- Replace verbose ANTIGRAVITY_SYSTEM_INSTRUCTION with compact version from CLIProxyAPI
- Replace bridgePrompt override with [ignore] wrapper pattern
- Switch Antigravity Gemini test model from gemini-3-flash to gemini-3-pro-high
- Rename calculator tool to math_operation (gemini-3-pro ignores schema for 'calculator')
closes#1415
- Use parametersJsonSchema instead of parameters for Gemini tool declarations
to support full JSON Schema (anyOf, oneOf, const, etc.)
- Keep legacy parameters field for Claude models on Cloud Code Assist, where
the API translates parameters into Anthropic's input_schema
- Revert claude-opus-4-6-thinking back to claude-opus-4-5-thinking (model
doesn't exist on the Antigravity endpoint)
fixes#1398
* feat(antigravity): update model costs and tokens, migrate compaction tests to Claude 4.6
- Update model costs for various models in `models.generated.ts` to reflect the latest pricing.
- Update maxTokens for certain models.
- Migrate compaction tests from `claude-opus-4-5-thinking` to `claude-opus-4-6-thinking` in `compaction-thinking-model.test.ts`.
* fix: remove unnecessary peer dependencies in package-lock.json
This commit removes the `peer: true` flag from several dependencies in `package-lock.json`. These dependencies (lit, tailwind-merge, tailwindcss, picomatch, @tailwindcss/typescript, vite, picomatch) do not need to be explicitly marked as peer dependencies in this context, as they are already managed as regular dependencies. Removing the `peer: true` flag simplifies the dependency graph and avoids potential conflicts during installation.
Add a manually inserted "auto" model entry for OpenRouter alongside
the existing "openrouter/auto" entry, allowing users to select the
auto-routing model with a shorter identifier.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Claude Opus 4.5 has been replaced by Claude Opus 4.6 on the
Antigravity (Google Cloud Code Assist) platform.
- Update model definition in generate-models.ts
- Update generated models output
The process.env access was outside the typeof process check, which
would throw in browser environments. Moved inside the Node.js/Bun
block for consistency with other env var access.
Also added changelog entry for #1320 and improved docs clarity.
- Remove :0 suffix from Opus 4.6 Bedrock model IDs (not valid for this model)
- Fix us/eu Opus 4.6 cache pricing (0.5/6.25 instead of 1.5/18.75)
- Add missing eu.anthropic.claude-opus-4-6-v1 inference profile
- Fix coding-agent default Bedrock model ID to match catalog
- Add adaptive thinking mode (type: 'adaptive') for Opus 4.6+
- Add effort parameter ('low', 'medium', 'high', 'max') for adaptive thinking
- thinkingEnabled now auto-detects: adaptive for 4.6+, budget-based for older
- streamSimple/completeSimple map ThinkingLevel to effort levels for Opus 4.6
- Add tests for Opus 4.6 adaptive thinking and GPT-5.3 Codex
- Update @anthropic-ai/sdk to 0.73.0
- Update @aws-sdk/client-bedrock-runtime to 3.983.0
- Update @google/genai to 1.40.0
- Remove fast-xml-parser override (no longer needed)
We had some workarounds in `generate-models.ts` initially - mainly to make cross-region inference work
for Amazon Bedrock provider, but now these are upstreamed into models.dev and we no longer need those.
Extracted HTTP proxy setup to shared module and imported it from both
stream.ts and oauth/index.ts. This ensures fetch() calls during OAuth
flows (token exchange, refresh, project discovery) go through the proxy.
fixes#1132
Allows users to override the Antigravity User-Agent version when Google
updates their version requirements, avoiding the need to wait for a
package release.
Fixes#1129
When a provider (e.g., Google Gemini CLI) requests a retry delay longer
than maxDelayMs (default: 60s), the request fails immediately with an
informative error instead of waiting silently for hours.
The error is then handled by agent-level auto-retry, which shows the
delay to the user and allows aborting with Escape.
- Add maxRetryDelayMs to StreamOptions (packages/ai)
- Add maxRetryDelayMs to AgentOptions (packages/agent)
- Add retry.maxDelayMs to settings (packages/coding-agent)
- Update _isRetryableError to match 'retry delay' errors
fixes#1123
* feat(ai): add Vercel AI Gateway routing support
Add vercelGatewayRouting to OpenAICompletionsCompat, parallel to
openRouterRouting. When a model targets ai-gateway.vercel.sh and has
vercelGatewayRouting configured, the openai-completions provider passes
providerOptions.gateway with only/order in the request body.
Changes:
- types.ts: VercelGatewayRouting interface + field on OpenAICompletionsCompat
- openai-completions.ts: buildParams passes providerOptions.gateway,
detectCompat/getCompat include the new field
- model-registry.ts: VercelGatewayRoutingSchema for models.json validation
- test: updated Required<OpenAICompletionsCompat> in test fixture
* docs(coding-agent): add vercelGatewayRouting to custom models documentation
- Add kimi-coding provider using Anthropic Messages API
- API endpoint: https://api.kimi.com/coding/v1
- Environment variable: KIMI_API_KEY
- Models: kimi-k2-thinking (text), k2p5 (text + image)
- Add context overflow detection pattern for Kimi errors
- Add tests for all standard test suites
- Add huggingface to KnownProvider type
- Add HF_TOKEN env var mapping
- Process huggingface models from models.dev (14 models)
- Use openai-completions API with compat settings
- Add tests for all provider test suites
- Update documentation
fixes#994
Adds support for extended cache retention via PI_CACHE_RETENTION=long:
- Anthropic: 5m -> 1h TTL
- OpenAI: in-memory -> 24h retention
Only applies to direct API calls (api.anthropic.com, api.openai.com).
Proxies and other providers are unaffected.
fixes#967
- Handle pipe-separated IDs from OpenAI Responses API in openai-completions provider
- Strip trailing underscores after truncation in openai-responses-shared (OpenAI Codex rejects them)
- Add regression tests for tool call ID normalization
fixes#1022
