Commit graph

3 commits

Author SHA1 Message Date
3ac9d89b98 Fix tool call tracking and streaming assembly for all providers
- agent/loop.go: Record assistant message with ToolCalls before tool results,
  and set ToolCallID on tool-result messages so follow-up requests have complete
  context (prevents models from losing track of already-attempted tools).

- llm/providers/llamacpp/client.go: Buffer fragmented tool call deltas during
  streaming, assemble them into complete calls when finish_reason arrives.
  Add ToolCalls, ToolCallID, Name fields to request building.

- llm/providers/openai/client.go: Send ToolCalls, ToolCallID, Name when
  building chat requests so messages are wire-format correct.

- llm/types.go: Add ToolCalls field to Message struct for serialization
  back into conversation history.

- agent/integration_test.go: Move integration test skip from TestMain to a
  per-test skipUnlessIntegration() so it doesn't hide other package tests.

- sandbox & tools: Add edge-case tests (relative traversal, array paths,
  non-path strings, zero-value guards, sentinel errors).
2026-07-08 16:11:57 -07:00
0652023037 feat(rag): add SQLite+FTS5 backend, fix content/usage plumbing bugs
Backend.Upsert never received the fragment's Content, so ChromaDB (and
any backend) stored the vector but silently dropped the actual text —
saved memories had nothing to retrieve later. Backend.Search now also
takes the raw query text, and a failed/missing embedding no longer
hard-fails Add/Search: it degrades to a nil vector so a lexical-capable
backend can still index/find the content (Chroma has no such fallback
and now says so explicitly instead of misbehaving).

Adds pkg/rag/backends/sqlitevec: a zero-dependency backend (pure-Go
SQLite, no external service) that does cosine similarity when a real
embedding vector is available and falls back to FTS5/BM25 full-text
search otherwise. Adds pkg/rag/embeddings.OpenAICompatible, covering
both a local llama.cpp server (`--embeddings` enabled) and real OpenAI
(or any OpenAI-shaped /embeddings endpoint) through the same client.

Also fixes token usage tracking for llama.cpp streaming: the client
never requested `stream_options.include_usage` nor parsed a usage-only
SSE event, and even when present, the agent loop's RunStream dropped
any chunk with no Delta/ReasoningDelta — silently discarding the only
chunk that carries usage.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-06 00:05:30 -07:00
641481022f feat(llm): add LLM client interface, types, providers (openai, llamacpp), and mock 2026-06-30 23:53:22 -07:00