CI checks and no-bundle Tauri build.
- 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
- Add `get_codex_oauth_models` Tauri command reusing the managed OAuth
access token to hit `chatgpt.com/backend-api/codex/models`; HTTP and
multi-shape JSON parsing live in `services::codex_oauth_models` so the
command stays thin.
- Unify the Claude form's "fetch models" button across normal / Copilot /
Codex OAuth presets, drop the auto-load effect for Copilot in favor of
explicit clicks, and guard against stale responses with a requestId ref.
- Add Vitest coverage for both Copilot and Codex OAuth paths asserting no
request on mount and the correct account id on click; add Rust unit
tests for the four model-list payload shapes.
When proxy takeover is active, write per-role *_MODEL aliases for routing
and *_MODEL_NAME with the upstream provider's real model name so the
Claude Code model menu reflects the active provider instead of stale
display names from a previous switch. Preserves the [1M] capability marker
for Sonnet/Opus, and strips it from implicit display names.
* model pricing routing: extend prefix-match families (gpt-/o1-o5/
gemini-/deepseek-/qwen-/glm-/kimi-/minimax-) with per-family dash
thresholds so short base IDs like gpt-5 no longer mis-match
gpt-5-mini; strip ISO and 8-digit date suffixes via UTF-8-safe
byte matching so claude-haiku-4-5-20251001 falls back to
claude-haiku-4-5 pricing
* SSE collector: SseUsageFinishGuard (RAII) guarantees finish() on
early return or panic; AtomicBool fast path lets push() skip the
Mutex once first-event time is recorded
* validation: shared validate_cost_multiplier / validate_pricing_source
helpers across DAO and service layers; PRICING_SOURCE_RESPONSE /
PRICING_SOURCE_REQUEST constants replace string literals; price
fields in update_model_pricing now reject empty / non-decimal /
negative input before INSERT
* backfill: add backfill_missing_usage_costs_for_model so a single
price edit only scans matching rows instead of the full log table;
startup backfill remains full-scan
* session_usage{,_codex,_gemini}: share find_model_pricing helper from
usage_stats; metadata_modified_nanos centralizes mtime precision
* frontend: NON_NEGATIVE_DECIMAL_REGEX + isNonNegativeDecimalString
replace three copies of the same multiplier regex; isUnpricedUsage
surfaces zero-cost rows that have usage tokens (cached per row to
avoid double evaluation); invalidate usageKeys.all on pricing mutate
so backfilled rows refresh
* 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
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.
claude.rs and gemini.rs each defined an identical `hv` closure that wrapped
`HeaderValue::from_str` into a ProxyError::AuthError result, and codex.rs
spelled the same conversion out inline. /simplify reviewers flagged this
as drift-prone copy-paste.
Move the conversion into a single `pub fn auth_header_value` in
providers/adapter.rs and have the three adapters import it locally. Same
error wording everywhere, one place to update if HeaderValue semantics
ever change.
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.
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.
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".
The Chat-Completions transformer used to forward tool_choice verbatim,
but the two APIs disagree on shape:
Anthropic "any" | {"type":"tool","name":"X"}
OpenAI Chat "required" | {"type":"function","function":{"name":"X"}}
Pass-through made the upstream return 400 for any tool-forcing client
(Claude Code, Copilot, etc.). The Responses-API transformer already had
the equivalent map_tool_choice_to_responses helper; this commit adds a
sibling map_tool_choice_to_chat with the chat-specific *nested* function
selector and five regression tests covering string / object × any /
auto / none / tool.
The two helpers are intentionally not merged: the difference between
flat and nested function selectors is exactly what the original bug
was, so keeping them as separate self-documenting functions reduces the
chance of the same regression returning.
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.
Two related drift bugs in the takeover state machine:
1. The "already taken over?" guard used has_backup OR live_taken_over, so
either condition alone would short-circuit. After a user or anomalous
flow restores Live manually the backup row still made set_takeover
return success, leaving the UI claiming takeover while requests bypass
the local proxy. Tighten to AND so the rebuild branch repairs the two
"split brain" states (backup-only and placeholder-only).
2. Disabling takeover called the bare restore_live_config_for_app, which
silently Ok()s when the backup is missing. If the backup was lost while
Live still held proxy placeholders (PROXY_MANAGED token / local proxy
URL), the client config was left broken with no error surfaced. Route
the disable path through the already-existing
restore_live_config_for_app_with_fallback (backup → SSOT → cleanup).
The line 354 takeover-failure rollback intentionally keeps the bare
variant since that path must preserve the backup for retry.
split('/') strips the slashes, so find(|s| s.starts_with("models/")) never
matched any segment and request_model fell through to "unknown" for every
Gemini call, poisoning usage records, per-request billing, and logs.
Match the literal "models" segment and take the next one, stripping any
:action suffix and query string. The extraction is now a pub(crate) free
function so it can be unit-tested directly; seven regression tests cover
action suffixes, dotted versions, the /gemini/ proxy prefix, query
strings, the bare list endpoint, and missing-segment paths.
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.
- Split CostCalculator into per-app cache semantics: Anthropic's
input_tokens is already fresh input, while Codex/Gemini include
cached tokens in their prompt count. The old shared formula
double-subtracted cache_read for Claude, under-billing input cost.
- Backfill now reads cost_multiplier from the per-log snapshot column
instead of re-querying providers.meta, so historical rows are no
longer rewritten with the current multiplier.
- Move the "pricing not found" warn out of find_model_pricing_row;
emit it only when a brand new log is written, and skip placeholder
models (unknown / empty / null / none) entirely.
- Broaden model id normalization: strip namespace prefixes
(anthropic./openai./global./bedrock.), bedrock-style -vN suffixes,
reasoning effort suffixes (-low/-medium/-high/-xhigh/-minimal),
Claude Desktop's claude-<non-anthropic> wrapper, dot-to-dash for
Claude, and try a LIKE prefix match for Claude short route ids
(e.g. claude-haiku-4-5 -> claude-haiku-4-5-20251001).
- Fall back to request_model when the stored model is missing, so
early Codex session rows with model=unknown can still be priced.
- 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.
Adapt to Claude Desktop 1.6259.1+ fail-all validation which only
accepts claude-(sonnet|opus|haiku)-* route IDs. Branded model names
(DeepSeek, Kimi, GLM, etc.) now live in a new labelOverride field
instead of being embedded in route IDs.
- Backend auto-repairs legacy unsafe routes to the next free
sonnet/opus/haiku slot instead of erroring
- Frontend swaps the free-form route input for a role dropdown plus
menu display name field
- Add CLAUDE_DESKTOP_ROLE_ROUTE_IDS as the single source of truth
for role-to-route mapping; presets and form both consume it
- Drop the dead displayName alias on ClaudeDesktopModelRoute and the
ineffective /v1/models display_name injection (UI ignores it)
- Update i18n (en/ja/zh) and form focus test for the new fields
- Normalize OpenAI/Gemini input_tokens semantics in SQL via the new
fresh_input_sql helper (cache_read subtracted at query time, no data
migration). Recovers correct cache hit rates for Codex/Gemini.
- Add get_usage_summary_by_app endpoint for per-app split (single
UNION ALL + GROUP BY, avoids N+1).
- Replace UsageSummaryCards + AppBreakdownRail with a single
filter-driven UsageHero card; clicking a filter button now truly
changes the displayed numbers and the title accent color.
- Tighten KNOWN_APP_TYPES to the 3 app_types whose token data is
reliably collected (claude/codex/gemini); hide claude-desktop,
hermes, opencode, openclaw filter buttons and i18n keys.
- Flag cache_creation as N/A for OpenAI-style protocols (Codex,
Gemini); show a "partial" tooltip when the All view mixes both
protocol families.
- Derive route keys from the upstream model name (pass-through style)
instead of fixed Claude aliases, and translate the legacy [1M] suffix
into the supports1m field at the import boundary. Three Claude aliases
mapped to the same upstream now collapse to a single route (e.g.
MiniMax-M2 across SONNET/OPUS/HAIKU env produces one
claude-MiniMax-M2 -> MiniMax-M2 row), with [1M] OR-aggregated.
- Add an import-time safety net that rebuilds claude-desktop-official
when missing, so users who deleted it can recover via the normal
import button without losing customizations on other providers.
- Hide API key and endpoint URL inputs in the official provider edit
form to mirror Claude Code's behavior and prevent user confusion.
- Reword the empty-state import button label for clarity.
inferenceModels entries now emit {name, supports1m: true} objects when
1M is enabled (plain strings otherwise), instead of appending a " [1M]"
suffix to model IDs. Route IDs and upstream model IDs are stored
verbatim; the suffix is rejected on input rather than silently stripped,
and proxy request mapping now requires an exact route_id match.
Claude Desktop's new model menu reads model IDs directly and ignores the
display_name field, so a separate displayName slot added UI noise without
any product value. Collapse the routeId / model / displayName tuple down
to routeId / model, and let the route ID carry the user-visible name
through a non-editable claude- prefix rendered next to the input.
Drop display_name from ClaudeDesktopModelRoute, ClaudeDesktopDefaultRoute,
and ResolvedModelRoute on the Rust side plus the matching TS interfaces,
stop emitting it in /v1/models responses, derive route IDs from upstream
model IDs when picked via the model dropdown, and update zh/en/ja copy to
describe the new two-field layout.
Add an "Only Official Website" header to the three READMEs, an
About panel button, and a tray menu entry — all pointing to
ccswitch.io. Consolidates brand and SEO signals on the canonical
domain across docs, GUI, and system tray.
- 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>`.
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.
- 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
Claude Desktop strips the [1M] suffix from model IDs when sending
requests, causing route lookup to fail with "model route is not
configured". Fall back to base-name comparison when exact match misses.
- services/proxy.rs: collapse 10 repeated `OpenCode | OpenClaw | Hermes |
ClaudeDesktop` match arms into `_` fallthroughs.
- claude_desktop_config.rs: extract a `with_rollback` closure shared by
apply_provider_to_paths and restore_official_at_paths.
- useProviderActions.ts: replace the triple-nested ternary picking the
switch-success toast message with a flat let/if/else block.
Net -36 lines. No behavior change; cargo test and pnpm typecheck pass.
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.
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.
Anthropic SDK assigns distinct semantics to the two env vars:
- ANTHROPIC_API_KEY -> x-api-key
- ANTHROPIC_AUTH_TOKEN -> Authorization: Bearer
The Claude adapter previously collapsed both into AuthStrategy::Anthropic
and then emitted Authorization: Bearer regardless, breaking strict
Anthropic-protocol endpoints (Anthropic official, Cloudflare AI Gateway,
OpenCode Go, DashScope) and silently overriding the user's intended auth
scheme.
- claude::extract_auth: infer strategy from env var name
(ANTHROPIC_AUTH_TOKEN -> ClaudeAuth, ANTHROPIC_API_KEY -> Anthropic),
matching the precedence already used by extract_key.
- claude::get_auth_headers: split the Anthropic arm so it emits
x-api-key, while ClaudeAuth and Bearer continue to use Bearer.
- stream_check: reuse ClaudeAdapter::get_auth_headers as the single
source of truth, replacing the prior "always Bearer + maybe x-api-key"
double injection that produced auth conflicts and false-negative
health checks.
- Cover each strategy -> header mapping and env-var precedence with
new unit tests in claude.rs.
Refs #2368, #2380
Claude Code injects a dynamic `x-anthropic-billing-header` line at the
start of `system` content. Its rotating `cch=` token was forwarded into
OpenAI Responses `instructions` and Chat system messages, which broke
upstream prefix prompt cache reuse — a stable ~95k-token prefix was
getting re-charged on every request.
Strip only the leading occurrence in both anthropic_to_openai and
anthropic_to_responses; later occurrences are preserved so user-authored
prompt text containing the same string is not lost.
Hermes aggregates all in-process API calls into a single sessions row
with the `model` field locked to the initial model, so the usage
dashboard cannot cleanly surface per-call billing context. Two rounds
of UI workarounds (raw mapping, then `<model> @ <host>` display) did
not resolve the user-facing confusion, so the whole tracking
integration is dropped for now.
Removes session_usage_hermes service (and its 17 tests), sync wiring
in commands/usage.rs and lib.rs, _hermes_session/hermes_session
entries in usage_stats SQL (provider_name_coalesce CASE and
effective_usage_log_filter IN clause), frontend Tab/banner/dropdown/
icon entries, and four i18n keys per locale.
Hermes app integration outside usage tracking (proxy routing,
session manager, config) is preserved. Pre-existing hermes rows in
proxy_request_logs are left as orphans — filtered out by the
updated SQL and never surfaced in the UI.
Zhipu's `data.limits[]` returns 1 entry for legacy plans (subscribed
before 2026-02-12) and 2 entries for current plans. Previously every
TOKENS_LIMIT entry was hardcoded as `five_hour`, so the weekly bucket
was rendered with the 5-hour i18n label.
Sort TOKENS_LIMIT entries by nextResetTime ascending and assign
`five_hour` to index 0, `weekly_limit` to index 1. Legacy plans
naturally degrade to a single five_hour tier.
Also harden the parser: case-insensitive type match (defends against
upstream casing changes), reuse TIER_FIVE_HOUR/TIER_WEEKLY_LIMIT
constants, and add 8 unit tests covering both plan shapes plus
defensive edge cases.
* fix(dashscope): enhance usage parsing robustness to prevent VSCode crashes
Enhanced build_anthropic_usage_from_responses() to handle null, missing, empty,
and partial usage fields gracefully. This prevents VSCode Extension crashes with
"Cannot read properties of null (reading 'output_tokens')" when connecting to
DashScope (Alibaba Cloud Bailian) models.
Changes:
- Added defensive null checks and empty object detection
- Implemented OpenAI field name fallbacks (prompt_tokens/completion_tokens)
- Added comprehensive logging for malformed usage scenarios
- Fixed streaming SSE event handlers with null-safe usage access
- Preserved cache token fields even when input/output tokens are missing
This ensures the proxy never crashes on malformed Responses API usage objects,
returning valid Anthropic-compatible usage structures (input_tokens/output_tokens)
in all cases.
* fix(proxy): tighten Responses API usage fix per review
- Drop redundant fallback in streaming.rs Chat Completions path; the
existing if-let-Some guard already prevents usage:null, so the extra
layer was dead code and caused a fmt-breaking indentation issue.
- Demote partial-usage warn to debug. Streaming chunks legitimately
arrive with partial token counts and the warn-level log was noisy.
- Rewrite CHANGELOG entry: reference #2422, broaden scope from
DashScope-only to all api_format=openai_responses users (Codex OAuth
is the strongest signal; DashScope compatible-mode/v1/responses is
the original report).
- cargo fmt to clear 12 formatting differences vs main.
---------
Co-authored-by: Jason <farion1231@gmail.com>
LaoYueHanNi