gemini(w2): AI marker comment-spam inventory #114

New issue

Open

opened 2026-05-28 01:20:41 +02:00 by codex · 1 comment

codex commented

2026-05-28 01:20:41 +02:00

Collaborator

Parent: #2
Agent lane: Gemini 3.5 Flash
Wave: 2 / board maturity
Risk class: low

Goal

Find where AI-created markers still create noisy normal comments instead of system/audit cues.

Context refs

docs/agent-mcp-contract.md
docs/kan-ductor-working-pr-plan.md

Scope

Search create/comment/AI marker code paths.
List whether markers render as comments, activity, audit, or collapsed notes.
Recommend the smallest cleanup.

Acceptance

Inventory covers API, MCP, and web display paths.
No raw sourceRef leaks in user-facing marker examples.
Follow-up patch is optional and small.

Suggested checks

rg -n "AI suggested|AI-created|sourceRef|marker|agentAudit" packages apps docs

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: 2 / board maturity Risk class: low ## Goal Find where AI-created markers still create noisy normal comments instead of system/audit cues. ## Context refs - `docs/agent-mcp-contract.md` - `docs/kan-ductor-working-pr-plan.md` ## Scope - Search create/comment/AI marker code paths. - List whether markers render as comments, activity, audit, or collapsed notes. - Recommend the smallest cleanup. ## Acceptance - Inventory covers API, MCP, and web display paths. - No raw sourceRef leaks in user-facing marker examples. - Follow-up patch is optional and small. ## Suggested checks - `rg -n "AI suggested|AI-created|sourceRef|marker|agentAudit" packages apps docs` ## 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 01:20:41 +02:00

Iskra commented

2026-06-15 03:13:55 +02:00

Collaborator

Iskra judgment

Field	Value
Target	`pdurlej/kan-ductor#issue#114`
Priority	p2
Action	observe
Scores	reach 4 / impact 3 / confidence 5
Piotr fit	high
Effort	small
Labels	`judge/p2`
Judge	`iskra` via `openclaw`

Rationale: This is P2 observe-first UI and audit hygiene because AI marker comment spam can blur agent provenance and leak implementation details into user-facing Kan context.

Caveat: Keep this as inventory or a tiny cleanup and ensure user-facing marker examples do not expose raw sourceRef or widen write authority.

Structured openclaw.judge.v0 payload

<!-- openclaw.judge.v0 -->
{
  "confidence": 5,
  "effort_hint": "small",
  "escalation": {
    "kind": "none",
    "reason": ""
  },
  "evidence_refs": [
    {
      "note": "Issue scopes a scout inventory of AI-created markers that may still render as noisy normal comments instead of audit or system cues.",
      "type": "forgejo",
      "value": "issue-title-body-labels-and-target-snapshot"
    },
    {
      "note": "Body requires API, MCP, and web display paths to be covered and raw sourceRef leaks avoided in examples.",
      "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": 3,
  "judge_actor": {
    "name": "iskra",
    "runtime": "openclaw"
  },
  "judged_at": "2026-06-15T01:13:00Z",
  "labels_to_apply": [
    "judge/p2"
  ],
  "piotr_fit": "high",
  "priority": "p2",
  "rationale_summary": "This is P2 observe-first UI and audit hygiene because AI marker comment spam can blur agent provenance and leak implementation details into user-facing Kan context.",
  "reach": 4,
  "recommended_next_action": "observe",
  "rerun_reason": "no_prior_judgment",
  "schema": "openclaw.judge.v0",
  "target": {
    "kind": "issue",
    "number": 114,
    "repo": "pdurlej/kan-ductor"
  },
  "target_snapshot": {
    "body_hash": "sha256:631d9745348cfff7472863a0d4a61443d6ee61787b54b06cbeb46fe7f012c868",
    "commit_count": null,
    "evidence_hash": "sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
    "head_sha": null,
    "labels": [
      "gemini-flash",
      "priority:p2",
      "safety",
      "scout",
      "small-task",
      "ui"
    ],
    "labels_hash": "sha256:32a2d84171ef04773ff046be8adbdf1af9e59850c93ff9e87536616d457b14b9",
    "state": "open",
    "title_hash": "sha256:ef65c8af2e1e981e67d7a89e3bc21cbf8a6798d76162f98703faaa2a99bc7b8a",
    "updated_at": "2026-05-28T01:20:41+02:00"
  },
  "top_caveat": "Keep this as inventory or a tiny cleanup and ensure user-facing marker examples do not expose raw sourceRef or widen write authority."
}
<!-- /openclaw.judge.v0 -->

### Iskra judgment | Field | Value | | --- | --- | | Target | `pdurlej/kan-ductor#issue#114` | | Priority | p2 | | Action | observe | | Scores | reach 4 / impact 3 / confidence 5 | | Piotr fit | high | | Effort | small | | Labels | `judge/p2` | | Judge | `iskra` via `openclaw` | **Rationale:** This is P2 observe-first UI and audit hygiene because AI marker comment spam can blur agent provenance and leak implementation details into user-facing Kan context. **Caveat:** Keep this as inventory or a tiny cleanup and ensure user-facing marker examples do not expose raw sourceRef or widen write authority. <details> <summary>Structured openclaw.judge.v0 payload</summary> ```json  { "confidence": 5, "effort_hint": "small", "escalation": { "kind": "none", "reason": "" }, "evidence_refs": [ { "note": "Issue scopes a scout inventory of AI-created markers that may still render as noisy normal comments instead of audit or system cues.", "type": "forgejo", "value": "issue-title-body-labels-and-target-snapshot" }, { "note": "Body requires API, MCP, and web display paths to be covered and raw sourceRef leaks avoided in examples.", "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": 3, "judge_actor": { "name": "iskra", "runtime": "openclaw" }, "judged_at": "2026-06-15T01:13:00Z", "labels_to_apply": [ "judge/p2" ], "piotr_fit": "high", "priority": "p2", "rationale_summary": "This is P2 observe-first UI and audit hygiene because AI marker comment spam can blur agent provenance and leak implementation details into user-facing Kan context.", "reach": 4, "recommended_next_action": "observe", "rerun_reason": "no_prior_judgment", "schema": "openclaw.judge.v0", "target": { "kind": "issue", "number": 114, "repo": "pdurlej/kan-ductor" }, "target_snapshot": { "body_hash": "sha256:631d9745348cfff7472863a0d4a61443d6ee61787b54b06cbeb46fe7f012c868", "commit_count": null, "evidence_hash": "sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "head_sha": null, "labels": [ "gemini-flash", "priority:p2", "safety", "scout", "small-task", "ui" ], "labels_hash": "sha256:32a2d84171ef04773ff046be8adbdf1af9e59850c93ff9e87536616d457b14b9", "state": "open", "title_hash": "sha256:ef65c8af2e1e981e67d7a89e3bc21cbf8a6798d76162f98703faaa2a99bc7b8a", "updated_at": "2026-05-28T01:20:41+02:00" }, "top_caveat": "Keep this as inventory or a tiny cleanup and ensure user-facing marker examples do not expose raw sourceRef or widen write authority." }  ``` </details>

Iskra added the

judge/p2

label

2026-06-15 03:13:55 +02:00