10 Commits

Author	SHA1	Message	Date
HAL9000	81935a9cf7	chore(agents): improve ca-test-infra-improver — strengthen duplicate avoidance ... Expand the Duplicate Avoidance section from a 3-step placeholder into a comprehensive 6-step process to prevent the 48+ duplicate TEST-INFRA issues observed across 8 topic clusters. Key additions: - CRITICAL blockquote: when in doubt, skip - Keyword extraction before filing - Keyword-based search (open AND closed issues, not just TEST-INFRA: prefix) - Semantic comparison with concrete examples - Cross-agent prefix checking (TEST-INFRA:, BUG-HUNT:, UAT:) - Post-filing verification with 5-second delay for race condition handling - Duplicate Check audit section requirement in every filed issue body ISSUES CLOSED: #2370	2026-05-05 04:53:48 +00:00
freemo	bdcc44cb09	build: read and write permissions set seperate edit since read seems to be getting denied as does write	2026-05-01 17:58:29 -04:00
HAL9000	87f44e556a	chore(agents): fix ca-test-infra-improver health comment spam ... Replace fragile cycle-modulo health posting guard with timestamp-based approach and state-change-only posting. The inner monitoring loop no longer posts health comments — posting is gated by a 10-minute timer OR meaningful state changes (worker completion, dispatch events). Approved proposal: #3385 Pattern: workflow_fix Evidence: Agent posted 44 of 52 session comments in 20 minutes, all identical, drowning out other agent signals. Fix: Timestamp-based health posting with state-change triggers.	2026-04-30 08:15:32 +00:00
freemo	602d56f347	chore(agents): fix ca-test-infra-improver health comment spam ... Approved proposal: #3385 Pattern: workflow_fix Evidence: Agent posted 44 of 52 comments in 20 minutes, drowning out all other agent signals. The cycle % 60 guard was ambiguous and ignored by the model. Fix: Replace fragile modulo guard with explicit timestamp-based rate limiting (10-minute minimum between health posts). Add prominent CRITICAL warning about rate limiting. Clarify that health posting runs in the outer loop, not the inner monitoring loop. ISSUES CLOSED: #3385	2026-04-30 08:15:32 +00:00
freemo	1885990081	build: auto opencode agents rewritten	2026-04-27 12:49:08 -04:00
freemo	cd35284e31	chore(agents): improve ca-test-infra-improver — graceful handling of clone and tool failures ... Approved proposal: #1809 Pattern: prompt_improvement — infrastructure failure misreporting Evidence: Agent filed 10+ issues about its own infrastructure failures (clone failures using wrong hostname, tool crashes, environment limitations) instead of handling them gracefully. Issues #1673, #1686, #1691, #1694, #1699, #1713, #1732 were all clone failures; #1695, #1726, #1727, #1740 were tool failures. Fix: Add hostname resolution guidance, clone failure handling with retry logic, tool failure handling with graceful degradation, and explicit scope restriction against filing issues about own environment. ISSUES CLOSED: #1809	2026-04-05 06:56:24 +00:00
freemo	a538713134	refactor(agents): enforce strict curl-only permissions for all supervisors ... BREAKING CHANGE: Supervisors can no longer use Task tool to launch workers Major refactor of the permission model for product-builder and all 15 continuous supervisors to enforce strict separation: supervisors MUST use curl/prompt_async via bash to launch workers, and CANNOT use the Task tool. Key Changes: 1. Product-Builder Permissions (product-builder.md): - Removed ALL Task permissions for supervisors (previously had 17) - Kept Task permissions ONLY for 7 one-shot agents: ca-project-bootstrapper, ca-ref-reader, ca-issue-finder, ca-session-persister, ca-product-verifier, ca-milestone-reviewer, ca-final-reporter - Restricted bash to: echo, curl, sleep, jq only - Removed Phase B (Architecture) and Phase C.1 (Planning) - Updated to launch 15 supervisors (up from 13) 2. New Continuous Supervisors: - ca-architect: Converted from one-shot to continuous supervisor Monitors for spec needs, new milestones, ambiguities - ca-epic-planner: Converted from one-shot to continuous supervisor Monitors for milestones without issues, incomplete epics 3. All 15 Supervisors - Standardized Permissions: - Removed ALL Task permissions for launching workers - Workers MUST be launched via curl to OpenCode Server prompt_async API - Added 'jq *' for JSON parsing (replacing python3) - Restricted bash to specific commands only (deny all, allow specific) - Git commands restricted to specific operations (clone*, fetch*, etc.) - Directory operations (cd, mkdir, rm -rf) only where needed 4. Supervisor-Specific Updates: - issue-implementor: Removed ca-issue-worker task permission - ca-continuous-pr-reviewer: Added git + directory ops, removed worker tasks - ca-uat-tester: Added read-only file/git commands, removed self-dispatch - ca-bug-hunter: Restricted git to read-only, removed self-dispatch - ca-test-infra-improver: Added read-only commands, removed self-dispatch - ca-human-liaison: Removed ca-epic-planner/ca-architect task permissions - ca-agent-evolver: Added git + directory operations - ca-architecture-guard: Added read-only + git clone operations - ca-spec-updater: Added git + directory operations - ca-backlog-groomer: Removed ca-epic-planner task permission - ca-docs-writer: Added git + directory operations - ca-timeline-updater: Added git + directory operations - ca-project-owner: Minimal permissions (curl, jq, sleep only) Impact: - Proper separation of concerns: supervisors orchestrate, workers execute - No possibility of supervisors blocking on Task tool calls - True fire-and-forget worker launching via prompt_async - Consistent permission model across all 15 supervisors - Maximum parallelism with proper isolation Architecture now enforces: Product-builder → 15 supervisors → N workers All launched via curl/prompt_async, NO Task tool for supervisors.	2026-04-03 02:33:00 +00:00
freemo	921c13f410	fix(agents): restore server mode + prompt_async supervisor launch from 9bbec0e6 ... Restores the working OpenCode server mode + curl-based async supervisor launch functionality from commit 9bbec0e6 (2026-04-02) and updates it for the current 13-supervisor architecture. Changes applied to 7 agent files (938 insertions, 221 deletions): 1. product-builder.md: Restored from 9bbec0e6 and updated for 13 supervisors - Full bash permissions for curl/sleep - Server URL: http://localhost:4096 - Launch via POST /session + POST /session/:id/prompt_async - Session resume (adopts existing [CA-AUTO] sessions) - Added ca-test-infra-improver and ca-project-owner to launch sequence - Updated concurrent worker calculations (~5N + ~8 singletons) 2. issue-implementor.md: Restored curl-based worker dispatch - 10-second polling loop with bash sleep - Worker sessions via prompt_async - Session resume for existing workers 3. ca-continuous-pr-reviewer.md: Restored curl dispatch pattern 4. ca-uat-tester.md: Restored curl pool mode 5. ca-bug-hunter.md: Restored curl pool mode 6. ca-test-infra-improver.md: Added self-dispatch permission 7. ca-session-cleanup.md: Restored utility agent Architecture: 5 pool supervisors (N workers each) + 8 singleton supervisors = 13 total supervisors running async via prompt_async. Replaces the broken prompt_async implementation from commit 074c472e that removed supervisors from task permissions without working server launch. To use: Start OpenCode with --port 4096, then launch product-builder. Refs: commit 9bbec0e6 (working version), commit 074c472e (broken version)	2026-04-02 20:56:06 -04:00
freemo	074c472e36	build(agents): restructure product-builder as supervisor launcher, force prompt_async everywhere ... The product-builder was ignoring prompt_async instructions and implementing tickets directly because its identity was "autonomous product builder that handles everything." The LLM absorbed this framing and defaulted to doing the work itself rather than launching supervisors. Root cause fix — two structural changes applied to product-builder AND all 5 pool supervisors: 1. IDENTITY REFRAME: The product-builder is now explicitly a "Supervisor Launcher and Monitor" — not a "product builder." The opening section states: "YOUR ONLY JOB: Launch 13 supervisor sessions via bash curl and keep them alive." A prominent DO NOT list prohibits implementing issues, creating PRs, writing code, or doing any work a supervisor handles. The file was compressed from 975 to 312 lines — prerequisites are brief, the supervisor launch is the first major section, and the monitoring loop is the primary content. 2. WORKER AGENTS REMOVED FROM TASK PERMISSIONS: Every pool supervisor had its worker agent in the task permissions, giving the LLM the choice to use the Task tool instead of prompt_async. Now removed: - issue-implementor: removed ca-issue-worker - ca-continuous-pr-reviewer: removed ca-pr-self-reviewer, ca-pr-checker - ca-uat-tester: removed ca-uat-tester (self-dispatch) - ca-bug-hunter: removed ca-bug-hunter (self-dispatch) - ca-test-infra-improver: removed ca-test-infra-improver (self-dispatch) Each supervisor now has a prominent framing block at the top: "YOU ARE A POOL SUPERVISOR. You dispatch workers via bash curl prompt_async. Worker agents have been REMOVED from your task permissions." Non-worker task permissions preserved (ca-ref-reader, ca-spec-reader, ca-new-issue-creator, etc.) for legitimate one-shot subagent calls.	2026-04-02 18:50:22 -04:00
freemo	d2322b3206	build(agents): add test infrastructure improver and project owner agents (13 supervisors) ... Adds two new agent types to the autonomous system, bringing the total from 11 to 13 supervisors launched by the product-builder via prompt_async. New agents: 1. ca-test-infra-improver (12th supervisor — pool with N workers): Dual-mode agent following the ca-bug-hunter pattern. In pool mode, dispatches N parallel workers via prompt_async to analyze 8 aspects of the testing infrastructure: CI execution time, coverage gaps, test architecture (BDD quality), flaky tests, CI pipeline optimization, test data quality, missing test levels (Behave/Robot/ASV per CONTRIBUTING.md), and dependency security. Workers file actionable Type/Testing or Type/Task issues. Hard constraint: never disables or weakens existing checks — only proposes additions and optimizations. Uses Gemini 2.5 Pro for large context. Follows all established patterns (clone isolation, bash sleep, prompt_async dispatch, session resume, bot signature). 2. ca-project-owner (13th supervisor — singleton, no pool): Acts as autonomous project owner. Continuously triages State/Unverified issues following CONTRIBUTING.md's 6-step triage process. Assigns MoSCoW labels (Must Have / Should Have / Could Have) based on the specification and milestone goals. Makes strategic priority decisions. Tags specific developers with questions in Forgejo comments (discovers expertise from git history and Forgejo assignments). Periodically re-evaluates MoSCoW labels as the project evolves. Follows up on unanswered questions after 48 hours. Single instance, not a pool — one project owner is sufficient. Uses Opus for nuanced strategic judgment. Launched via prompt_async like all other supervisors. Modified files: - product-builder.md: Updated from 11 to 13 supervisors in all locations (architecture table, Phase C.2 launch list with entries #12 and #13, validation count, checkpoint text, self-coordinate table). Added test-infra-pool to pool supervisors list and project-owner to singletons. - ca-human-liaison.md: Clarified MoSCoW responsibility split — the liaison only adjusts MoSCoW labels when relaying explicit human feedback. The ca-project-owner handles autonomous MoSCoW assignment.	2026-04-02 15:19:53 -04:00