10 Commits

Author SHA1 Message Date
Ed Zynda 06bf6d087a feat(models): resolve SDK default URLs for all registered providers
- Add sdkDefaultBaseURL map covering the 14 npm SDKs that ship a
  hard-coded baseURL (groq, cerebras, mistral, xai, perplexity,
  togetherai, deepinfra, cohere, v0, aihubmix, venice, merge-gateway,
  openrouter, vercel gateway), so providers whose models.dev entry
  omits the api field still auto-route correctly.
- Extend npmToWireProtocol so these thin OpenAI-compatible wrappers
  route through fantasy's openaicompat provider.
- Add resolveTemplatedAPIURL to substitute ${VAR} placeholders for
  cloudflare-workers-ai, databricks, snowflake-cortex from the env,
  with friendly errors that name the missing vars.
- Wire amazon-bedrock and azure-cognitive-services aliases into the
  existing native handlers; add createGoogleVertexProvider for the
  google-vertex case.
- Expose kit.ResolveProviderBaseURL in the public SDK so embedders
  can introspect the effective endpoint before instantiating a Kit.
- Refresh embedded_models.json from models.dev (5113 -> 5121 models;
  139 providers unchanged).
2026-06-07 14:06:05 +03:00
Ed Zynda 7315c1dea7 chore(models): update embedded model database from models.dev
- Refresh internal/models/embedded_models.json with latest data
- Add providers: alibaba-token-plan, anyapi, snowflake-cortex
- 139 providers, 5113 models total
2026-06-04 15:35:43 +03:00
Ed Zynda 1a2f6da40f chore(models): refresh embedded models database from models.dev
- Bump provider count from 131 to 136
- Bump model count from 4817 to 4965
2026-05-29 15:09:26 +03:00
Ed Zynda 592f8dc84f chore(models): refresh embedded models.dev snapshot
- Sync internal/models/embedded_models.json from https://models.dev/api.json
- Providers: 114 → 131 (+17)
- Models: 4276 → 4817 (+541)
2026-05-19 15:11:01 +03:00
Ed Zynda 81240b075e chore: update all deps and fix acp-go-sdk v0.12.0 breaking changes
- Update all Go dependencies (bubbletea v2.0.6, fantasy v0.19.0,
  acp-go-sdk v0.12.0, mcp-go v0.49.0, and transitive deps)
- Replace SetSessionModel with SetSessionConfigOption to match new
  acp-go-sdk Agent interface (union type with ValueId/Boolean variants)
- Add ListSessions stub returning empty list (new required method)
- Refresh embedded_models.json from models.dev/api.json
- Update ACP smoke test: add initialize handshake, session/list,
  session/set_config_option, session/cancel, and fix update parsing
2026-04-22 11:55:40 +03:00
Ed Zynda 50f586ec8f chore(models): update embedded model database from models.dev
Update internal/models/embedded_models.json with the latest snapshot
from https://models.dev/api.json.

- Providers: 111 → 115 (+4)
- Models: 4,191 → 4,259 (+68)
2026-04-21 10:38:23 +03:00
Ed Zynda a67f514560 chore(models): refresh embedded models.dev database
- update internal/models/embedded_models.json from https://models.dev/api.json
- 110 → 111 providers, 4172 → 4191 models
2026-04-17 12:19:21 +03:00
Ed Zynda 65c6e9f797 refactor(models): decouple TUI progress from SDK dependency tree
- Remove direct internal/ui/progress import from internal/models/providers.go
- Add ProgressReaderFunc callback to ProviderConfig for dependency inversion
- Wire Bubble Tea progress reader via CLIOptions in cmd/root.go
- Add NewProgressReadCloser convenience wrapper in progress package
- SDK consumers (pkg/kit) no longer transitively pull bubbletea, lipgloss
  v2, or bubbles
- Update embedded_models.json from models.dev (110 providers, 4172 models)
2026-04-14 17:17:01 +03:00
Ed Zynda 46bf809715 chore(models): update embedded models.json from models.dev
- Providers: 97 -> 109 (+12 new)
- Models: 3039 -> 4156 (+1117 new)
- New providers: alibaba-coding-plan, alibaba-coding-plan-cn, clarifai,
  dinference, drun, llmgateway, perplexity-agent, tencent-coding-plan,
  the-grid-ai, xiaomi-token-plan-ams, xiaomi-token-plan-cn,
  xiaomi-token-plan-sgp
2026-04-06 09:50:43 +03:00
Ed Zynda 71bdc768be feat: replace catwalk with models.dev, auto-route openai-compatible providers, fix all lint issues
Replace catwalk dependency with direct models.dev integration (97 providers,
3039 models vs catwalk's 22/679). Auto-route @ai-sdk/openai-compatible
providers through fantasy's openaicompat using the api URL from models.dev,
eliminating the need for --provider-url. Add --all flag to 'mcphost models'
to show all providers vs just fantasy-compatible ones.

Fix all 74 golangci-lint issues: errcheck (53), staticcheck SA4006 (24),
SA9003 (2), ST1005 (5), ineffassign (3). Restructure styles.go color
handling into a colorScheme struct to eliminate SA4006 false positives
from new(x) syntax.
2026-02-25 22:51:45 +03:00