Azure OpenAI and newer OpenAI models (o1, o3, o4...) reject `max_tokens`
with a 400 error and require `max_completion_tokens` instead.
Maps `params.max_tokens` → `max_completion_tokens` in the request body,
which is the current standard across OpenAI-compatible providers.
Adds a new startup screen with filled-block text logo and sunset
gradient, printed to stdout before the Ink UI loads. Removes the
old OPEN box logo from the chat UI since the new screen replaces it.
Changes:
- src/components/StartupScreen.ts (NEW) — gradient OPEN CLAUDE logo
with provider info box (Provider, Model, Endpoint). Auto-detects
active provider from env vars (OpenAI, Gemini, DeepSeek, Ollama,
Groq, Mistral, Azure, LM Studio, Anthropic). Skipped in CI and
non-TTY environments.
- src/entrypoints/cli.tsx — calls printStartupScreen() at startup
before Ink renders
- src/components/Messages.tsx — removes <LogoV2 /> from LogoHeader
so the old OPEN box logo no longer appears in the chat UI
Addresses #55.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit addresses strict schema validation limitations when running subagents under OpenAI backend shims.
- Drops empty properties from payloads (like Record<string, string>) that break OpenAI's Structured Outputs validation.
- Handles edge cases for automated initial teams when subagents bypass standard creation routines.
- Aborts sending unsupported experimental backend parameters like temperature and top_p for GPT-5 derivatives.
Load nested SKILL.md files from .claude/skills and namespace them with colons so category-based skill layouts work in Claude Code clients.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The /login platform_setup screen only listed Amazon Bedrock,
Microsoft Foundry, and Vertex AI — OpenAI-compatible providers
and Gemini were completely absent, leaving users with no guidance
on how to use OpenClaude's main feature.
Changes:
- Selector label: "Amazon Bedrock, Microsoft Foundry, or Vertex AI"
→ "OpenAI, Gemini, Bedrock, Ollama, and more"
- Description updated to mention OpenAI-compatible providers and Gemini
- Added OpenAI and Gemini env var instructions to the docs list
Fixes#43 (login screen confusion for Gemini users).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
CLAUDE_CODE_USE_GEMINI was missing from the is3P check in
isAnthropicAuthEnabled(), causing Gemini users to see the
Anthropic login screen at startup even with GEMINI_API_KEY set.
isAnthropicAuthEnabled() returns true when is3P is false, which
triggers the OAuth/login flow. Since CLAUDE_CODE_USE_GEMINI was
not included, Gemini was not treated as a 3P provider here,
showing the gcloud/Anthropic login prompt unexpectedly.
Fix: add CLAUDE_CODE_USE_GEMINI to the is3P check, consistent
with how CLAUDE_CODE_USE_OPENAI is handled in the same block.
Fixes#43.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The proxy bypass logic assigned port 80 to any non-https protocol,
including wss:// whose default port is 443. A NO_PROXY entry like
example.com:443 would not match wss://example.com because the port
was incorrectly resolved to 80.
Relates to #40
Co-Authored-By: Juan Camilo <juancamilo.auriti@gmail.com>
The /status panel showed 'undefined' for the API provider label when
using OpenAI or Gemini providers, and did not display the base URL or
model name. Added provider labels and property sections for both.
Relates to #39
Co-Authored-By: Juan Camilo <juancamilo.auriti@gmail.com>
DeepSeek V3 documentation specifies 128k context window for both
deepseek-chat and deepseek-reasoner. The previous 64k value caused
premature compaction and underutilization of available context.
Relates to #39
Co-Authored-By: Juan Camilo <juancamilo.auriti@gmail.com>
Some providers send an empty string as the first delta to signal
streaming start. The falsy check `if (delta.content)` treated "" as
absent, skipping content_block_start. The next delta with actual
content was emitted without it, violating the Anthropic protocol.
Changed to `delta.content != null` to distinguish between absent field
and empty string.
Relates to #42
Co-Authored-By: Juan Camilo <juancamilo.auriti@gmail.com>
OpenAI and Codex enforce strict JSON Schema validation — every key in
`properties` must also appear in `required`. Anthropic schemas often
mark fields as optional (omitted from `required`), which causes 400
errors on OpenAI/Codex endpoints.
Example: the Agent tool has `subagent_type` in `properties` but not
in `required`, producing:
"Invalid schema for function 'Agent': Missing 'subagent_type'
in required array"
Fix: add `normalizeSchemaForOpenAI()` in `convertTools()` that ensures
`required` is a superset of all `properties` keys before the schema is
sent to the API. Existing `required` entries are preserved; missing
ones are appended. Schemas without `properties` pass through unchanged.
Fixes#46.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
