Keys with non-empty allowedQuotas may only use models whose provider belongs
to their pools' provider set; anything outside → 403 QUOTA_ONLY.
Normal allowedModels/allowedCombos checks are bypassed for quota-exclusive keys.
Introduces src/lib/quota/quotaKey.ts with resolveQuotaKeyScope(), a
pure async helper that maps an API key's allowedQuotas pool-ID list to
the concrete connectionIds and provider slugs it is permitted to use.
Covers empty/null/undefined input, missing pools, orphaned connectionIds,
and multi-pool deduplication. No behaviour change to existing code paths.
The agy provider was registered in providerRegistry.ts with
executor: "antigravity" but the executor map in executors/index.ts
only had an "antigravity" entry. getExecutor("agy") fell through to
DefaultExecutor, which returned undefined for baseUrl (agy only has
baseUrls), causing fetch(undefined) → TypeError: Cannot read properties
of undefined (reading 'toString').
Closesdiegosouzapw/OmniRoute#2932
The authz pipeline runs in the Next middleware runtime (proxy.ts -> runAuthzPipeline)
where ctx.request is a NextRequest with no .socket/.ip. requestPeerAddress therefore
returned null, so isLoopbackRequest was ALWAYS false and every LOCAL_ONLY path 403'd
even from loopback (Services/MCP/Traffic-Inspector were unusable). Read the Host
header instead — exactly what isLoopbackHost/isPrivateLanHost were built to parse —
which restores loopback and, combined with isPrivateLanHost, enables the
owner-authorized private-LAN access. Spawn-capable endpoints still require
manage-scope auth after this gate.
Services + Traffic-Inspector (LOCAL_ONLY, spawn-capable) returned 403 when the
dashboard was reached via the LAN IP (192.168.0.x) instead of loopback. Add
isPrivateLanHost (RFC1918 IPv4 + IPv6 ULA/link-local) and widen ONLY the
local-only PATH gate to accept private-LAN socket peer IPs — based on the real
socket peer address (not the spoofable Host header), so public-internet clients
present public IPs and stay blocked. The CLI-token gate stays strictly loopback;
paths remain LOCAL_ONLY-classified (Hard Rules 15/17 unchanged). Enforcement-layer
carve-out for a LAN-deployed instance, authorized by the operator.
The pool usage snapshot can come back without a dimensions array (e.g. when the
plan resolves to empty for catalog-only providers). PoolCard.computeStatus and
hasDimensions read usage.dimensions.length directly, crashing the whole page
("Cannot read properties of undefined (reading 'length')"). Normalize to [] in
PoolCard and in usePoolsUsageAggregate (dimensions/perKey).
5 new test files covering all 13 changed production files:
- estimateSizeFast.test.ts: 16 tests for fast size estimator (circular ref
protection, early exit, nested structures, Map safety)
- eviction-guards-apiKeyRotator.test.ts: 5 tests for Map eviction guards
(!has() check prevents evicting existing keys on update)
- eviction-guards-codexQuotaFetcher.test.ts: 4 tests for connectionRegistry
and quotaCache eviction guards
- rateLimitManager-idle-eviction.test.ts: 6 tests for idle limiter cleanup,
limiterLastUsed tracking, and shutdown behavior
- registry-direct-exports.test.ts: 20 tests verifying all 8 registries export
plain objects (no Proxy traps, no lazy getters, mutable entries)
Extract estimateSizeFast/isSmallEnoughForSemanticCache into standalone
open-sse/utils/estimateSize.ts to make them testable without importing
the entire chatCore.ts dependency tree.
- Chat (StudioConfigPane): add Provider + Model selects reusing the translator
hooks; order Endpoint -> Provider -> Model; ConfigState gains optional provider.
- Compare (CompareTab): add a user-prompt input and include it in the request
body; throttle per-column stream updates via requestAnimationFrame to stop the
UI freeze (was setColumns per chunk x N columns with an empty user message).
- Build (BuildTab + build/BuildWizard): redesign as a guided 3-step wizard
(What to test -> Configure -> Run) reusing ToolsBuilder/StructuredOutputEditor;
all run/tool-call handlers preserved.
- i18n: playground.build.* (18 keys) in en + pt-BR.
- MemoriesTab: auto-run health check on mount + poll every 30s (was manual-only).
- page: add enable/disable memory toggle (role=switch) via useMemorySettings.save({ enabled }).
- MemoryEngineStatus: show "npm install sqlite-vec" hint when vector store backend is "none".
- i18n: memory.memoryEnabled + memory.engine.vectorStoreInstallHint (en + pt-BR).
- Add compliance.eventTypes (36 labels) to en.json + pt-BR.json.
- ComplianceTab: render translated label via t.has/t fallback instead of raw entry.action.
- A2aAuditTab: render translated task state via a2aState* keys instead of raw task.state.
- Memory type/strategy dropdowns needed no i18n change — keys already exist; the
Phase 1 Select fix makes them render.
- search-tools: export modal no longer opens by default / stuck — guard on
exportOpen and drop the invalid isOpen prop the modal never read.
- logs: remove duplicate proxy/console tabs + SegmentedControl (dedicated
/dashboard/logs/proxy and /console pages already exist in the menu).
- memory: order tabs Memories -> Engine -> Playground.
- ui(Select): render children and suppress the placeholder/options branch when
children are provided — fixes the "empty" memory type/strategy dropdowns
(children were being shadowed by the component's own option list).
- test: source-level regression guards for all four.
The CPA executor now cloaks non-Claude-Code tool names (not just mcp_*), so the
prior "does not rewrite non-mcp_ tool names" assertion no longer holds:
my_tool is aliased to MyTool and restored on the response via _toolNameMap.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Addresses confirmed findings from an adversarial review of the prior commits:
- schema sanitizer: a truncation placeholder in a SCALAR annotation keyword
(description/title/pattern/format) was coerced to {}, which is itself invalid
draft-2020-12 and re-triggered the exact "input_schema is invalid" 400 the
sanitizer exists to prevent. Placeholders are now only coerced to {} in
subschema-expecting positions; scalar keywords are left untouched.
- schema sanitizer: numeric-string coercion is folded into
stripInvalidSchemaConstructs so it also covers contains / propertyNames /
additionalItems (which coerceSchemaNumericFields never visited).
- schema sanitizer: stop stripping the valid `default` keyword on the Claude
native/passthrough surface (the #1782 default-strip is a translator concern;
tool schemas here were previously forwarded verbatim). sanitizeClaudeToolSchema
is now a single stripInvalidSchemaConstructs pass.
- tool-name cloak: consult TOOL_RENAME_MAP / EXTRA_TOOL_RENAME_MAP before the
generic PascalCase fallback, so the CLIProxyAPI path uses the established
fingerprint-evasion aliases (subagents->SubDispatch, session_status->CheckStatus,
webfetch->WebFetch, ...) identically to the native path instead of weaker
first-letter casing.
- kill-switch: CLAUDE_DISABLE_TOOL_NAME_CLOAK is now honoured inside
cloakThirdPartyToolNames, so BOTH the native and CLIProxyAPI executor paths
respect it (previously only base.ts did); .env.example + ENVIRONMENT.md updated.
Regression tests added for each. Verified end-to-end through the live CPA path:
mixture_of_agents, subagents, and a tool carrying placeholder descriptions and
`default` values all return 200 with original names restored on the response.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The /dashboard/tools/agent-bridge page (Server Component) passed ALL_TARGETS
directly to AgentBridgePageClient (a Client Component). Each MitmTarget carries
a `handler: () => Promise<...>` function, which Next.js forbids across the
Server/Client boundary, raising at SSR time:
"Functions cannot be passed directly to Client Components ..."
This broke the whole page ("erro ao carregar").
Fix: introduce MitmTargetView = Omit<MitmTarget, "handler"> and pass a
sanitized array (ALL_TARGETS.map(({ handler, ...rest }) => rest)). The UI never
invokes handler, so behavior is unchanged. Adds a regression test asserting the
sanitized targets are function-free and JSON-serializable.
The native Claude OAuth guard in executors/base.ts is bypassed when
`upstream_proxy_config.mode = cliproxyapi` routes the request through the
CliproxyAPI executor — it has its own execute()/transformRequest() and never
reaches BaseExecutor.execute(), so the cloak/sanitizer never ran for that
(common) deployment. Wire the same guards into
CliproxyapiExecutor.transformRequest (Anthropic-shape branch), composing with
the existing bisected `mcp_*` reserved-namespace rewrite:
- sanitizeClaudeToolSchemas() on transformed.tools.
- cloakThirdPartyToolNames() with skip = mcp-reserved, so applyMcpToolNameRewrite
keeps authority over `mcp_*` (its bisected `Mcp_X` form) and the two reverse
maps stay disjoint / single-hop. Both merge into the non-enumerable
_toolNameMap the response stream already uses to restore the caller's names.
cloakThirdPartyToolNames is now non-mutating (clones changed entries) to respect
transformRequest's no-input-mutation contract, and takes an optional `skip`
predicate.
Verified end-to-end through the live CPA path: a real ~100-tool harness payload
that returned the "out of extra usage" placeholder now returns 200 with original
tool names restored on the response stream; `mcp_*` tools and genuine PascalCase
Claude Code tools are unaffected.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Follow-up commit on PR #2943 review:
- Preserve boolean schemas in `sanitizeClaudeToolSchemas` (Gemini Code Assist,
high severity). `additionalProperties: false` is the canonical JSON Schema
lock-down for object tools; the previous coercion silently turned it into the
permissive `{}`, which would invite models to hallucinate extra arguments
during tool calling. Same rule now applies to per-property boolean schemas
under `properties`. Placeholder strings still get the permissive `{}` slot —
booleans get preserved verbatim.
- Defensive null guards in `cloakThirdPartyToolNames` for `tools[]` and
`messages[]` entries that might be `null`/`undefined`. Prevents a runtime
`TypeError` if a malformed payload reaches the cloak.
- Document `CLAUDE_DISABLE_TOOL_NAME_CLOAK` in `.env.example` and
`docs/reference/ENVIRONMENT.md` (env/docs contract was failing in CI).
- Regression tests covering all of the above (5 boolean preservation cases,
2 null-tolerance cases).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Native Claude OAuth (claude->claude passthrough) forwards client tool
definitions verbatim. Anthropic's first-party Messages API then rejects:
- invalid tool input_schemas (deep-truncation placeholders such as
`enum: "[MaxDepth]"`, or index-keyed objects where arrays are required), and
- tool names it fingerprints as a third-party agent harness (specific
blacklisted names like `mixture_of_agents`, or a large enough set of
recognizable snake_case agent tool names),
both surfaced as a misleading `400 You're out of extra usage` placeholder
(the SSE stream is refused — not a real billing event). The same request
succeeds on translator-backed providers (OpenAI/Codex), which already sanitize
and re-shape tool payloads — so the gap is specific to the native passthrough.
Adds the missing guards on the native Claude OAuth path (executors/base.ts):
- sanitizeClaudeToolSchemas(): coerce/drop invalid draft-2020-12 constructs
(non-array enum/required/anyOf/..., placeholder schema slots -> {}).
- cloakThirdPartyToolNames(): deterministically alias non-Claude-Code tool
names (Claude Code canonical mapping where one exists, else PascalCase),
tracked in the existing per-request _toolNameMap so remapToolNamesInResponse
restores the caller's original names. Opt out via
CLAUDE_DISABLE_TOOL_NAME_CLOAK=true.
Genuine Claude Code tool names (PascalCase) and already-valid schemas are
left untouched, so existing first-party traffic is unaffected.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Keep existing object-argument cleanup behavior, but avoid parsing and stripping arbitrary JSON-string arguments for unrelated tools where empty strings or arrays may be valid payloads. Add regression coverage for non-Read and non-object Read arguments.
Only translate Claude Code web_search_YYYYMMDD server tools to native Responses web_search when the final target is OpenAI Responses. Keep the Chat Completions target on function-tool shape and cover the full translateRequest path.
Translate Claude Code web_search_YYYYMMDD server tools to the native OpenAI Responses web_search tool and preserve filters/location. Convert forced Claude tool_choice for web_search to the native Responses tool choice while leaving ordinary custom functions unchanged.
Closes#2936
Buffer Claude Code Read tool calls through the existing shim layer so empty pages placeholders are removed before streaming input_json_delta to the client. Also clean JSON-string Responses tool arguments, not only object arguments.
Closes#2935
Addresses #2889
Plan 14 (#2839) test listed only cli-code/cli-agents/acp-agents/cloud-agents; #2858 added agent-bridge/traffic-inspector to TOOLS_GROUP. Align test to real code (both feature sets).
