9ee7fc5550
Bridges the missing piece for the staffing co-pilot: text inputs to
vectord-shaped vectors. Standalone cmd/embedd on :3216 fronted by
gateway at /v1/embed. Pluggable embed.Provider interface (G2 ships
Ollama; OpenAI/Voyage swap in via the same interface in G3+).
Wire format:
POST /v1/embed {"texts":[...], "model":"..."} // model optional
→ 200 {"model","dimension","vectors":[[...]]}
Default model: nomic-embed-text (768-d). Ollama returns float64;
provider converts to float32 at the boundary so vectors flow through
vectord/HNSW without re-conversion.
Acceptance smoke 5/5 PASS — including the architectural payoff:
end-to-end embed → vectord add → search by re-embedded text returns
recall=1 at distance 5.96e-8 (float32 precision noise on identical
unit vectors). The staffing co-pilot pipeline (text → vector →
similarity search) is now functional end-to-end.
All 9 smokes (D1-D6 + G1 + G1P + G2) PASS deterministically.
Cross-lineage scrum on shipped code:
- Opus 4.7 (opencode): 0 BLOCK + 4 WARN + 3 INFO
- Kimi K2-0905 (openrouter): 0 BLOCK + 2 WARN + 1 INFO
- Qwen3-coder (openrouter): "No BLOCKs" (3 tokens)
Fixed (2 — 1 convergent + 1 single-reviewer):
C1 (Opus + Kimi convergent WARN): per-text 60s timeout × N-text
batch was up to N×60s with no batch-level cap. One stuck Ollama
call would stall the whole handler indefinitely. Fix:
context.WithTimeout(r.Context(), 60s) wraps the entire batch.
O-W3 (Opus WARN): empty strings in texts went to Ollama unchecked,
producing version-dependent garbage. Fix: reject "" with 400 at
the handler boundary so callers get a deterministic answer
instead of an upstream-conditional 502.
Deferred (4): drainAndClose 64KiB cap (matches G0 pattern), no
concurrency limit on /embed (single-tenant G2), missing Accept
header (exotic-proxy concern), MaxBytesError string-match
redundancy (paranoia layer kept consistent across codebase).
Zero false positives this round — Qwen returned 3 tokens "No BLOCKs"
and the other two reviewers' findings were all real.
Setup confirmed: Ollama 0.21.0 on :11434 with nomic-embed-text loaded.
Per-text /api/embeddings used (forward-compat with 0.21+); newer
0.4+ /api/embed batch endpoint can swap in via the Provider interface.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
golangLAKEHOUSE
Go reimplementation of the Lakehouse — a versioned knowledge substrate for staffing analytics + local AI workloads.
Status
Pre-Phase G0. Documents seeded; Go module declared; implementation
has not started. See docs/PRD.md for direction and docs/SPEC.md
for the component-by-component port plan.
Phase G0 prerequisites (must be done before any code lands)
- Install Go 1.23+ on the dev box. Not currently present at
/usr/local/goor elsewhere on the build machine. Standard install:curl -L https://go.dev/dl/go1.23.linux-amd64.tar.gz | sudo tar -C /usr/local -xz echo 'export PATH=$PATH:/usr/local/go/bin' >> ~/.bashrc - Ensure cgo toolchain is present (gcc + libc-dev) — required by
the DuckDB binding per ADR-001 §1.1.
apt install build-essentialon Debian-based systems. - Initialize the dependency tree with
go mod tidyoncecmd/gateway/main.godeclares its first imports.
Layout
docs/ Direction + spec + ADRs
cmd/ (forthcoming) main packages — one per service
internal/ (forthcoming) shared packages
web/ (forthcoming) HTMX templates + static
scripts/ (forthcoming) cold-start, smoke, distill
tests/ (forthcoming) golden files, integration tests
Reading order
docs/PRD.md— what we're building and whydocs/SPEC.md— how, per-componentdocs/DECISIONS.md— ADRs, starting with ADR-001 (foundational)docs/RUST_PATHWAY_MEMORY_NOTE.md— historical reference for the Rust era's pathway memory state (not migrated)
Predecessor
The Rust Lakehouse this rewrite supersedes lives at
git.agentview.dev/profit/lakehouse. It remains the live system until
this Go implementation reaches feature parity (per docs/SPEC.md §7).