wehub-resource-sync
b4fbd6fe9f
Deploy Site / deploy-vercel (push) Has been skipped
Deploy Site / deploy-docs (push) Has been skipped
Build Skills Index / build-index (push) Has been skipped
Build Skills Index / trigger-deploy (push) Waiting to run
CI / Deny unrelated histories (push) Has been skipped
CI / CI timing report (push) Blocked by required conditions
CI / Detect affected areas (push) Successful in 27m35s
CI / OSV scan (push) Failing after 4s
CI / Build&Test Docker image (push) Successful in 9s
CI / Supply-chain scan (push) Has been skipped
CI / Lint Docker scripts (push) Failing after 5m13s
CI / Check contributors (push) Failing after 12m8s
CI / Docs Site (push) Failing after 12m8s
CI / TypeScript (push) Failing after 12m8s
CI / Python lints (push) Failing after 12m9s
CI / Python tests (push) Failing after 12m9s
CI / Check uv.lock (push) Failing after 23m22s
CI / All required checks pass (push) Waiting to run
1.7 KiB
1.7 KiB
Tool Search live test harness
Runs five scenarios against a real model (Claude Haiku 4.5 via OpenRouter) to
verify that the bridge tools work end-to-end. Records transcripts in
scripts/out/.
Running
cd <repo root>
python3 scripts/tool_search_livetest.py # runs all 5 scenarios x 2 modes
python3 scripts/analyze_livetest.py # side-by-side report
Requires OPENROUTER_API_KEY set or present in ~/.hermes/.env.
What it verifies
| Scenario | Tests |
|---|---|
| A obvious_single | BM25 retrieval on an obvious tool name (github_create_issue) |
| B vague_paraphrased | Retrieval when the model has to paraphrase ("schedule meeting" → evt_create) |
| C multi_tool_chain | Multi-step task chaining two deferred tools (GitHub + Slack) |
| D core_plus_deferred | Mixed: core tool (read_file) called directly, deferred tool (Slack) via bridge |
| E no_tool_needed | Pure-knowledge prompt; verify no spurious tool_search invocations |
Each scenario runs with tool_search.enabled = on and again with off for an
A/B baseline. The harness records:
- bridge_calls (the tool_search / tool_describe / tool_call sequence the model emitted)
- underlying_tool_calls (what actually ran through the registry dispatcher)
- final_response, iteration count, elapsed time, any errors
Output structure
scripts/out/
<scenario>__enabled.json # tool_search ON
<scenario>__disabled.json # tool_search OFF
_summary.json # one-line summary across all runs
The 2026-05 baseline run is checked in for reference. Re-running may produce slightly different transcripts (the model is non-deterministic) but the expected_underlying_tools assertions should remain satisfied.