pdurlej/kan-ductor

Fork 0

gemini(w4): long-history flow metrics window fixture #122

New issue

Open

opened 2026-05-28 01:20:42 +02:00 by codex · 2 comments

codex commented

2026-05-28 01:20:42 +02:00

Collaborator

Parent: #2
Agent lane: Gemini 3.5 Flash
Wave: 4 / analytics foundation
Risk class: low

Goal

Prevent transitionLimit from hiding recent completions in long histories.

Context refs

Open issue #57
docs/agent-mcp-contract.md flow metrics

Scope

Build fixture with long old transition history plus recent completions.
Assert since/until is applied at DB/query layer before safety cap.
Keep fixture cheap.

Acceptance

Recent window metrics are correct despite old transitions.
transitionLimit remains a cap, not a semantic filter.
Test would fail on the historical bug.

Suggested checks

Flow metrics targeted tests.

Non-goals / fences

Do not deploy, restart production, rotate secrets, or run production migrations.
Do not widen MCP write authority or public exposure.
Keep the change small enough for one focused PR or one scouting report.

Expected output

A short PR or issue comment with findings, touched files, tests run, and remaining risks.

Parent: #2 Agent lane: Gemini 3.5 Flash Wave: 4 / analytics foundation Risk class: low ## Goal Prevent `transitionLimit` from hiding recent completions in long histories. ## Context refs - Open issue #57 - `docs/agent-mcp-contract.md` flow metrics ## Scope - Build fixture with long old transition history plus recent completions. - Assert `since/until` is applied at DB/query layer before safety cap. - Keep fixture cheap. ## Acceptance - Recent window metrics are correct despite old transitions. - `transitionLimit` remains a cap, not a semantic filter. - Test would fail on the historical bug. ## Suggested checks - Flow metrics targeted tests. ## Non-goals / fences - Do not deploy, restart production, rotate secrets, or run production migrations. - Do not widen MCP write authority or public exposure. - Keep the change small enough for one focused PR or one scouting report. ## Expected output A short PR or issue comment with findings, touched files, tests run, and remaining risks.

codex added the

labels

2026-05-28 01:20:42 +02:00

codex referenced this issue from a commit

2026-05-29 00:27:46 +02:00

fix(agent): correctly compute lead/cycle time for completions traversing flow metrics window boundaries (#122)

gemini referenced this issue from a pull request that will close it,

2026-05-29 00:27:54 +02:00

fix(agent): correctly compute lead/cycle time for completions traversing flow metrics window boundaries (#122) #139

codex referenced this issue

2026-06-03 08:51:00 +02:00

fix(agent): salvage Gemini regression fixtures #140

codex commented

2026-06-03 10:20:03 +02:00

Author

Collaborator

Codex verification on current origin/main (966de964...): #122 is already covered by current code and integration tests.

Evidence:

packages/api/src/routers/agent.ts#buildFlowMetrics queries transition history with since/until before applying transitionLimit.
It seeds createdAt from current cards and has a second targeted getTransitionHistory pass for completed cards missing cycleStartAt, so completions whose cycle start is before the requested window still get cycle-time samples.
packages/api/integration-tests/agent.integration.test.ts includes computes flow metrics from the requested window before applying transition limits:
- creates 130 old completed cards plus 5 recent completions,
- calls getFlowMetrics with transitionLimit: 100,
- asserts throughput returns the 5 recent cards,
- asserts leadTime.sampleSize === 5, cycleTime.sampleSize === 5, and transitionsTruncated === false.

Verification run:

pnpm --filter @kan/api exec vitest integration-tests/agent.integration.test.ts --run -t "computes flow metrics from the requested window"

Passed. Recommendation: close #122 as already satisfied by current main.

Codex verification on current `origin/main` (`966de964...`): #122 is already covered by current code and integration tests. Evidence: - `packages/api/src/routers/agent.ts#buildFlowMetrics` queries transition history with `since`/`until` before applying `transitionLimit`. - It seeds `createdAt` from current cards and has a second targeted `getTransitionHistory` pass for completed cards missing `cycleStartAt`, so completions whose cycle start is before the requested window still get cycle-time samples. - `packages/api/integration-tests/agent.integration.test.ts` includes `computes flow metrics from the requested window before applying transition limits`: - creates 130 old completed cards plus 5 recent completions, - calls `getFlowMetrics` with `transitionLimit: 100`, - asserts throughput returns the 5 recent cards, - asserts `leadTime.sampleSize === 5`, `cycleTime.sampleSize === 5`, and `transitionsTruncated === false`. Verification run: ```bash pnpm --filter @kan/api exec vitest integration-tests/agent.integration.test.ts --run -t "computes flow metrics from the requested window" ``` Passed. Recommendation: close #122 as already satisfied by current main.

Iskra commented

2026-06-18 03:08:29 +02:00

Collaborator

Iskra judgment

Field	Value
Target	`pdurlej/kan-ductor#issue#122`
Priority	p2
Action	observe
Scores	reach 4 / impact 4 / confidence 5
Piotr fit	high
Effort	small
Labels	`judge/p2`
Judge	`iskra` via `openclaw`

Rationale: This is P2 observe-first analytics testing because transitionLimit must remain a safety cap rather than silently filtering out recent flow metrics.

Caveat: Keep the fixture cheap and scoped; do not change metric semantics beyond proving window filtering precedes the safety cap.

Structured openclaw.judge.v0 payload

<!-- openclaw.judge.v0 -->
{
  "confidence": 5,
  "effort_hint": "small",
  "escalation": {
    "kind": "none",
    "reason": ""
  },
  "evidence_refs": [
    {
      "note": "Issue scopes a flow-metrics fixture to ensure recent completions are not hidden by long old transition histories.",
      "type": "forgejo",
      "value": "issue-title-body-labels-and-target-snapshot"
    },
    {
      "note": "Body requires since/until filtering to be applied at query layer before transitionLimit safety cap.",
      "type": "forgejo",
      "value": "issue-body-scope-and-acceptance"
    },
    {
      "note": "Body fences the work away from production deploys, migrations, authority widening, and exposure changes.",
      "type": "forgejo",
      "value": "issue-body-non-goals"
    }
  ],
  "impact": 4,
  "judge_actor": {
    "name": "iskra",
    "runtime": "openclaw"
  },
  "judged_at": "2026-06-18T01:08:00Z",
  "labels_to_apply": [
    "judge/p2"
  ],
  "piotr_fit": "high",
  "priority": "p2",
  "rationale_summary": "This is P2 observe-first analytics testing because transitionLimit must remain a safety cap rather than silently filtering out recent flow metrics.",
  "reach": 4,
  "recommended_next_action": "observe",
  "rerun_reason": "no_prior_judgment",
  "schema": "openclaw.judge.v0",
  "target": {
    "kind": "issue",
    "number": 122,
    "repo": "pdurlej/kan-ductor"
  },
  "target_snapshot": {
    "body_hash": "sha256:406919a6f0953a1046c1d318ebd7ef946f2ff0637f0bc0bc394437a7eeb580c5",
    "commit_count": null,
    "evidence_hash": "sha256:54be38007f7bb0632996d14b02b6e9364ebff2a590a559cf52a26ff91fc52341",
    "head_sha": null,
    "labels": [
      "analytics",
      "gemini-flash",
      "priority:p2",
      "small-task",
      "tests"
    ],
    "labels_hash": "sha256:fb5a1d5bb7bb666df34dd3de5a47748013df5c087589f0d29c6dc5ad08f3de4e",
    "state": "open",
    "title_hash": "sha256:de6a257514b540cfb947af0313363c2cbb5746046a6fc8d94a56301db9e7f7f0",
    "updated_at": "2026-06-03T10:20:03+02:00"
  },
  "top_caveat": "Keep the fixture cheap and scoped; do not change metric semantics beyond proving window filtering precedes the safety cap."
}
<!-- /openclaw.judge.v0 -->

### Iskra judgment | Field | Value | | --- | --- | | Target | `pdurlej/kan-ductor#issue#122` | | Priority | p2 | | Action | observe | | Scores | reach 4 / impact 4 / confidence 5 | | Piotr fit | high | | Effort | small | | Labels | `judge/p2` | | Judge | `iskra` via `openclaw` | **Rationale:** This is P2 observe-first analytics testing because transitionLimit must remain a safety cap rather than silently filtering out recent flow metrics. **Caveat:** Keep the fixture cheap and scoped; do not change metric semantics beyond proving window filtering precedes the safety cap. <details> <summary>Structured openclaw.judge.v0 payload</summary> ```json  { "confidence": 5, "effort_hint": "small", "escalation": { "kind": "none", "reason": "" }, "evidence_refs": [ { "note": "Issue scopes a flow-metrics fixture to ensure recent completions are not hidden by long old transition histories.", "type": "forgejo", "value": "issue-title-body-labels-and-target-snapshot" }, { "note": "Body requires since/until filtering to be applied at query layer before transitionLimit safety cap.", "type": "forgejo", "value": "issue-body-scope-and-acceptance" }, { "note": "Body fences the work away from production deploys, migrations, authority widening, and exposure changes.", "type": "forgejo", "value": "issue-body-non-goals" } ], "impact": 4, "judge_actor": { "name": "iskra", "runtime": "openclaw" }, "judged_at": "2026-06-18T01:08:00Z", "labels_to_apply": [ "judge/p2" ], "piotr_fit": "high", "priority": "p2", "rationale_summary": "This is P2 observe-first analytics testing because transitionLimit must remain a safety cap rather than silently filtering out recent flow metrics.", "reach": 4, "recommended_next_action": "observe", "rerun_reason": "no_prior_judgment", "schema": "openclaw.judge.v0", "target": { "kind": "issue", "number": 122, "repo": "pdurlej/kan-ductor" }, "target_snapshot": { "body_hash": "sha256:406919a6f0953a1046c1d318ebd7ef946f2ff0637f0bc0bc394437a7eeb580c5", "commit_count": null, "evidence_hash": "sha256:54be38007f7bb0632996d14b02b6e9364ebff2a590a559cf52a26ff91fc52341", "head_sha": null, "labels": [ "analytics", "gemini-flash", "priority:p2", "small-task", "tests" ], "labels_hash": "sha256:fb5a1d5bb7bb666df34dd3de5a47748013df5c087589f0d29c6dc5ad08f3de4e", "state": "open", "title_hash": "sha256:de6a257514b540cfb947af0313363c2cbb5746046a6fc8d94a56301db9e7f7f0", "updated_at": "2026-06-03T10:20:03+02:00" }, "top_caveat": "Keep the fixture cheap and scoped; do not change metric semantics beyond proving window filtering precedes the safety cap." }  ``` </details>

Iskra added the

judge/p2

label

2026-06-18 03:08:30 +02:00