2 Commits

Author	SHA1	Message	Date
Teknium	62fb6b2cd8	fix: guard zero context length display + add 19 tests for model info ... - ModelInfoCard: hide card when effective_context_length <= 0 instead of showing 'Context Window: 0 auto-detected' - Add tests for _normalize_config_for_web model_context_length extraction - Add tests for _denormalize_config_from_web round-trip (write back, remove on zero, upgrade bare string to dict, coerce string input) - Add tests for CONFIG_SCHEMA ordering (model_context_length after model) - Add tests for GET /api/model/info endpoint (dict config, bare string, empty model, capabilities, graceful error handling)	2026-04-13 22:04:35 -07:00
kshitijk4poor	8fd3093f49	feat(web): add context window support to dashboard config ... - Add GET /api/model/info endpoint that resolves model metadata using the same 10-step context-length detection chain the agent uses. Returns auto-detected context length, config override, effective value, and model capabilities (tools, vision, reasoning, max output, model family). - Surface model.context_length as model_context_length virtual field in the config normalize/denormalize cycle. 0 = auto-detect (default), positive value overrides. Writing 0 removes context_length from the model dict on disk. - Add ModelInfoCard component showing resolved context window (e.g. '1M auto-detected' or '500K override — auto: 1M'), max output tokens, and colored capability badges (Tools, Vision, Reasoning, model family). - Inject ModelInfoCard between model field and context_length override in ConfigPage General tab. Card re-fetches on model change and after save. - Insert model_context_length right after model in CONFIG_SCHEMA ordering so the three elements (model input → info card → override) are adjacent.	2026-04-13 22:04:35 -07:00