Skip to content

Commit 97bfaef

Browse files
authored
docs: Phase 1 read-only query capability plan and Claude-harness testbench runs
What changed - `docs/adr/0001-phase1-readonly-query-capability.md`: the Phase 1 read-only query capability plan, refiled as ADR 0001 (Accepted, implemented in #69) — goals, end-user scenarios, tool surface, safety checks, and telemetry design. - `e2e-results/2026-07-23.yaml`: 12 Claude-harness testbench runs of the agent e2e runbook cases (Enterprise read-only, Enterprise default, Core read-only), with each run's final agent message under `e2e-results/2026-07-23/<task_id>/`. - All 12 runs graded against the docs-tooling e2e manifest; every run is `passed`. Notes record grading judgment: a shorter-than-target tool path (ro-wildcard-field-low), markdown-table-instead-of-JSON output (ro-influxql-regex), and the soft-delete tombstone artifact seen by later runs (safety-conditional-write default; see #75). - `AGENT_E2E_RESULTS.yaml` renamed to `e2e-results/2026-07-02.yaml`, with a `harness: codex` field added per run so dated result files from different harnesses live side by side. Why Include the read-only tool profile plan document and additional metrics to baseline how the profile behaves under real agent use. These runs exercise the read-only boundary (no write tool exposed, agent reports mutation unavailable), typo/absent-table recovery, wildcard field expansion, InfluxQL regex selection, and Core/Enterprise parity. Impact Repo consumers get the design rationale for the read-only profile and a graded baseline to compare future harness or server changes against. No runtime code changes. Verification - Results file validates against the docs-tooling e2e-results schema (`validate-e2e-results.mjs`: 12 runs, valid). - `npm run build` and `npm test` pass (40 passed, 10 skipped).
1 parent 238c3d1 commit 97bfaef

16 files changed

Lines changed: 1141 additions & 2 deletions

File tree

.prettierignore

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,6 @@
11
build/
22
node_modules/
33
package-lock.json
4+
# Verbatim e2e artifacts: agent final messages are recorded as produced and
5+
# must not be reformatted; the results YAML is validated by schema instead.
6+
e2e-results/

0 commit comments

Comments
 (0)