Redefine request-retry as additional credential retry rounds and
enforce max-retry-credentials per round. Home dispatch now carries
excluded and pinned auth constraints, supports remote retry limits, and
propagates cooldown retry-after metadata across exhausted rounds.
Move Antigravity upstream retries under conductor ownership to avoid
double-consuming retry attempts. Update configuration comments and add
coverage for Home retry rounds, cooldown handling, pinned credentials,
and legacy dispatcher compatibility.
* feat(codex): add opt-in stream bootstrap buffering
The upstream smuggles capacity rejections into an HTTP 200 stream. The
handshake events arrive normally and only a later event carries
{"error":{"type":"service_unavailable_error","code":
"server_is_overloaded"}}. By then the executor has already handed the
first chunk downstream, the response is committed, and the conductor can
no longer retry on another credential, so the request fails even though
other credentials were available.
When codex.stream-bootstrap-buffering is enabled the executor holds back
the handshake events until it can tell whether the stream carries real
output or a rejection. An overload rejection then fails the attempt
before any chunk is delivered, letting the conductor retry on another
credential; every other terminal failure is flushed in order and
delivered in-stream exactly as before.
Detection uses an event-type allow-list rather than a fixed count. On the
websocket transport codex.rate_limits and codex.response.metadata arrive
before response.created, making the first generated event the fifth
frame, so a small counter would release the stream before the rejection
is visible. Buffering is bounded and hitting the bound degrades to the
original unbuffered behaviour.
Two details are load-bearing. The error must be returned synchronously:
delivering it as the first stream chunk makes ExecuteStream downgrade it
into a committed 200 and the status is lost. And the websocket path must
not signal an upstream disconnect for a rejection it intends to retry,
because the downstream handler closes the client connection on that
signal and the retry would have nowhere to deliver.
The 503 status is produced only on this path rather than in the shared
codexTerminalFailureStatus mapping, so disabling the feature restores the
previous behaviour exactly, including cooldown classification and
retry-after parsing.
Defaults to false: response headers are withheld until generation
starts, which can trip client or reverse-proxy read timeouts.
* test(codex): pin bootstrap overload failover through the conductor
Executor-level tests cannot show what the client finally receives. These
exercise ExecuteStream end to end to pin three properties that are easy
to regress:
- consecutive overloaded credentials are skipped until one serves the
request, and retries are capped by max-retry-credentials rather than
multiplying with request-retry
- exhausting the pool surfaces the upstream status instead of a
committed 200 stream
- with buffering disabled the rejection stays an in-stream error on a
committed stream, which is the behaviour the feature must preserve
The third case also documents why the executor returns its error
synchronously: an error arriving as the first stream chunk is wrapped and
downgraded into a committed 200, silently losing the status.
- Add `oauth-request-scoped-errors` configuration with normalization, sanitization, and YAML management persistence/hot-reload hooks.
- Route request-scoped error classification to use per-provider rules only for OAuth auth entries.
- Add config diff reporting and management CRUD endpoints for `oauth-request-scoped-errors` (get/put/patch/delete) with input sanitization.
Closes: #5085
- Propagate request headers into custom-header resolution for OpenAI/Gemini/XAI/Codex execution and websocket flows.
- Resolve auth `header:` values like `$ABC` from incoming request headers at request time and omit headers when no value is available.
- Add documentation for the dynamic custom-header behavior in `config.example.yaml`.
Closes: #5053
Claude Code 2.1.220 through 2.1.234 emit the cch attribution only for
firstParty on api.anthropic.com and for vertex; every other backend sends
the billing header unsigned. CPA had dropped its endpoint check, so an
opted-in API key signed a per-request hash on any gateway and could bust
that gateway's prompt cache.
- Restore the endpoint gate in claudeCCHSigningEnabled: a real Claude OAuth
credential still signs on every upstream, because a downstream Claude Code
pointed at CPA cannot produce that value itself, while a claude-code-cli
API key signs only on api.anthropic.com or Vertex
- Drop the unused origin parameter from Claude fingerprint policy resolution
and restore the original resolveClaudeWirePolicy signature; the wire profile
follows the credential and only CCH follows the origin
- Add config.NormalizeClaudeFingerprintProfile / ValidateClaudeFingerprintProfile
as the single source of truth for fingerprint-profile values
- Reject unknown fingerprint-profile values in the Management API, and warn
once per distinct value at request time instead of on every resolution,
which previously logged about four warnings per request for one typo
- Preserve unrecognized values through config sanitization so rewriting a
config file never discards operator input
- Update config.example.yaml and tests for the origin-scoped CCH behavior
* feat(config): add fingerprint-profile to Claude keys and auth JSON
- Add FingerprintProfile to ClaudeKey configuration struct and normalizer
- Track fingerprint-profile in config diff
- Map fingerprint-profile / fingerprint_profile to auth attributes in file and config synthesizers
- Support fingerprint-profile in Management API PatchClaudeKey and normalization
- Add Claude billing attribution string manipulation utilities in internal/util
- Document fingerprint-profile options in config.example.yaml
* feat(claude): add fingerprint policy and request-local CLI identity
- Centralize Claude fingerprint policy resolution in claude_fingerprint_policy.go
- Support stable Claude CLI identity synthesis (UUIDv5 account_uuid and SHA-256 device_id)
seeded from API keys or stable OAuth IDs, keeping access tokens isolated
- Warn on unrecognized fingerprint-profile values
* feat(claude): apply CLI fingerprint to Messages and keep API keys caller-owned
- Wire centralized fingerprint policy into Claude and Kimi executors
- Keep first-party Anthropic API keys and delegated providers caller-owned by default
- Apply Claude Code CLI wire profile (betas, metadata, diagnostics, MCP aliases)
when fingerprint-profile=claude-code-cli is configured
- Strictly align CCH signing with native Claude Code 2.1.220: only first-party
api.anthropic.com and Vertex sign dynamic CCH; third-party gateways and Kimi
receive billing header without cch= to avoid prompt cache busting
- Respect caller-owned count_tokens bodies by default while aligning CLI shape on opt-in
- Fall back to CLIProxyAPI/<version> User-Agent when caller sends no UA in caller-owned mode
- Scope custom operator header overrides accurately in caller-owned mode
- Add comprehensive test coverage for policy resolution, gateway opt-in, Kimi, and token counting
- Changed `DisableCooling` from a boolean to a pointer in various config types to allow explicit inheritance.
- Updated tests to reflect the new pointer usage for `DisableCooling`.
- Enhanced the `BuildConfigChangeDetails` function to handle optional boolean changes for `DisableCooling`.
- Added new tests to ensure proper handling of cooling overrides in configurations.
- Refactored the `SetQuotaCooldownDisabled` function and related logic to clarify the purpose of cooldown management.
- Introduced new tests for cooling override precedence in the auth manager.
- Ensured that all relevant handlers and synthesizers correctly manage the `DisableCooling` setting.
- Add request-scoped error rule extraction from auth metadata or runtime provider config (including OpenAI compatibility fallback)
- Match rules by HTTP/status-code plus error body substring or regex patterns
- Support `stop`, `stop-and-cooldown`, `continue`, `continue-and-cooldown` actions with normalized validation
- Apply matched actions to execution results via request-scoped vs force-cooldown error codes and stop/continue flow control
- Introduce request-stop error wrappers/helpers for matching and unwrapping scoped stop state
Closes: #5006
- Add `is-compat` support to OpenAI compatibility model config, capabilities, hashing, and example config.
- Propagate `IsCompat` through API-key model resolution and switch OpenAI-compat executor translation to compatibility-aware routing.
- Keep Claude assistant thinking content in compatibility mode while keeping default behavior unchanged when `is-compat` is disabled.
Closes: #4776
- Added `is-compat` model metadata plumbing from config through executor and helpers, including hash computation.
- Introduced a compatibility-aware translation path (`TranslateRequestWithAPIKeyModelCompatibility`) and wired it into Claude/Gemini/Codex/Interactions request flows.
- Updated Claude message sanitization/translation behavior to keep empty-thinking compatibility blocks (including signatures) when `is-compat` is enabled, while keeping default behavior unchanged.
Keep a healthy cached session binding even when a higher-priority credential recovers. Continue applying credential priority to cold selection, plugin scheduling, and true failover.
Resolve the across-priority candidate list in a single availability pass and narrow the highest-priority tier from the same cloned auths, so the selection path does not scan or deep-clone candidates twice. Document that an established binding outranks credential priority.
Fixes#4808
Align the remaining measured OAuth wire profiles, including the ordered
connection writer in internal/httpwire that reproduces the observed header
sequence, and the refresh/profile response shapes in internal/auth/claude.
Replay the measured Fast path and keep diagnostic continuity across cloaked and
native requests.
Preserve the native direct token-counting shape so a caller that reaches
count_tokens itself is not reshaped into the cloaked form.
Scope cloak dates to the credential's timezone rather than the host's, so
currentDate matches what the real client would have sent for that account.
Claude Code builds Anthropic-Beta per request instead of sending a fixed list.
Captured from an isolated 2.1.220 profile pointed at api.anthropic.com through
a local proxy, over two rounds covering 11 model IDs and the [1m] variants:
constant claude-code, interleaved-thinking, redact-thinking,
thinking-token-count, context-management, prompt-caching-scope
tools advanced-tool-use-2025-11-20 only when tools are declared
model mid-conversation-system-2026-04-07 only on models that accept a
role=system turn
[1m] context-1m-2025-08-07, directly after claude-code-20250219 rather
than at the end
trailing effort-2025-11-24, then server-side-fallback-2026-06-01
claude-sonnet-5 emits mid-conversation-system-2026-04-07, so it accepts a
role=system turn and must not sit in the legacy reminder whitelist.
count_tokens does not reuse the inference fingerprint. Running /context in an
interactive session issues 37 identical calls, which made the endpoint
observable for the first time: four betas only, and 21 headers rather than 22
because X-Stainless-Timeout is absent. The profile is selected from the request
path so no call site has to thread another flag.
Preserve a cloaked caller's own system prompt instead of discarding it, place
it as a mid-conversation system turn on models that accept one, and route the
remaining legacy models through system reminders.
Scope the legacy reminder whitelist to official model IDs. claude-opus-4-6-thinking
was dropped: Anthropic publishes no -thinking IDs, that one belongs to the
antigravity provider in models.json and is served by a different executor, so it
can never reach ClaudeExecutor cloaking. Keeping it implied that synthetic
suffixes are normalized here, which they are not, since thinking.ParseSuffix only
strips parenthesis suffixes. The map is anchored to the "claude" provider block
plus Anthropic's bare and "-latest" aliases, and now covers claude-opus-4-7.
Detect confirmed CLI, sdk-cli and VSCode callers before mutation so native
software, system, tool, cache and beta shapes pass through, while unconfirmed
OAuth clients receive a coherent minimum CLI identity.
Persist each Claude OAuth credential's upstream account metadata and one stable
device ID, derive one stable session per agent conversation, and keep body and
header identity synchronized across Messages, streaming and count_tokens.
Alias every cloaked third-party custom tool through caller-stable opaque MCP
names and restore declarations, choices, history, references, non-stream
responses and SSE events without changing tool ownership.
Implement the Claude Code 2.1.220 CCH algorithm over the final serialized
request bytes, align currentDate and first-user cache layout, update the
official beta/header baseline, and use upstream count_tokens for OAuth and
first-party Anthropic credentials.
Match the 2.1.220 TLS ClientHello so the transport fingerprint agrees with the
identity the request now claims, and document the CLI defaults and automatic
OAuth signing / tool alias behaviour in config.example.yaml.
- Add OpenAI-compat executor-time normalization for `tool` message content, converting non-string tool results to plain text and replacing image parts with a clear unsupported marker for models configured with text-only `input-modalities`.
- Apply normalization in both regular and streaming OpenAI-compat execution paths before prompt-cache processing.
- Update config example to document `[text]` `input-modalities` for upstreams that reject multimodal tool-result content.
Closes: #4737
- Add optional `max-context-length` model configuration across supported provider model types and expose it via `GetMaxContextLength`.
- Propagate the override into model metadata so Codex/client model catalog responses honor the configured value (`context_window`, `max_context_window`, and `max_context_length`).
- Update example configuration with documented usage of the new option.
Closes: #4728
- Introduced a new `support-prompt-cache-key` configuration option to enable optional prompt cache key derivation for supported models.
- Updated relevant API handlers and internal logic to handle the new configuration.
- Enhanced executor workflows to apply prompt cache keys conditionally during request processing.
- Added tests to validate prompt cache key behavior across various scenarios and providers.
- Updated configuration examples and documentation for the new option.
Closes: #4700
- Introduced `alpha-search` flag for Codex API keys to enable Alpha Search functionality.
- Added `CredentialPolicyCodexAlphaSearchV1` for filtering and validating API keys compatible with Alpha Search.
- Extended configuration, synthesizer, and watcher functionality to track and manage `alpha-search` flag changes.
- Updated Codex executor to dynamically construct Alpha Search endpoint based on API key attributes.
- Enhanced tests to validate Alpha Search flag handling, endpoint construction, and credential filtering.
Closes: #4692
- Introduced `disable-codex-cloaking` to allow disabling enforced `User-Agent` and `Originator` headers for Codex requests.
- Updated header application logic to conditionally include `codexUserAgent` and `codexOriginator` based on configuration.
- Enhanced config diff tracking to detect changes in `disable-codex-cloaking`.
- Expanded tests to cover new config behavior and header application scenarios.
- Replaced instances of `thinking.ApplyThinking` with `helps.ApplyRequestThinking` across all executors for consistency.
- Updated `applyGeminiInteractionsThinking` to accept `cliproxyexecutor.Request` and `Options`.
- Centralized logic for request thinking application to `helps` package for improved maintainability.
Closes: #4618
- Added support for weighted round-robin authentication scheduling strategy.
- Implemented credential weight validation for attributes and metadata, with strict error handling for invalid weights.
- Enhanced scheduler with smooth weighted state handling and proportional selection logic.
- Introduced tests for credential weight parsing, validation, and weighted round-robin behavior.
- Updated configuration to include `weight` field for credentials with range validation.
Closes: #4470
- Introduced `DisableCloakingModelList` in `ClaudeCodeConfig` to control model ID cloaking in Anthropic model list responses.
- Updated relevant APIs and handlers to respect the new configuration.
- Added comprehensive tests for enabling/disabling cloaking behavior and config-driven hot reload scenarios.
- Extended example configuration and documentation to include the new setting.
Closes: #4473
- Introduced `InjectXSearch` in `XAIConfig` to enable automatic injection of the native `x_search` tool when not explicitly declared.
- Updated `XAIExecutor` to honor the `InjectXSearch` configuration, ensuring consistent tool availability.
- Enhanced configuration handling with support for dynamic diffing to track changes in `InjectXSearch`.
- Added comprehensive tests to validate `InjectXSearch` behavior, including preparation and tool choice synchronization.
- Updated example config and documentation to outline `InjectXSearch` usage.
Closes: #4339
- Implemented a TCP proxy for WebRTC candidate tunneling in Codex Live, supporting passive TCP candidates on port 443.
- Restricted tunneling to globally routable public IPs and added safeguards for rejecting unsafe/private targets.
- Added robust validation of STUN BindingRequest frames before forwarding to upstream candidates.
- Includes extensive unit tests for proxying behavior, candidate validation, and tunnel edge cases.
- Added comprehensive diffing for Codex live media relay settings, including support for public IP, UDP port ranges, and ICE server changes.
- Introduced `displayOptionalValue` utility to handle optional values in diff outputs.
- Improved test coverage for config change detection, ensuring no sensitive information leakage.
- Replaced `allow-private-remote-ips` with the new `disable-private-remote-ips` property, adding YAML backward compatibility.
- Updated Codex live handler to differentiate media relay configuration changes and runtime updates.
- Updated Kimi and Gemini executors to use `TranslateRequestWithCodexMultiAgentV2` for improved multi-agent v2 optimization.
- Enhanced configuration and API server to support `CodexOptimizeMultiAgentV2`.
- Added codex multi-agent V2 optimizations in `config`, `executor`, and `watcher` modules.
- Introduced `display-name` field for human-readable model names in config and YAML files.
- Updated alias application logic to set and preserve display names during model alias mapping.
- Enhanced tests to validate display name behavior for various scenarios, including forks and upstream preservation.
- Refined `sanitizeOAuthModelAlias` to handle `display-name` with proper trimming and formatting.
Closes: #4398
- Introduced `xai-api-key` to configuration for supporting xAI provider integration.
- Added API key operations: creation, updates, deletion, and sanitization.
- Implemented backend enhancements for credential-specific routing, response filtering with model aliasing, and WebSocket handling for xAI services.
- Included extensive test coverage to validate configuration parsing, CRUD operations, and the new functionalities.
- Updated related modules to handle `xai-api-key`, including the watcher, management handlers, and configuration sanitizers.
- Added `DisplayName` to model configuration for Codex, Claude, Gemini, Vertex, and OpenAI compatibility.
- Updated hash computation and model summary to account for `DisplayName`.
- Enhanced API handlers to use `DisplayName` for client-facing catalogs.
- Expanded tests to verify `DisplayName` usage, preservation, and fallback mechanisms.
- Updated documentation and configuration examples for `DisplayName` field.
Closes: #4245
- Added handling of input/output modalities metadata for Codex and compatibility clients.
- Updated model registry and configurations to support "text" and "image" modalities.
- Introduced new tests to validate input/output modalities registration and processing.
Closes: #3976
- Introduced API handlers and executor logic for Google Interactions
- Added request and response transformations for OpenAI and Claude Interactions.
- Integrated Gemini API with Interactions support.
- Updated tests to validate Interactions request parsing and error handling.
- Refactored translator logic for Interactions data flows.
- Added Manifest struct to encapsulate plugin metadata and installation details.
- Implemented ManifestFromRelease and ManifestFromPlugin functions for creating manifests from releases and plugins.
- Enhanced Plugin struct to include Versions and InstallPlan for direct installations.
- Introduced validation for direct install type, ensuring artifacts are correctly specified.
- Updated registry validation to support new schema version and direct install requirements.
- Added tests for parsing and validating direct install plugins, ensuring correct artifact handling.
Add OAuthModelAlias.ForceMapping to rewrite client-visible model fields in non-stream and SSE stream responses while leaving request-log upstream payloads unchanged.
- Wire config, watcher diff, and conductor execute/stream paths
- Rewrite force-mapped responses in Antigravity credits fallback paths
- Prevent buffered SSE chunks from being emitted by line-wise fallback
- Preserve thinking suffixes for same-base force-mapping aliases
- Cover codex, antigravity, kimi, and xai with live-derived fixtures and regression tests
- Document a conservative antigravity-only force-mapping example in config.example.yaml
- Introduced `RebuildMidSystemMessage` field in config to move system messages into the top-level Claude system field.
- Updated executor to handle mid-system message rebuilding when enabled via config or auth attributes.
- Added unit tests to verify rebuilding behavior and default behavior when disabled.
- Updated configuration example and API handlers to support the new field.
Closes: #3792
- Introduced `SetOAuthModelAliasesAttribute` and `OAuthModelAliasesFromAttributes` for managing per-auth model aliases.
- Enhanced OAuth model resolution logic to prioritize per-auth aliases over global aliases.
- Updated metadata handling to extract and sanitize per-account model aliases.
- Added tests to validate alias precedence, empty attributes, and conflict scenarios.
Closes: #3764
- Introduced `CooldownStateStore` interface for managing independent cooldown state persistence.
- Implemented `FileCooldownStateStore` for storing cooldown states as per-auth `.cds` files with atomic writes and stale file cleanup.
- Enhanced `Manager` to support restoring state from `CooldownStateStore` and persisting state changes during auth updates.
- Updated tests to validate cooldown state saving, loading, concurrency handling, and error scenarios.
Closes: #3368
