Commit Graph

14 Commits

Author SHA1 Message Date
0xallam e09b5b42c1 fix: Prevent assistant-message prefill rejected by Claude 4.6 2026-02-20 08:29:01 -08:00
0xallam 3b3576b024 refactor: Centralize strix model resolution with separate API and capability names
- Replace fragile prefix matching with explicit STRIX_MODEL_MAP
- Add resolve_strix_model() returning (api_model, canonical_model)
- api_model (openai/ prefix) for API calls to OpenAI-compatible Strix API
- canonical_model (actual provider name) for litellm capability lookups
- Centralize resolution in LLMConfig instead of scattered call sites
2026-02-20 04:40:04 -08:00
octovimmer d2c99ea4df resolve: merge conflict resolution, llm api base resolution 2026-02-19 17:37:00 -08:00
octovimmer 06ae3d3860 fix: linting errors 2026-02-19 17:25:10 -08:00
octovimmer e38f523a45 Strix LLM Documentation and Config Changes (#315)
* feat: add to readme new keys

* feat: shoutout strix models, docs

* fix: mypy error

* fix: base api

* docs: update quickstart and models

* fixes: changes to docs

uniform api_key variable naming

* test: git commit hook

* nevermind it was nothing

* docs: Update default model to claude-sonnet-4.6 and improve Strix Router docs

- Replace gpt-5 and opus-4.6 defaults with claude-sonnet-4.6 across all docs and code
- Rewrite Strix Router (models.mdx) page with clearer structure and messaging
- Add Strix Router as recommended option in overview.mdx and quickstart prerequisites
- Update stale Claude 4.5 references to 4.6 in anthropic.mdx, openrouter.mdx, bug_report.md
- Fix install.sh links to point to models.strix.ai and correct docs URLs
- Update error message examples in main.py to use claude-sonnet-4-6

---------

Co-authored-by: 0xallam <ahmed39652003@gmail.com>
2026-02-20 01:43:18 +04:00
0xallam c2fbf81f1d fix(llm): Pass API key and base URL to memory compressor litellm calls
The memory compressor was calling litellm.completion() without passing
the api_key and api_base parameters, causing authentication errors when
LLM_API_KEY is set but provider-specific env vars (OPENAI_API_KEY, etc.)
are not. This matches the pattern used in dedupe.py.
2026-01-28 01:29:33 -08:00
0xallam 56526cbf90 fix(agent): fix agent loop hanging and simplify LLM module
- Fix agent loop getting stuck by adding hard stop mechanism
- Add _force_stop flag for immediate task cancellation across threads
- Use thread-safe loop.call_soon_threadsafe for cross-thread cancellation
- Remove request_queue.py (eliminated threading/queue complexity causing hangs)
- Simplify llm.py: direct acompletion calls, cleaner streaming
- Reduce retry wait times to prevent long hangs during retries
- Make timeouts configurable (llm_max_retries, memory_compressor_timeout, sandbox_execution_timeout)
- Keep essential token tracking (input/output/cached tokens, cost, requests)
- Maintain Anthropic prompt caching for system messages
2026-01-14 18:54:45 -08:00
0xallam 83efe3816f feat: add centralized Config class with auto-save to ~/.strix/cli-config.json
- Add Config class with all env var defaults in one place
- Auto-load saved config on startup (env vars take precedence)
- Auto-save config after successful LLM warm-up
- Replace scattered os.getenv() calls with Config.get()

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-10 15:49:03 -08:00
Ahmed Allam 1abfb360e4 feat: add configurable timeout for LLM requests 2025-11-12 18:58:03 +04:00
Ahmed Allam 9a9a7268cd Better handling of LLM request failures 2025-09-10 15:39:01 -07:00
Ahmed Allam 337d64d362 Adding full support for gpt-5 models (#5) 2025-08-15 21:02:39 +01:00
Ahmed Allam 5207cdc90c Reverting back to claude as default 2025-08-11 18:28:46 -07:00
Ahmed Allam 139faed8ed Use gpt-5 as default 2025-08-11 18:00:24 -07:00
Ahmed Allam 81ac98e8b9 Open-source release for Alpha version 2025-08-08 20:36:44 -07:00