Merge branch 'main' into symphony/pln-228

Author: peterulsteen

CHANGELOG.md

@@ -6,6 +6,69 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
 ## [Unreleased]
 
+### bootstrap v1.2.0
+
+#### Changed
+- Migrated critic-gates configuration path from `.claude/settings/critic-gates.json` to `.closedloop-ai/settings/critic-gates.json` across `agent-decomposer`, `agent-prompt-validator`, `generation-validator`, and `agent-bootstrap` command
+- Migrated schema validation path from `.claude/schemas/` to `.closedloop-ai/schemas/` in `agent-prompt-validator`
+- Updated agent output path references from `.claude/runs/` to `.closedloop-ai/runs/` in `agent-prompt-generator`
+- Updated bootstrap configuration documentation in `agent-bootstrap.md` to reference `.closedloop-ai/` state directory
+
+### code v1.6.0
+
+#### Changed
+- Migrated all remaining `.claude/` path references to `.closedloop-ai/` across hooks, scripts, agents, skills, and orchestrator prompt -- completes the directory migration started in v1.1.0
+- Replaced `gawk` FPAT-based TOON parser with portable `csv_split()` function in `pretooluse-hook.sh` and `subagent-start-hook.sh`, removing the hard dependency on GNU awk
+- Refactored awk array usage from associative `patterns[n]["key"]` to parallel flat arrays for POSIX awk compatibility
+- Updated `install-dependencies.sh` to verify any `awk` instead of requiring `gawk` with FPAT support
+- Updated org learnings copy path in `run-loop.sh` to use `.closedloop-ai/learnings/` with workdir-adjacent state directory resolution
+
+#### Removed
+- Removed all legacy `.claude/.closedloop/` session/workdir/env fallback paths from `loop-stop-hook.sh`, `pretooluse-hook.sh`, `session-end-hook.sh`, `subagent-start-hook.sh`, `subagent-stop-hook.sh`, and `setup-closedloop.sh`
+- Removed legacy `~/.claude/.learnings/org-patterns.toon` fallback from `pretooluse-hook.sh` and `subagent-start-hook.sh`
+- Removed legacy cleanup logic from `session-end-hook.sh` (PID cleanup, stale session removal, legacy directory deletion)
+
+#### Added
+- Tests for legacy path ignorance in pretooluse and subagent-start hooks, setup-closedloop, and self-learning flag tests
+- Tests for portable awk injection (`test_injects_when_only_plain_awk_is_available`) in both hook test suites
+
+### code-review v1.4.0
+
+#### Changed
+- Migrated GitHub mode output file paths from `.claude/` to `.closedloop-ai/`: `code-review-findings.json`, `code-review-threads.json`, and `code-review-summary.md`
+- Updated `route` subcommand to read critic-gates from `.closedloop-ai/settings/critic-gates.json`
+- Simplified fast-path routing to `total_loc <= 200` threshold only (was `<= 150 LOC AND <= 5 files AND no domain critics`); domain critics are now folded into the fast-path agent as an additional pass
+
+#### Added
+- Structured reasoning protocol for Premise Reviewer: `AUTHOR'S CLAIM / COUNTER-EVIDENCE / ALTERNATIVE CHECK / CONCLUSION` validation gate before reporting premise findings
+- Reasoning certificate for Bug Hunter A: `PREMISE / TRACE / DIVERGENCE / GUARD CHECK / CONCLUSION` trace-based bug confirmation gate with emission filtering
+- Domain critic pass injection in fast-path reviewer via `{DOMAIN_CRITIC_PASS}` placeholder, enabling domain expert review within single-agent fast-path runs
+- Replaced shared prompt reasoning checklist with structured `PREMISE / EVIDENCE / GUARD CHECK / SEVERITY CHECK` analysis framework
+
+### judges v1.5.0
+
+#### Changed
+- Migrated threshold override paths from `.claude/settings/threshold-overrides.json` to `.closedloop-ai/settings/threshold-overrides.json` in `run-judges` skill (both run-specific and repo-level locations)
+
+### platform v1.1.0
+
+#### Changed
+- Version bump to align with cross-plugin `.closedloop-ai/` directory migration
+
+### self-learning v1.1.0
+
+#### Changed
+- Migrated org learnings paths from `.claude/learnings/` to `.closedloop-ai/learnings/` across `pull-learnings`, `push-learnings`, and `bootstrap-learnings.sh`
+- Migrated run path references from `.claude/runs/` to `.closedloop-ai/runs/` in `process-learnings` command
+- Simplified `preflight-check.sh` to verify `awk` availability instead of requiring `gawk` with FPAT support
+
+#### Removed
+- Removed legacy `~/.claude/.learnings/org-patterns.toon` fallback from `compute_success_rates.py` and `write_merged_patterns.py`
+- Removed legacy session file lookup path from `evaluate_goal.py`
+
+#### Added
+- Test verifying CLI ignores legacy home TOON path in `test_compute_success_rates.py`
+
 ### code v1.5.10
 
 #### Changed

docs/glossary.md

@@ -5,7 +5,7 @@ A comprehensive guide to ClosedLoop terminology and concepts.
 ## Orchestration
 
 **Closed Loop**
-The external bash loop (`run-loop.sh`) that drives fresh-context Claude iterations. Each iteration launches `claude -p` with a clean context window, preventing context exhaustion on long tasks. State persists between iterations in `.claude/closedloop-loop.local.md`.
+The external bash loop (`run-loop.sh`) that drives fresh-context Claude iterations. Each iteration launches `claude -p` with a clean context window, preventing context exhaustion on long tasks. State persists between iterations in `.closedloop-ai/closedloop-loop.local.md`.
 
 **Orchestrator**
 The `prompt.md` system prompt loaded by `run-loop.sh` at the start of each iteration. Coordinates 8 workflow phases (discovery, planning, judge review, plan refinement, implementation, verification, build validation, and learning capture) entirely through subagent delegation. The orchestrator never reads project files directly.

plugins/bootstrap/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "bootstrap",
   "description": "Bootstrap plugin for ClosedLoop",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "author": {
     "name": "ClosedLoop",
     "email": "support@closedloop.ai"

plugins/bootstrap/README.md

@@ -92,7 +92,7 @@ Decomposition is driven by domain complexity (high complexity favors decompositi
 
 Also generates `critic-gates.json`, which defines which agents act as critics in the `code` workflow. Required agents (`test-strategist`, `security-privacy`) and language experts are always base critics. Domain agents are mapped to module patterns so they are only invoked when relevant.
 
-Produces: `synthesis/decomposed-agents.json`, `.claude/settings/critic-gates.json`
+Produces: `synthesis/decomposed-agents.json`, `.closedloop-ai/settings/critic-gates.json`
 
 ### generation-validator
 
@@ -214,7 +214,7 @@ Durable outputs written outside the run directory:
   <agent-name>.md            (one file per generated agent)
 .closedloop-ai/
   bootstrap-metadata.json    (tracks all generated agents for --update mode)
-.claude/settings/
+.closedloop-ai/settings/
   critic-gates.json          (critic selection rules for the code workflow)
 ```
 

plugins/bootstrap/agents/agent-decomposer.md

@@ -23,7 +23,7 @@ For each decomposable candidate agent, decide: keep as single agent OR split int
 
 ### Generating Critic Gates Configuration
 
-After decomposition decisions are made, generate `.claude/settings/critic-gates.json` to define which agents can act as critics.
+After decomposition decisions are made, generate `.closedloop-ai/settings/critic-gates.json` to define which agents can act as critics.
 
 **Step 1: Identify Base Critics**
 
@@ -492,7 +492,7 @@ For each final agent (decomposed or not), define:
 }
 ```
 
-### 2. Critic Gates Configuration: `.claude/settings/critic-gates.json`
+### 2. Critic Gates Configuration: `.closedloop-ai/settings/critic-gates.json`
 
 Generated critic configuration for the code workflow:
 
@@ -543,7 +543,7 @@ Generated critic configuration for the code workflow:
 - Only include agents that exist in finalAgents
 - Skip moduleCritics entries if no relevant agents exist (e.g., don't add database patterns if no database-architect)
 - Only include language experts that were detected (don't add python-pro if no Python found)
-- Safe-write: If `.claude/settings/critic-gates.json` already exists, write to `$RUN/settings/critic-gates.json` instead and warn user
+- Safe-write: If `.closedloop-ai/settings/critic-gates.json` already exists, write to `$RUN/settings/critic-gates.json` instead and warn user
 
 ## Input Validation
 
@@ -581,7 +581,7 @@ This ensures the upstream `expertise-mapper` produced valid output before decomp
 - ✅ Critic-capable agents (from generated critic-gates.json) contain `supportsCriticMode` + `modes` blocks with review metadata
 - ✅ Both output files are valid JSON
 - ✅ decomposed-agents.json written to synthesis/
-- ✅ critic-gates.json written to .claude/settings/ (or $RUN/settings/ if file exists)
+- ✅ critic-gates.json written to .closedloop-ai/settings/ (or $RUN/settings/ if file exists)
 
 ## Error Handling
 

plugins/bootstrap/agents/agent-prompt-generator.md

@@ -423,7 +423,7 @@ Translate the agent's `requires` and `produces` into clear documentation:
 ```markdown
 ## Output Format
 
-Write to `.claude/runs/<timestamp>/arch/database-schema.md`:
+Write to `.closedloop-ai/runs/<timestamp>/arch/database-schema.md`:
 
 ### Required Sections
 

plugins/bootstrap/agents/agent-prompt-validator.md

@@ -378,7 +378,7 @@ Write to `$RUN/synthesis/agent-validation.json`:
 
 ## Schema Validation
 
-Before running semantic checks, validate input artifacts against schemas in `.claude/schemas/`:
+Before running semantic checks, validate input artifacts against schemas in `.closedloop-ai/schemas/`:
 
 - `$RUN/synthesis/decomposed-agents.json` → `decomposed-agents.schema.json`
 - `.closedloop-ai/bootstrap-metadata.json` → `bootstrap-metadata.schema.json`

plugins/bootstrap/agents/generation-validator.md

@@ -14,7 +14,7 @@ You validate that the decomposed agent list is ready for generation by checking
 ## Inputs
 
 - `$RUN/synthesis/decomposed-agents.json` - Final agent list with artifact contracts
-- `.claude/settings/critic-gates.json` - Critic configuration (generated by agent-decomposer)
+- `.closedloop-ai/settings/critic-gates.json` - Critic configuration (generated by agent-decomposer)
 
 ## Task
 
@@ -39,7 +39,7 @@ Each agent spec must have:
 - ✅ **parallelizable**: Boolean
 - ✅ **group**: String or null
 - ✅ **priority**: Number 0-2 (if has group)
-- ✅ **supportsCriticMode** and `modes` when agent is in the critic-capable set (dynamically discovered from `.claude/settings/critic-gates.json`).
+- ✅ **supportsCriticMode** and `modes` when agent is in the critic-capable set (dynamically discovered from `.closedloop-ai/settings/critic-gates.json`).
   - To discover critics: Extract all unique agent names from `defaults.baseCritics` and `moduleCritics[].critics`.
   - Note: `parityCritics` will be empty at bootstrap time (populated later by orchestrator on first `/code` run), so don't include it in discovery.
   - If critic-gates.json doesn't exist, skip critic validation entirely.
@@ -161,7 +161,7 @@ For each critic-capable agent (discovered from critic-gates.json):
 
 #### 9. critic-gates.json Structure Validation
 
-Validate the structure of `.claude/settings/critic-gates.json`:
+Validate the structure of `.closedloop-ai/settings/critic-gates.json`:
 
 - `defaults.baseCritics`: must be array of strings
 - `moduleCritics`: must be array of objects, each with `patterns` (array of strings) and `critics` (array of strings)

plugins/bootstrap/commands/agent-bootstrap.json

@@ -50,7 +50,7 @@
         "$RUN/discovery/project-context.md",
         "$RUN/discovery/domains.json"
       ],
-      "produces": ["$RUN/synthesis/decomposed-agents.json", ".claude/settings/critic-gates.json"],
+      "produces": ["$RUN/synthesis/decomposed-agents.json", ".closedloop-ai/settings/critic-gates.json"],
       "parallelizable": false
     },
     {

plugins/bootstrap/commands/agent-bootstrap.md

@@ -109,7 +109,7 @@ Maps detected languages and domains to base expert agent roles.
 
 Analyzes candidate agents and decides which should be split into specialists based on complexity and breadth. Generates critic-gates.json configuration for the code workflow.
 
-**Produces:** `synthesis/decomposed-agents.json`, `.claude/settings/critic-gates.json`
+**Produces:** `synthesis/decomposed-agents.json`, `.closedloop-ai/settings/critic-gates.json`
 
 ### Phase 5: Pre-Generation Validation
 
@@ -157,7 +157,7 @@ Generated agents written to `.claude/agents/`:
 
 Generated configuration files:
 
-- `.claude/settings/critic-gates.json` - Critic selection rules for the code workflow (safe write)
+- `.closedloop-ai/settings/critic-gates.json` - Critic selection rules for the code workflow (safe write)
 
 ## Examples
 
@@ -227,7 +227,7 @@ Constrain analysis to backend domains:
 
 ## Configuration
 
-Bootstrap behavior can be customized via `.claude/commands/agent-bootstrap.json` (created automatically on first run).
+Bootstrap behavior is defined by `commands/agent-bootstrap.json`; generated run state lives under `.closedloop-ai/`, and generated agents are written to `.claude/agents/`.
 
 ## Exit Criteria