Models not in the lookup table fall through to a 200k default, causing
auto-compact to never trigger for models with smaller actual context
windows. Users hit hard context_window_exceeded errors instead.
Added to both context window and max output token tables:
- o1, o1-mini, o1-preview, o1-pro (OpenAI reasoning models)
- llama3.2:1b, qwen3:8b, codestral (common Ollama models)
Relates to #248
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.
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).
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>
Without this fix, getContextWindowForModel() returns 200k for all OpenAI
models (the Claude default), causing two problems:
1. Auto-compact/warnings trigger at wrong thresholds (200k instead of 128k)
2. getModelMaxOutputTokens() returns 32k causing 400 errors from APIs that
cap output tokens lower (gpt-4o supports max 16384)
Fix:
- Add openaiContextWindows.ts with known context window sizes and max output
token limits for 30+ OpenAI-compatible models (OpenAI, DeepSeek, Groq,
Mistral, Ollama, LM Studio)
- Hook into getContextWindowForModel() so correct input limits are used
- Hook into getModelMaxOutputTokens() so correct output limits are sent,
preventing 400 "max_tokens is too large" errors
All existing warning, blocking, and auto-compact infrastructure works
automatically once the correct limits are returned.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
