mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
4145 commits 895 branches 10 tags 1.7 GiB
Commit graph

3 commits

Author SHA1 Message Date
Austin Pickett
e88aa8a58c feat(web): re-apply dashboard UI improvements on top of i18n 
Re-applies changes from #9471 that were overwritten by the i18n PR:

- URL-based routing via react-router-dom (NavLink, Routes, BrowserRouter)
- Replace emoji icons with lucide-react in ConfigPage and SkillsPage
- Sidebar layout for ConfigPage, SkillsPage, and LogsPage
- Custom dropdown Select component (SelectOption) in CronPage
- Remove all non-functional rounded borders across the UI
- Fixed header with proper content offset

Made-with: Cursor
 2026-04-14 10:23:43 -04:00
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