- Buffer and publish observed upstream usage when apply patch transformation or translation encounters an error in Meta and xAI executors
- Add stream usage buffer helpers to report failure metrics with captured upstream token usage
Closes: #6427
- Update cloaking check to retain caller system instructions at the top level when a conversation begins with multiple consecutive user messages followed by assistant turns
Closes: #6426
- Update terminal user run check in Claude cloaking logic so conversations ending with a single user turn keep caller system instructions at the top level instead of relocating them into mid-conversation messages
Closes: #6423
- Detect terminal stream chunks and avoid recording client cancellations as execution failures once completion events have been delivered
Closes: #6421
- Pre-allocate `oauthToolAliases` in Claude and Kimi executor constructors so request copies created via `ForAPIKey` reuse the same store
- Replace struct-level mutex with package-level mutex for lazy store allocation to prevent copying mutexes by value
Closes: #6401
- Retain unknown-format `encrypted_content` during reasoning signature sanitization when compatibility mode is enabled
- Continue stripping empty signatures and known foreign provider signatures in compat mode
Closes: #6399
- Record reasoning effort from finalized upstream payload after cache helper processing across execution, streaming, compaction, and image requests
Closes: #6388
- Track pending completion state in OpenAI-to-Responses translator when item output is complete and a finish reason is received
- Synthesize terminal `[DONE]` event on clean EOF when response completion is pending instead of failing the stream
Closes: #6381
- Honor `prompt_cache_options.mode = "explicit"` to suppress automatic `cache_control` insertion while preserving client-defined cache breakpoints
- Strip `prompt_cache_options` from request payloads before forwarding upstream and during token counting
Closes: #6380
Replace Codex-specific response model APIs with shared model observation and remove redundant substitution warning throttling. Consolidate repeated Antigravity context-hash rejection messages into a single request-level log while preserving rejection details across index rebuilds.
- Track terminal chunks including finish reasons, stop messages, and completion events during streaming
- Commit replay settlements and publish observed usage instead of reporting stream failure when the client disconnects after a terminal chunk
Closes: #6376
- Buffer and assemble multi-line or split JSON chunks until a valid JSON payload is formed
- Intercept upstream backend error objects during streaming and surface them as terminal errors with appropriate status codes
Closes: #6357
- Track terminal connection errors on websocket session when upstream read loops fail or receive unexpected binary payloads
- Return recorded terminal errors immediately during session activation to prevent callers from blocking indefinitely after upstream disconnects
- Reset terminal error state when configuring new connections
Closes: #6354
- Add bounded in-memory store to retain Claude OAuth tool alias mappings keyed by message ID
- Restore alias mappings for thread continuation requests omitting tool declarations, returning a request-scoped not found error when state is missing
- Record tool aliases on execution and streaming response completion
Closes: #6346
- Add `claudeMidConversationSystemMessagesAtEnd` to detect consecutive user messages ending the message array
- Append forwarded system blocks to top-level `system` payload instead of inserting mid-conversation message turns when trailing user turns are present
Closes: #6336
- Add `FlushResponse` to prefer error-aware flushing and unwrap wrapped response writers
- Bypass Gin's void `Flush` while maintaining header accounting via `WriteHeaderNow` to keep transport errors observable
Closes: #6332
- Add `PayloadFinalizer` to apply configuration rules at the final serialization barrier
- Support decoding, modifying, and re-encoding Devin protobuf business fields
- Add multipart form-data payload normalization to JSON for media payload rules
Closes: #5067
- Allow early content streaming for OpenAI formats while preserving ordering behind queued tools
- Defer thought step termination and accumulate signature fragments for OpenAI Responses format
- Flush deferred reasoning step stops when closing open stream steps
Closes: #6306
- Add ASCII pre-filter to skip expensive gjson traversals for title helper and 1h TTL checks
- Check raw bytes for target keywords before initiating full JSON walks
- Fall back to full inspection when printable ASCII Unicode escapes are detected
Closes: #6291
- Pin local date to continuity context on the first request of a session
- Reuse pinned session date during cloaked date injection across execute and stream flows
- Prevent midnight calendar date flips from invalidating conversation prompt cache prefixes
Closes: #6282
Accept historical v8 config paths and request bodies while saving the
latest canonical layout. Preserve comments on scalar updates and keep v0
saves from migrating legacy-only files unnecessarily.
Move shared Codex, Claude, and xAI provider options under upstream so
they apply consistently to OAuth and API-key credentials. Migrate
historical OAuth paths, preserve OAuth-only header scope, and expose the
new upstream management API path.
- Fall back to top-level token usage when Codex response usage contains only service tier metadata
- Propagate parsed service tier while retaining top-level token counts
- Avoid early return during stream usage observation for chunks with zero token counts
Closes: #6261
- Allow connection count slack for concurrent wave dials to prevent flakiness under load
- Assert strictly against unpooled worst case instead of fragile lower bounds on connection count
Closes: #6259
- Track cumulative usage snapshots from `usageMetadata` and `cpaUsageMetadata` across stream chunks
- Defer terminal response event emission until usage frames arrive or the stream ends
- Map `MAX_TOKENS` finish reason to `response.incomplete` status and incomplete output item states
Closes: #6258
- Handle apply_patch custom tool call streaming deltas and snapshots for Responses API translation
- Track and resolve step indexes, function call identities, and error states across stream events
- Propagate apply_patch tool input errors and upstream failure states in stream and non-stream responses
xAI raised the minimum accepted x-grok-client-version on
cli-chat-proxy.grok.com, so every xAI OAuth chat request through the CLI
chat-proxy failed with HTTP 426 ("Your Grok CLI version (0.2.120) is
outdated"). /v1/models is not gated, so discovery looked healthy while
inference was dead.
Bump the pin to the current stable Grok CLI version (1.0.44) and record
the observed server floor in the constant's comment. Both
x-grok-client-version and the derived User-Agent ship from this one
constant.
Regression tests lock three things: the pinned version meets the known
server floor (red against 0.2.120), the two identity headers stay
derived from the same constant, and the per-auth `header:*` custom
header override still wins over the pin - the documented operator
escape hatch when xAI ratchets the floor again.
Closes#6249
Generated-by: GLM-5.3-Flash (ZCode)
- Pass target executor identity during Codex token counting and xAI request translation
- Skip tool integer normalization when target executor is Codex during compatibility translation
- Preserve number types in tool parameter schemas during token counting requests
- Return Bad Gateway error when Codex upstream stream closes before emitting any payload
- Allow failover to subsequent credentials on premature stream disconnect before output
- Map HTTP 408 Request Timeout status to server_error in base error response handlers
Closes: #6247
- Skip normalizing tool parameter number types to integer when the target executor is Codex or Codex WebSocket
- Remove tool integer type normalization from schema cleanup in native Codex execution paths to preserve reserved tool schemas
- Apply tool integer type normalization only for non-Codex upstream targets with Codex client User-Agents
Closes: #6244
- Select HTTP/2 or HTTP/1.1 transport dynamically based on TLS ALPN negotiation
- Route empty ALPN and HTTP/1.1 requests through a dedicated non-pooled transport reusing the handshaken connection
- Ensure uTLS connections are cleanly closed upon response completion or request failure
Closes: #6223
- Defer intervening non-tool messages until all batch tool outputs are emitted to keep outputs contiguous
- Apply responses input normalization across standard and streaming executor execution paths
Closes: #6231
- Detect Codex client requests via User-Agent and convert target numeric parameters to integer types
- Support schemas across OpenAI functions, Claude input schema, Gemini declarations, and namespace tools
- Apply normalization during executor payload processing, multi-agent request translation, and WebSocket streaming
Closes: #6237
- Enable multi-agent input rewriting when model compatibility mode is active, even if `optimize-multi-agent-v2` is disabled
- Ensure `agent_message` items are converted into portable user messages for third-party endpoints under API key configurations
Closes: #6233
- Forward unmapped Claude OAuth MCP tool aliases unchanged instead of returning an error
- Log a warning when no request-local tool match is found to prevent stream termination
Closes: #6208
