- 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outdated").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
- Translate `response.failed` and `interaction.failed` events across Claude, Gemini, OpenAI Chat, and Responses formats
- Lazily emit `interaction.created` in Devin executor to allow clean HTTP error status propagation on immediate
Closes: #6204
- Track auto-refresh jobs with registration epochs to prevent stale or phantom pending states
- Enforce bounded timeouts for Antigravity token refresh and project discovery
- Manage Antigravity credits refresh tasks with epoch validation and lifecycle cancellation
Closes: #6199
- Add `Path` field to model execution requests and plugin interceptor responses
- Propagate custom request paths through execution metadata
- Allow image models during execution when entry or exit protocol is `openai-image`
Closes: #6196
- Add `isClaudeSonnet55Model` helper and prevent Sonnet 5 matching on Sonnet 5.5 prefixes
- Include Claude Sonnet 5.5 in progress display checks
Closes: #6193
Use Home credential options as authoritative model capability
configuration for compat handling and prompt cache behavior.
Expose quota provider operations through the public plugin host API.
- Extract `plan_type` from JWT claims and default missing values to `free`
- Include `plan_type` in token data, token storage, auth attributes, and file synthesis
- Ensure `plan_type` is maintained across token refresh flows
- Preserve empty map allocations during auth object cloning
- Rewrite `tool.name` of mid-conversation `tool_addition`/`tool_removal` blocks with a `tool_reference` to the same MCP alias as `tools[]`
- Rewrite `tool.definition.name` of inline `tool_definition` additions that redefine a declared custom tool
- Apply the same rewrite in the batched-edits and legacy remap paths
- Prevent upstream `references unknown tool` 400s for cloaked requests using mid-conversation tool changes
Closes: #6174
- Add `SanitizeMetaWebSearchTools` to remove `search_content_types` from `web_search` tool definitions
- Support sanitizing nested tools within `namespace` tool definitions
- Apply web search tool sanitization during Meta request preparation
Closes: #6156
- Use `ExtractSummaryConfig` to parse summary configuration from OpenAI response payloads
- Default to enabled auto summaries when reasoning effort is set without explicit summary visibility
- Apply the resolved summary configuration directly to Antigravity translations
Closes: #6143
- Implement `splitDevinUID` for consistent UID splitting and effort extraction.
- Update model aggregation to handle thinking levels and merge variants.
- Refine display name cleaning logic to remove redundant suffixes.
- Adjust Devin catalog integration to exclude exposed thinking variants.
- Normalize and sort thinking levels with an extended rank scheme.
Closes: #6141
- Attach resolved execution model info during execution and token counting even when restoring execution models
- Propagate configuration update support to resolved Home dispatch model info
- Track modifications to configuration updates across plugin normalizers in the translation pipeline
- Mark configuration update support for eligible Codex models in the registry
- Remove direct Messages passthrough bypass for unconfirmed OAuth credentials
- Ensure standard cache control handling and CLI fingerprinting apply upstream
- Support detection for Claude Code 2.1.280 title helper payload shape
Closes: #6120
- Fix malformed `X-Client-Id` header and ensure it is applied to upstream requests
- Preserve subscription metadata during OAuth token creation and token refreshes
- Support dynamic retry-after for 404 responses and shorten default Meta 404 cooldown
Closes: #6117
- Map Devin grok models to xai owned_by in catalog and fetch_devin_models tool
- Update Antigravity fetched capability test to reflect gemini-pro-agent native web search support
- Fix formatting in test fixtures
* fix(claude): align Opus 5.5 cloak and preserve native CLI hints
* fix(claude): recognize the 2.1.280 Haiku title helper
The native title request now appends server-side fallback, fallback credit,
and cache diagnosis after the structured-output beta. Keep the helper
allowlist exact so this sequence passes through without cloaking.
* fix(claude): align thinking visibility and Messages passthrough
* fix(claude): preserve thinking visibility through compatibility paths
* fix(claude): harden OAuth beta, session alignment, and 2.1.280 helper headers
- Pass resolved `baseModel` directly to `applyCodexRoutingHint` instead of reading model from the upstream body
- Ensure the routing hint header accurately reflects the resolved model across HTTP and WebSocket executions
- Send X-Codex-Routing-Hint ("model=<slug>" plus ";tier=<service_tier>")
on ChatGPT-backend requests over HTTP, compact and websocket handshakes,
matching openai/codex rust-v0.155.0 build_routing_hint_header. Translated
requests previously carried service_tier=priority only in the body.
- Derive the hint from the final upstream body, replacing a hint a native
client forwarded, so it names the model and tier actually sent.
- Keep operator precedence: an auth header rule that resolves to a value
wins, a dynamic rule that resolves to nothing falls back to the derived
hint, and models.json override_header still applies last.
- Leave API-key requests unchanged, and keep websocket reuse as native Codex
does: an open connection keeps its handshake hint when the tier changes.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
- Add `RequestID` (unique execution UUID) and `TraceID` (inbound request ID) fields to usage records and plugin API
- Generate unique UUIDs per model attempt in `UsageReporter` while linking to parent trace context
- Expose `execution_id` and `trace_id` in Redis queue usage payloads while preserving legacy `request_id`
- Add header definitions and ordering for per-turn control, timing, inline tools, clear-at, dangerous tool use, thinking binding/resumption, and prompt caching evict betas
- Dynamically assemble beta headers based on model capabilities and request body fields matching Claude Code 2.1.280 behavior
Closes: #6054
- Update default Claude CLI version to 2.1.280 in cloaking and device profile
- Add `mid-conversation-tool-changes-2026-07-01` beta header support for supported models
Closes: #6054
- Convert `input_video` and `video_url` content parts to chat completion video parts
- Preserve video URL and processing options for upstream handling
Closes: #6037
Read Gemini interactions scanner lines directly because emitted frames are already cloned before reuse, and allocate each Kimi responses passthrough chunk once so it stays owned without a second copy.
