[gjkim42]

What type of PR is this?

/kind cleanup

What this PR does / why we need it:

Updates the autonomous discovery issue-slot prompts for Kelos, Agora, and Kanon so every managed issue:

• starts its title with the owning TaskSpawner name in brackets;
• is revalidated against the current repository and related work before it is retained;
• records one replaceable Latest verdict section with status, timestamp, and evidence; and
• is replaced or closed when its tracked problem is no longer valid.

Verdict-only refreshes and invalid-slot closure preserve existing labels. The
prompts add triage-accepted only when replacing the tracked candidate or
creating a new slot, so scheduled refreshes cannot undo a maintainer's triage
decision.

The manual fake-strategist Task and the self-development READMEs now follow the same contract.

Which issue(s) this PR is related to:

N/A

Special notes for your reviewer:

Validation: make verify

Does this PR introduce a user-facing change?

NONE

[gjkim42]

/kelos review

[kelos-bot]

🤖 Kelos Task Status

Task kelos-reviewer-issue-comment-aca71c7c1db3 has succeeded. ✅

[kelos-bot]

🤖 Kelos Reviewer Agent @gjkim42

Review Summary

Verdict: APPROVE
Overall correctness: patch is correct
Scope: Adds title prefixes, current-validity rechecks, and replaceable verdict sections to autonomous discovery issue slots across Kelos, Agora, and Kanon.

Findings Overview

Priority	Count	File:Line	Summary
P0	0	—	none
P1	0	—	none
P2	1	self-development/kelos-fake-strategist.yaml:116	Valid-slot refresh can undo explicit triage removal
P3	0	—	none

Findings

Correctness

• [P2] self-development/kelos-fake-strategist.yaml:116 — Retaining a valid unassigned slot now requires an edit on every run, but the prescribed edit command at line 139 always adds triage-accepted. If a maintainer explicitly uses /remove-triage-accepted, the next scheduled verdict refresh silently restores that label and the label workflow removes needs-triage, undoing the human decision; preserve the slot's existing triage labels for a verdict-only refresh, and add triage-accepted only when creating or replacing the candidate. The same edit pattern appears in the other updated discovery-agent manifests and the manual task.

[cubic-dev-ai]

1 issue found across 13 files

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="self-development/kanon/README.md">

<violation number="1" location="self-development/kanon/README.md:26">
P3: The new intro paragraph documents that discovery spawners now revalidate their unassigned slot each run and may retain, replace, or close it, but the dedicated sections for kanon-fake-user, kanon-fake-strategist, and kanon-self-update in this same README still say only "Creates or updates the single unassigned ... issue slot ... If that issue is assigned, the run treats it as ongoing and exits without editing it or creating another issue." Reading the file, a reader following the per-spawner sections won't learn about validity re-checking or closing invalid slots, which is now core behavior (it is implemented in the matching spawner YAMLs). Update those three sections to mention the keep/replace/close-on-invalid rules so the file is internally consistent.</violation>
</file>

<sub>Reply with feedback, questions, or to request a fix.

Re-trigger cubic</sub>

[cubic-dev-ai]

P3: The new intro paragraph documents that discovery spawners now revalidate their unassigned slot each run and may retain, replace, or close it, but the dedicated sections for kanon-fake-user, kanon-fake-strategist, and kanon-self-update in this same README still say only "Creates or updates the single unassigned ... issue slot ... If that issue is assigned, the run treats it as ongoing and exits without editing it or creating another issue." Reading the file, a reader following the per-spawner sections won't learn about validity re-checking or closing invalid slots, which is now core behavior (it is implemented in the matching spawner YAMLs). Update those three sections to mention the keep/replace/close-on-invalid rules so the file is internally consistent.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At self-development/kanon/README.md, line 26:

<comment>The new intro paragraph documents that discovery spawners now revalidate their unassigned slot each run and may retain, replace, or close it, but the dedicated sections for kanon-fake-user, kanon-fake-strategist, and kanon-self-update in this same README still say only "Creates or updates the single unassigned ... issue slot ... If that issue is assigned, the run treats it as ongoing and exits without editing it or creating another issue." Reading the file, a reader following the per-spawner sections won't learn about validity re-checking or closing invalid slots, which is now core behavior (it is implemented in the matching spawner YAMLs). Update those three sections to mention the keep/replace/close-on-invalid rules so the file is internally consistent.</comment>

<file context>
@@ -20,13 +20,14 @@ instructions where needed: triage and squash-commits share `agentconfig.yaml`
+open `generated-by-kelos` issue slot per TaskSpawner. Its title starts with the
+TaskSpawner name in brackets, and its body includes both a
+`kelos-taskspawner=<name>` marker and one replaceable `Latest verdict` section.
+Each run checks whether an unassigned slot is still valid against the current
+repository before retaining, replacing, or closing it. Assigned issues and PRs
+are treated as ongoing human or agent work and are not updated by autonomous
</file context>