fix: use updated ollama ai package

memory-bank/activeContext.md

@@ -26,14 +26,15 @@ Docs directory created with 4 files (PRD.md, Architecture.md, API.md, Discoverie
 5. [x] Provider resolution uses explicit provider from config (no model prefix parsing)
 6. [x] Typecheck and lint pass (0 errors)
 7. [x] Test onboard and agent commands work correctly
-8. [ ] Test with a real Mattermost config (optional — user can do this)
+8. [x] Updated Ollama provider from `ollama-ai-provider` to `ai-sdk-ollama`
+9. [ ] Test with a real Mattermost config (optional — user can do this)
 
 ## Key Decisions Made
 - Mattermost channel uses raw WebSocket + fetch (no mattermostdriver, no SSL hack)
 - No MCP support (use shell tools / CLI instead)
 - No reasoning/thinking token handling (can add later)
 - Config is fresh Zod schema (no migration from Python config needed)
-- `ollama-ai-provider` package (not `@ai-sdk/ollama` which 404s on npm)
+- `ai-sdk-ollama` package for Ollama provider (replaced old `ollama-ai-provider`)
 - `strArg(args, key, fallback?)` helper exported from `agent/tools/base.ts` for safe unknown→string extraction
 - Agent config requires explicit `provider` field (no more model prefix like "anthropic/claude-...")
 - Model names are now just the raw model ID (e.g., "claude-sonnet-4-5" not "anthropic/claude-sonnet-4-5")