indifferentketchup/boocode
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
8bd32537cf682369b9f49926db71c173b39e8d01
boocode/openspec/changes/multi-llama-swap-providers-model-favorites/tasks.md
indifferentketchup b18de2a331 chore: snapshot working tree - pty_exited notifications + in-flight inference WIP 
feat(booterm): structured pty_exited WS notifications. Plan-validated, impl-validated, code-reviewed green (contracts build clean, contracts test 29/29, booterm + web typecheck clean).

wip: in-progress inference/provider refactor (agents.ts, provider.ts, new llama-providers.ts, removed llama-args-validator), plus arena, dispatcher, compaction, schema changes.

openspec: pty-exit-notifications complete; x-agent-flags planned (not yet implemented).
2026-06-14 12:48:47 +00:00

5.0 KiB
Raw Blame History

multi-llama-swap-providers-model-favorites — tasks

P0 — config and contracts

  • Add a shared local-provider config schema under packages/contracts.
  • Add LLAMA_PROVIDERS_PATH to apps/server/src/config.ts and apps/coder/src/config.ts.
  • Add data/llama-providers.example.json with sam-desktop and embedding.
  • Implement a loader that falls back to the legacy single-provider env vars when the shared file is missing.

P1 — model identity helpers

  • Add shared parsing/formatting helpers for composite model IDs: provider/model.
  • Preserve indefinite support for legacy bare IDs by resolving them to the configured default provider.
  • Update display-name helpers to strip only the provider prefix intended for presentation, not for routing/cache identity.

P2 — server model catalog and routing

  • Refactor apps/server/src/routes/models.ts to emit a provider-aware model catalog with composite IDs.
  • Refactor apps/server/src/services/inference/provider.ts to resolve route and base URL from provider identity instead of string heuristics alone.
  • Make sidecar routing a per-provider attribute so embedding/* never hits LLAMA_SIDECAR_URL.
  • Replace the bare deepseek- prefix special case with provider-aware handling for DeepSeek models.

P3 — server call sites that currently assume one endpoint

  • Update apps/server/src/services/model-context.ts to fetch upstream props from the resolved provider and key caches by the full composite ID.
  • Update apps/server/src/services/compaction.ts to use the resolved provider endpoint for summaries.
  • Update apps/server/src/services/task-model.ts to resolve fallback models through the same provider-aware endpoint logic.
  • Verify any other direct LLAMA_SWAP_URL usage in apps/server is either migrated or explicitly documented as legacy-only.

P4 — favorites persistence

  • Add favorite_models handling to apps/server/src/routes/settings.ts.
  • Define normalization rules for malformed, duplicate, or unavailable favorites.
  • Ensure unavailable favorites are hidden from visible picker sections but never auto-deleted from settings.
  • Keep favorites out of the server model-catalog payload; derive the Favorites section in the clients from settings + provider-aware inventory.

P5 — BooChat UI

  • Update apps/web/src/components/ModelPicker.tsx to render: Favorites first, then provider sections.
  • Add a per-model favorite toggle wired to PATCH /api/settings.
  • Keep favorited models visible in their provider group as well as the Favorites section.
  • Verify session model changes write composite IDs for new selections.

P6 — BooCoder snapshot, dispatch, and arena

  • Update apps/coder/src/services/provider-snapshot.ts so BooCode's local boocode provider models retain composite IDs in snapshot data.
  • Update the compact picker in apps/web/src/components/AgentComposerBar.tsx to match the grouped/favorite behavior used by BooChat for native local models.
  • Update apps/coder/src/services/arena-model-call.ts and apps/coder/src/services/arena-analyzer.ts to use provider-aware routing.

P7 — external-agent parity decision (opencode)

  • Decide whether the first slice includes opencode multi-provider local models or explicitly limits parity to native boocode.
  • If opencode parity is included, add a provider-identity-preserving bridge instead of collapsing to llama-swap/<wireModelId>.
  • Preferred bridge: a BooCoder-hosted OpenAI-compatible local-model gateway for consumers that still assume one provider namespace.
  • If the bridge is deferred, stop advertising multi-provider local models under the opencode provider until the bridge exists.

P8 — tests and verification

  • Add unit tests for model-ref parsing, legacy bare-ID fallback, and provider-aware routing.
  • Add tests covering the embedding/deepseek-r1-qwen3-8b collision case.
  • Add tests proving duplicate model names on two hosts do not share context cache entries.
  • Add UI or route tests for favorites hide-not-delete behavior. (apps/server/src/routes/__tests__/settings-favorites.test.ts, DB-gated: unavailable favorite persists through PATCH/GET and unrelated writes; removal is explicit-only.)
  • Smoke test native BooChat/BooCoder against: sam-desktop, embedding, and DeepSeek-enabled configs. (API layer verified 2026-06-12: both hosts healthy, /api/models serving grouped composite ids live. Remaining: in-browser send-a-message pass per provider group + a DeepSeek-enabled config.)
  • If opencode parity ships in-scope, add a smoke test proving duplicate local model names still route to the intended provider. (apps/coder/src/services/__tests__/local-gateway-routing.test.ts: resolver + HTTP-route level — same wire name routes to distinct baseUrls with the bare wire id upstream; unknown provider → 400, no upstream call.)
Reference in New Issue View Git Blame Copy Permalink