Two fixes in openaiContextWindows.ts:
1. Sort lookup keys by length descending in lookupByModel() so the most
specific prefix always wins. Without this, 'gpt-4-turbo-preview'
could match 'gpt-4' (8k) instead of 'gpt-4-turbo' (128k) depending
on V8's object key iteration order.
2. Update Llama 3.1/3.2/3.3 context windows from 8,192 to 128,000.
These models support 128k context natively (Meta official specs).
The previous 8k value was Ollama's default num_ctx, not the model's
actual capability, causing premature auto-compact warnings.
Two fixes for issue #133 where setting ANTHROPIC_API_KEY=dummy alongside
CLAUDE_CODE_USE_GEMINI=1 causes "Invalid API key" errors:
1. auth.ts: In the CI branch of getAnthropicApiKeyWithSource(), the
ANTHROPIC_API_KEY value was returned without checking isUsing3PServices().
A dummy key leaked into the Anthropic key resolution pipeline even when
Gemini was the active provider. Now guards with isUsing3PServices().
2. errors.ts: The x-api-key error handler surfaced "Invalid API key" for
any provider. Added getAPIProvider() === 'firstParty' guard so 3P users
see the real underlying error instead of a misleading auth message.
Note: The cli.tsx Gemini validation fix (originally part of this PR) was
independently implemented in PR #121 and is already on main.
OpenAI returns cached token counts in usage.prompt_tokens_details.cached_tokens
but the shim hardcoded cache_read_input_tokens to 0. This made prompt
caching invisible to the cost tracker and session summary even when
OpenAI's automatic caching was actively reducing costs.
Changes:
- Extend OpenAIStreamChunk usage interface with prompt_tokens_details
- Map cached_tokens to cache_read_input_tokens in convertChunkUsage()
- Same fix in _convertNonStreamingResponse() for non-streaming path
- cache_creation_input_tokens remains 0 (OpenAI auto-caching has no
creation cost — it is free and automatic)
Replace raw === '1' || === 'true' comparisons with isEnvTruthy() in
context.ts for consistency with getAPIProvider() in providers.ts.
This also covers the newly added CLAUDE_CODE_USE_GITHUB provider.
Add native Gemini model entries (without google/ prefix) to both
context window and max output token tables. Corrects gemini-2.5-pro
and gemini-2.5-flash max output tokens to 65,536 (was 8,192/32,768).
Addresses the most critical remaining issues in the provider shim layer,
building on top of #124 (recursive schema normalization + try/finally).
openaiShim.ts:
- Throw APIError via SDK factory instead of plain Error — enables retry
on 429/503 (was completely broken: zero retries for all 3P providers)
- Guard stop_reason !== null before emitting usage-only message_delta
(Azure/Groq send usage before finish_reason)
- Fix assistant content: join text parts instead of invalid as-string cast
(Mistral rejects array content on assistant role)
- Expose real HTTP Response in withResponse() for header inspection
- Skip stream_options for local providers (Ollama < 0.5 compatibility)
codexShim.ts:
- Throw APIError at all 4 throw sites (HTTP + 3 streaming errors)
- Add tool_choice 'none' mapping (was silently ignored)
- Forward is_error flag with Error: prefix (matching openaiShim)
Split the setup documentation into a simple beginner path and a separate advanced path. Add OS-specific quick starts for Windows and macOS/Linux so non-technical users can copy and paste the right commands without sorting through Bun and source-build instructions.
- Set competing provider flags to undefined in updateSettingsForSource to ensure clean GitHub boot
- Fix resolveProviderRequest to default to github:copilot when OPENAI_MODEL is unset
- Hydrate secure tokens and managed settings in system-check.ts to prevent false negatives
- Add models:read scope to GitHub device flow
- Updated the `getAtomicChatApiBaseUrl` function to parse the base URL correctly and ensure the pathname is formatted without trailing version segments.
- Cleared search and hash components from the URL to standardize the output.
This change improves the robustness of the URL handling for the Atomic Chat provider.
Wait for failed MCP transport cleanup before command exit so targeted live checks do not crash on Windows.
Co-Authored-By: Claude <noreply@anthropic.com>
Add the MCP doctor subcommand with text and JSON output, config-only mode, and scope filtering so users can diagnose MCP issues from the CLI.
Co-Authored-By: Claude <noreply@anthropic.com>
Add the diagnostics core and report model for MCP health, scope, and config analysis. This creates the structured report used by both text and JSON doctor output.
Co-Authored-By: Claude <noreply@anthropic.com>
The version kill-switch calls Anthropic's GrowthBook endpoint to
enforce a minimum version. This is currently safe for 3P users only
because isAnalyticsDisabled() returns true (disabling GrowthBook).
Adding an explicit provider guard makes this safety independent of the
analytics stub, preventing 3P users from being blocked by Anthropic's
version requirements in case of future upstream merges.
Pin all GitHub Actions to commit SHA instead of mutable version tags
to prevent supply chain attacks via tag poisoning. This is especially
important for third-party actions like oven-sh/setup-bun.
Add provider guard to migrateSonnet1mToSonnet45() so it only runs for
firstParty (Anthropic) users. Without this, a 3P user with
model='sonnet[1m]' would have it rewritten to an Anthropic-specific
alias that is invalid for OpenAI/Gemini/Ollama providers.
- Make getProviderLabel() switch exhaustive with explicit openai/gemini
arms instead of falling through to env-var checks in default
- Add clarifying comment on additionalProperties override in schema
normalization
