* refactor: consolidate relay protocol converters
* refactor relayconvert text converters
* feat: refine relay converters and advanced custom routing
* refactor: enhance logging and add thought signature handling for Gemini requests
* refactor: enhance channel cache and pricing endpoint handling for advanced custom models
* feat: preserve billing usage semantics
* feat: add protocol-aware billing usage
* Delete useless files
* chore: update action versions in workflow files
* chore: update Docker action versions in workflow files
* fix: harden billing usage settlement and hot-path route matching
- estimate Gemini completion tokens locally when billable usageMetadata is
prompt-only but output content was received (e.g. client aborts the stream
before the final chunk), and rebuild the attached billing_usage as estimated
so settlement does not bill zero output tokens
- guard NewClaudeMessagesBillingUsage against all-zero ClaudeUsage, matching
the OpenAI/Gemini constructors, so a zero billing_usage cannot override a
non-zero top-level usage during settlement
- cache compiled advanced-custom route model regexes; they run on the request
hot path and were recompiled per request
- move the effectiveBillingUsage remap to PostTextConsumeQuota only, and
document that calculateTextQuotaSummary expects remapped usage
- document the updatePricingLock -> channelSyncLock lock ordering that
InitChannelCache/CacheUpdateChannel rely on, and the aux-struct pitfall in
GeminiChatResponse.UnmarshalJSON
* fix(openai): harden Chat-to-Responses compatibility
Add a shared Responses-to-Chat stream state machine and use it from the OpenAI relay path. Preserve assistant text alongside tool calls, bind tool argument deltas by output_index, map incomplete finish reasons, support reasoning/custom tool events, and buffer upstream SSE for non-stream Chat clients.
Add deterministic service tests and relay SSE tests for the conversion path.
Related to #5745.
* refactor: rename openaicompat to relayconvert for improved clarity
* feat(gemini): support responses request conversion
* feat: add responses to chat conversion support
* fix: harden responses chat conversion edge cases
- Add StreamStatus type (relay/common) to track stream end reason
(done/timeout/client_gone/scanner_error/eof/panic/ping_fail) and
accumulate soft errors during streaming via sync.Once + sync.Mutex.
- Add StreamResult (relay/helper) as the callback interface: adapters
call sr.Error() for soft errors, sr.Stop() for fatal, sr.Done() for
normal completion. No early-return problem — multiple errors per chunk
are naturally supported.
- Refactor StreamScannerHandler callback from func(string) bool to
func(string, *StreamResult). All 9 channel adapters updated.
- Write stream_status into log other JSON field (admin-only) with
status ok/error, end_reason, error_count, and error messages.
- Frontend: display stream status in log detail expansion for admins.
- Remove claude-instant-1.2, claude-2, claude-2.0, claude-2.1 from model lists
- Remove /v1/complete endpoint support (legacy completion API)
- Remove RequestModeCompletion and related code paths
- Simplify handler functions by removing requestMode parameter
- Update all channel adaptors that referenced claude handlers
- Add model to Claude ModelList
- Add model ratio (0.5, $1/1M input tokens)
- Add completion ratio support (5x, $5/1M output tokens)
- Add cache read ratio (0.1, $0.10/1M tokens)
- Add cache write ratio (1.25, $1.25/1M tokens)
Model specs:
- Context window: 200K tokens
- Max output: 64K tokens
- Release date: October 1, 2025
- Introduced new OpenAI text models in `common/model.go`.
- Added `IsOpenAITextModel` function to check for OpenAI text models.
- Refactored token estimation methods across various channels to use estimated prompt tokens instead of direct prompt token counts.
- Updated related functions and structures to accommodate the new token estimation approach, enhancing overall token management.
Calcium-Ion