@amsterdamdatalabs/enact-extensions 0.1.37 → 0.1.47

package/extensions/enact-evolve/skills/session-analysis/scripts/run-evolve-analysis.sh

@@ -1,343 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-usage() {
-  cat <<'USAGE'
-Usage:
-  run-evolve-analysis.sh --surface codex|claude|factory --session <path-or-id> [--watchdog <path>] [--out <dir>]
-
-Runs enact-evolve ingest, enact-evolve evaluate, and writes synthesis.md.
-This workflow does not run promotion.
-USAGE
-}
-
-surface=""
-session=""
-watchdog=""
-out=""
-
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --surface)
-      surface="${2:-}"
-      shift 2
-      ;;
-    --session)
-      session="${2:-}"
-      shift 2
-      ;;
-    --watchdog)
-      watchdog="${2:-}"
-      shift 2
-      ;;
-    --out)
-      out="${2:-}"
-      shift 2
-      ;;
-    -h|--help)
-      usage
-      exit 0
-      ;;
-    *)
-      echo "Unknown argument: $1" >&2
-      usage >&2
-      exit 2
-      ;;
-  esac
-done
-
-if [[ -z "$surface" || -z "$session" ]]; then
-  usage >&2
-  exit 2
-fi
-
-case "$surface" in
-  codex|claude|factory)
-    ;;
-  *)
-    echo "Invalid --surface: $surface" >&2
-    usage >&2
-    exit 2
-    ;;
-esac
-
-if ! command -v enact-evolve >/dev/null 2>&1; then
-  echo "enact-evolve is required on PATH." >&2
-  exit 127
-fi
-
-safe_session_id() {
-  local value="$1"
-  value="${value%/}"
-  value="${value##*/}"
-  value="${value:-session}"
-  printf '%s' "$value" | sed -E 's/[^A-Za-z0-9._-]+/-/g; s/^-+//; s/-+$//'
-}
-
-safe_id="$(safe_session_id "$session")"
-if [[ -z "$out" ]]; then
-  storage_json="$(enact-evolve storage --json)" || {
-    echo "Unable to resolve project-scoped enact-evolve storage from the current working directory. Run inside a project, or pass --out." >&2
-    exit 1
-  }
-  analysis_root="$(python3 -c 'import json, sys; print(json.load(sys.stdin).get("analysis_dir", ""))' <<< "$storage_json")"
-  if [[ -z "$analysis_root" ]]; then
-    echo "enact-evolve storage --json did not return analysis_dir." >&2
-    exit 1
-  fi
-  out="${analysis_root}/${surface}-${safe_id}"
-  if [[ -e "${out}/session-evidence.jsonl" ]]; then
-    out="${out}-$(date -u +%Y%m%dT%H%M%SZ)"
-  fi
-fi
-
-mkdir -p "$out"
-
-if [[ "$surface" == "factory" ]]; then
-  ingest_cmd=(enact-evolve ingest --surface "$surface" --scenario "$session" --out "$out")
-else
-  ingest_cmd=(enact-evolve ingest --surface "$surface" --session "$session" --out "$out")
-fi
-
-if [[ -n "$watchdog" ]]; then
-  ingest_cmd+=(--watchdog "$watchdog")
-fi
-
-evaluate_cmd=(enact-evolve evaluate --evidence "${out}/session-evidence.jsonl" --out "${out}/eval")
-
-{
-  printf 'ingest: '
-  printf '%q ' "${ingest_cmd[@]}"
-  printf '\n'
-  printf 'evaluate: '
-  printf '%q ' "${evaluate_cmd[@]}"
-  printf '\n'
-} > "${out}/pipeline-commands.txt"
-
-"${ingest_cmd[@]}"
-"${evaluate_cmd[@]}"
-
-python3 - "$out" "$surface" "$session" <<'PY'
-import collections
-import json
-import sys
-from pathlib import Path
-
-out = Path(sys.argv[1]).expanduser().resolve()
-surface = sys.argv[2]
-session_arg = sys.argv[3]
-
-def read_jsonl(path):
-    path = Path(path)
-    if not path.exists():
-        return []
-    text = path.read_text(encoding="utf-8").strip()
-    if not text:
-        return []
-    if text.startswith("["):
-        data = json.loads(text)
-        return data if isinstance(data, list) else [data]
-    rows = []
-    for line in text.splitlines():
-        line = line.strip()
-        if line:
-            rows.append(json.loads(line))
-    return rows
-
-def first_present(mapping, keys, default=None):
-    cur = mapping
-    for key in keys:
-        if not isinstance(cur, dict) or key not in cur:
-            return default
-        cur = cur[key]
-    return cur
-
-def fmt_count_map(counter):
-    if not counter:
-        return "- None"
-    items = counter.items() if hasattr(counter, "items") else counter
-    return "\n".join(f"- `{key}`: {value}" for key, value in sorted(items))
-
-def compact_json(value, limit=600):
-    if value in (None, "", [], {}):
-        return "None"
-    text = json.dumps(value, ensure_ascii=False, sort_keys=True)
-    if len(text) > limit:
-        return text[: limit - 3] + "..."
-    return text
-
-def bullet_lines(items, limit=20, key=None):
-    if not items:
-        return "- None"
-    lines = []
-    for item in items[:limit]:
-        if key and isinstance(item, dict):
-            value = item.get(key)
-            count = item.get("count")
-            if count is not None:
-                lines.append(f"- `{value}`: {count}")
-            else:
-                lines.append(f"- `{value}`")
-        elif isinstance(item, dict):
-            lines.append(f"- `{compact_json(item, 360)}`")
-        else:
-            lines.append(f"- `{item}`")
-    if len(items) > limit:
-        lines.append(f"- ... {len(items) - limit} more")
-    return "\n".join(lines)
-
-evidence_rows = read_jsonl(out / "session-evidence.jsonl")
-metrics_rows = read_jsonl(out / "metrics.jsonl")
-candidate_rows = read_jsonl(out / "candidate-improvements.jsonl")
-trace_rows = read_jsonl(out / "trace-events.jsonl")
-eval_metrics_rows = read_jsonl(out / "eval" / "metrics.jsonl")
-eval_candidate_rows = read_jsonl(out / "eval" / "candidate-improvements.jsonl")
-
-evidence = evidence_rows[-1] if evidence_rows else {}
-quality_metrics = evidence.get("quality_metrics") or {}
-context_usage = quality_metrics.get("context_usage") or {}
-token_usage = quality_metrics.get("token_usage") or {}
-context_summary = evidence.get("context_summary") or []
-context_entries = evidence.get("context_entries") or []
-tool_summary = evidence.get("tool_summary") or []
-tool_timeline = evidence.get("tool_timeline") or []
-hook_summary = evidence.get("hook_summary") or []
-hook_timeline = evidence.get("hook_timeline") or []
-system_prompts = evidence.get("system_prompts") or []
-candidate_source = eval_candidate_rows or candidate_rows
-candidate_counts = collections.Counter(
-    (row.get("target_family") or "unknown") for row in candidate_source if isinstance(row, dict)
-)
-source_signal_counts = collections.Counter()
-for row in candidate_source:
-    if not isinstance(row, dict):
-        continue
-    for signal in row.get("source_signals") or []:
-        source_signal_counts[str(signal)] += 1
-
-artifact_paths = []
-for path in sorted(out.rglob("*")):
-    if path.is_file():
-        artifact_paths.append(path.relative_to(out).as_posix())
-
-transcripts = [
-    path for path in sorted(out.glob("*.md"))
-    if path.name != "synthesis.md"
-]
-
-commands = (out / "pipeline-commands.txt").read_text(encoding="utf-8").strip()
-session_id = evidence.get("session_id") or Path(session_arg).name
-evidence_id = evidence.get("evidence_id") or evidence.get("id") or "unknown"
-source_refs = evidence.get("source_refs") or []
-source_path = evidence.get("source_path") or evidence.get("source") or (source_refs[0] if source_refs else session_arg)
-
-top_context_sources = context_usage.get("top_context_sources") or []
-largest_context_blocks = context_usage.get("largest_context_blocks") or context_usage.get("largest_blocks") or []
-duplicate_context_count = context_usage.get("duplicate_context_count")
-if duplicate_context_count is None:
-    duplicate_context_count = context_usage.get("duplicate_count", "not normalized")
-
-tool_family_counts = collections.Counter()
-for item in tool_summary:
-    if isinstance(item, dict):
-        name = item.get("name") or item.get("tool") or item.get("kind") or item.get("key") or "unknown"
-        tool_family_counts[str(name)] += int(item.get("count") or 1)
-
-markdown = f"""# Enact Evolve Session Analysis
-
-## Session Identity
-
-- Surface: `{surface}`
-- Session id: `{session_id}`
-- Source path: `{source_path}`
-- Evidence id: `{evidence_id}`
-- Output directory: `{out}`
-- Transcript markdown: `{transcripts[0] if transcripts else 'not generated'}`
-
-## Pipeline Proof
-
-```text
-{commands}
-```
-
-Generated artifacts:
-{bullet_lines(artifact_paths, limit=80)}
-
-## Tool And MCP Analysis
-
-Normalized tool summary:
-{bullet_lines(tool_summary, limit=30)}
-
-Tool timeline entries: `{len(tool_timeline)}`
-
-Tool family counts:
-{fmt_count_map(tool_family_counts)}
-
-Raw MCP cross-check: not performed by this helper. Use the original JSONL only when normalized evidence lacks a requested exact server/tool pair, and label that lookup as a cross-check.
-
-## Hook Evidence
-
-Normalized hook summary:
-{bullet_lines(hook_summary, limit=30)}
-
-Hook timeline entries: `{len(hook_timeline)}`
-
-Evidence limitation: {"normalized evidence did not capture hook firings for this transcript; inspect raw JSONL only as a labeled cross-check for hook execution gaps." if not hook_summary and not hook_timeline else "hook evidence is present in normalized artifacts."}
-
-## Context Injection
-
-- System prompt entries: `{len(system_prompts)}`
-- Context entries: `{len(context_entries)}`
-- Context usage: `{compact_json(context_usage, 1200)}`
-- Context summary: `{compact_json(context_summary, 1200)}`
-- Token usage: `{compact_json(token_usage, 1200)}`
-- Duplicate context count: `{duplicate_context_count}`
-
-Top context sources:
-{bullet_lines(top_context_sources, limit=20)}
-
-Largest context blocks:
-{bullet_lines(largest_context_blocks, limit=20)}
-
-## Candidate Summary
-
-Candidate rows: `{len(candidate_source)}`
-
-Counts by target family:
-{fmt_count_map(candidate_counts)}
-
-Top source signals:
-{fmt_count_map(source_signal_counts.most_common(20))}
-
-Extension implications: review candidates targeting skill instructions, hook rules, tool descriptions, and agent routing. Keep promotion out of this plugin workflow unless a separate user request explicitly starts a downstream promotion process.
-
-## Findings
-
-- The canonical workflow ran through `enact-evolve ingest` and `enact-evolve evaluate` before synthesis.
-- Findings should be grounded in normalized evidence first; raw transcript inspection is only a cross-check for missing normalized fields.
-- If hook evidence is empty above, the actionable issue is normalizer coverage, not proof that hooks did not execute.
-- If the original assistant analyzed raw JSONL without this pipeline, the follow-up is to route session-forensics requests through this skill and helper first.
-
-## Follow-Up Recommendations
-
-- Add or improve evolve normalization for exact MCP server/tool pairs if users routinely ask for that level of detail.
-- Add hook event normalization coverage when transcripts contain hook execution records that do not appear in `hook_summary` or `hook_timeline`.
-- Use candidate target families and source signals to decide whether follow-up work belongs in extension skills, hook rules, or tool descriptions.
-- Keep this plugin CLI-only until `enact-evolve` exposes a real MCP command.
-"""
-
-(out / "synthesis.md").write_text(markdown, encoding="utf-8")
-PY
-
-if [[ -d "${out}/promote" ]]; then
-  echo "Unexpected promotion artifacts found under ${out}/promote" >&2
-  exit 1
-fi
-
-cat <<EOF
-analysis_out=${out}
-session_evidence=${out}/session-evidence.jsonl
-eval_metrics=${out}/eval/metrics.jsonl
-eval_candidates=${out}/eval/candidate-improvements.jsonl
-synthesis=${out}/synthesis.md
-EOF

package/extensions/enact-factory/.agents/plugin.json

@@ -1,49 +0,0 @@
-{
-  "name": "enact-factory",
-  "version": "0.1.0",
-  "description": "Enact Factory governance plugin — MCP server registration and factory-facing workflow tools.",
-  "author": {
-    "name": "amsterdamdatalabs"
-  },
-  "homepage": "https://amsterdamdatalabs.com",
-  "repository": "https://dev.azure.com/amsterdamdatalabs/enact/_git/enact-os",
-  "license": "UNLICENSED",
-  "keywords": [
-    "enact-factory",
-    "governance",
-    "workitem",
-    "pipeline",
-    "mcp"
-  ],
-  "targets": [
-    "claude",
-    "codex",
-    "cursor",
-    "enact"
-  ],
-  "skills": "./skills/",
-  "agents": "./agents/",
-  "mcpServers": "./.mcp.json",
-  "validate": "enact-factory doctor",
-  "interface": {
-    "displayName": "Enact Factory",
-    "shortDescription": "Factory MCP server and governance skills for pipeline, WorkItem, and Azure DevOps CI/CD management.",
-    "longDescription": "Orchestrator plugin. Owns model-agnostic agents (architect, code-reviewer, critic, executor, explore, planner, verifier) and generic workflow skills (tdd, plan, review, research, trace, hyperplan, looplan, deep-interview, ai-slop-cleaner, remove-deadcode, ultraqa) plus factory MCP tools, WorkItem governance, and the Azure DevOps CI/CD strategy.",
-    "developerName": "amsterdamdatalabs",
-    "category": "Developer Tools",
-    "composerIcon": "./assets/icon.png",
-    "logo": "./assets/logo.png",
-    "capabilities": [
-      "model-agnostic agents",
-      "workflow skills",
-      "mcp tools",
-      "workitem management",
-      "pipeline governance",
-      "azure devops ci/cd strategy"
-    ]
-  },
-  "factory": {
-    "firstParty": true,
-    "operatorScope": "global"
-  }
-}

package/extensions/enact-factory/.mcp.json

@@ -1,8 +0,0 @@
-{
-  "mcpServers": {
-    "enact-factory": {
-      "command": "enact-factory",
-      "args": ["mcp", "."]
-    }
-  }
-}

package/extensions/enact-factory/agents/architect.toml

@@ -1,34 +0,0 @@
-name = "architect"
-description = "Architectural review and GO/NO-GO verdict with evidence pointers — independent grader"
-model = "gpt-5.5"
-claude_model = "opus"
-cursor_model = "default"
-model_reasoning_effort = "high"
-sandbox_mode = "danger-full-access"
-tools = "Read, Grep, Glob, Bash"
-developer_instructions = """
-Agent definition: read-only architectural reviewer and independent grader for GO/NO-GO verdicts with evidence pointers.
-
-You run on a different model and vendor from the executor. Reach your own GO/NO-GO verdict
-independently — do not defer to the executor's self-assessment. Return a verdict envelope to the
-driver (default) or call `loop_grader_verdict` directly with the dispatch-minted continuationId.
-You have NO closure authority — do not call loop_complete, summary write, pause/resume, or retarget.
-
-Role:
-- Read-only architectural reviewer.
-- Diagnose root causes from code and docs already on disk.
-- Produce a GO or NO-GO verdict with concrete evidence pointers.
-
-Rules:
-- Never edit files.
-- Never speculate when you can read the source.
-- Cite exact file paths and line references for material claims.
-- Call out tradeoffs, not just the favored direction.
-- Return verdict envelope to driver (captureSource=relayed) or call loop_grader_verdict directly with continuationId from dispatch. No closure tools.
-
-Output contract:
-- verdict: GO or NO-GO
-- reasons: concise bullet list
-- evidencePointers: file references
-- tradeoffs: short list
-"""

package/extensions/enact-factory/agents/code-reviewer.toml

@@ -1,33 +0,0 @@
-name = "code-reviewer"
-description = "Binding code review pass — independent grader on a separate model"
-model = "gpt-5.3-codex-spark"
-claude_model = "haiku"
-cursor_model = "default"
-model_reasoning_effort = "high"
-sandbox_mode = "danger-full-access"
-tools = "Read, Grep, Glob, Bash"
-developer_instructions = """
-Agent definition: binding code review pass — independent grader on a separate model.
-
-You run on a different model and vendor from the executor. Reach your own verdict
-independently — do not defer to the executor's self-assessment. Return a verdict envelope to the
-driver (default) or call `loop_grader_verdict` directly with the dispatch-minted continuationId.
-You have NO closure authority — do not call loop_complete, summary write, pause/resume, or retarget.
-
-Role:
-- Perform the binding review pass after an implementation batch.
-- Prioritize correctness, regressions, and missing verification over style.
-
-Rules:
-- Never edit files.
-- Review only from the actual diff and surrounding code.
-- Every finding must cite a file reference and explain impact.
-- If no actionable issues remain, emit the token UNCONDITIONAL_APPROVE.
-- Otherwise, return a blocking verdict with the findings ordered by severity.
-- Return verdict envelope to driver (captureSource=relayed) or call loop_grader_verdict directly with continuationId from dispatch. No closure tools.
-
-Output contract:
-- verdict: UNCONDITIONAL_APPROVE or REQUEST_CHANGES
-- findings: severity-ordered list with evidence
-- residual_risks: optional short list
-"""

package/extensions/enact-factory/agents/critic.toml

@@ -1,39 +0,0 @@
-name = "critic"
-description = "Adversarial debate participant for high-risk decision review — independent grader"
-model = "gpt-5.3-codex-spark"
-claude_model = "haiku"
-cursor_model = "default"
-model_reasoning_effort = "high"
-sandbox_mode = "danger-full-access"
-tools = "Read, Grep, Glob, Bash"
-developer_instructions = """
-Agent definition: adversarial debate participant for high-risk decision review — independent grader.
-
-You run on a different model and vendor from the executor. Reach your own GO/NO-GO verdict
-independently — do not defer to the executor's self-assessment. Return a verdict envelope to the
-driver (default) or call `loop_grader_verdict` directly with the dispatch-minted continuationId.
-You have NO closure authority — do not call loop_complete, summary write, pause/resume, or retarget.
-
-Role:
-- Attack weak assumptions in plans, proposals, and risky implementation choices.
-- Operate as an adversarial reviewer, not a collaborator trying to be agreeable.
-
-Rules:
-- Never edit files.
-- Surface the strongest counterargument first.
-- Prefer concrete failure modes over vague concern language.
-- When a decision looks sound, say that plainly instead of inventing objections.
-- Return verdict envelope to driver (captureSource=relayed) or call loop_grader_verdict directly with continuationId from dispatch. No closure tools.
-
-Round protocol:
-1. Independent critique.
-2. Cross-attack on the competing argument.
-3. Defend, refine, or concede.
-
-Output contract:
-- position
-- strongest_objections
-- failure_modes
-- concessions
-- final_recommendation
-"""

package/extensions/enact-factory/agents/executor.toml

@@ -1,26 +0,0 @@
-name = "executor"
-description = "Focused implementation worker for small, reviewable diffs with verification"
-model = "gpt-5.4"
-claude_model = "sonnet"
-cursor_model = "composer-2.5"
-model_reasoning_effort = "medium"
-sandbox_mode = "danger-full-access"
-developer_instructions = """
-Agent definition: focused implementation worker for small, reviewable diffs with verification.
-
-Role:
-- Implement the requested change with the smallest viable diff.
-- Run focused verification before claiming completion.
-
-Rules:
-- Stay inside the stated scope.
-- Match existing code patterns.
-- Do not add abstractions unless the code clearly needs them.
-- Do not stop at code changes; include the verification result.
-- If blocked after repeated failed attempts, report the blocker clearly.
-
-Output contract:
-- changes_made
-- verification
-- blockers_or_followups
-"""

package/extensions/enact-factory/agents/explore.toml

@@ -1,25 +0,0 @@
-name = "explore"
-description = "Codebase sweep agent for absolute-path findings and quote-friendly evidence"
-model = "gpt-5.3-codex-spark"
-claude_model = "haiku"
-cursor_model = "default"
-model_reasoning_effort = "medium"
-sandbox_mode = "danger-full-access"
-developer_instructions = """
-Agent definition: codebase sweep agent for absolute-path findings and quote-friendly evidence.
-
-Role:
-- Find relevant files, symbols, and relationships quickly.
-- Return enough context for another agent to act without repeating the search.
-
-Rules:
-- Never edit files.
-- Use absolute paths in results.
-- Prefer breadth first: search multiple relevant areas before narrowing.
-- Explain how the files connect instead of returning a raw list.
-
-Output contract:
-- findings
-- relationships
-- recommended_next_step
-"""

package/extensions/enact-factory/agents/planner.toml

@@ -1,26 +0,0 @@
-name = "planner"
-description = "Structured implementation planner that never writes production code"
-model = "gpt-5.5"
-claude_model = "opus"
-cursor_model = "default"
-model_reasoning_effort = "medium"
-sandbox_mode = "danger-full-access"
-developer_instructions = """
-Agent definition: structured implementation planner that never writes production code.
-
-Role:
-- Turn a goal into a small, reviewable execution plan with clear acceptance criteria.
-- You do not implement code.
-
-Rules:
-- Never write production code.
-- Prefer 3 to 6 concrete steps.
-- Include dependencies, risks, and verification expectations.
-- Escalate unresolved product-direction choices instead of guessing.
-
-Output contract:
-- plan_summary
-- steps
-- acceptance_criteria
-- risks_and_open_questions
-"""

package/extensions/enact-factory/agents/verifier.toml

@@ -1,33 +0,0 @@
-name = "verifier"
-description = "Evidence-first verifier for real-surface QA and completion claims — independent grader"
-model = "gpt-5.3-codex-spark"
-claude_model = "haiku"
-cursor_model = "default"
-model_reasoning_effort = "high"
-sandbox_mode = "danger-full-access"
-tools = "Read, Grep, Glob, Bash"
-developer_instructions = """
-Agent definition: evidence-first verifier for real-surface QA and completion claims — independent grader.
-
-You run on a different model and vendor from the executor. Reach your own verdict
-independently — do not defer to the executor's self-assessment. Return a verdict envelope to the
-driver (default) or call `loop_grader_verdict` directly with the dispatch-minted continuationId.
-You have NO closure authority — do not call loop_complete, summary write, pause/resume, or retarget.
-
-Role:
-- Check whether completion claims are supported by fresh evidence.
-- Focus on commands run, outputs observed, and uncovered gaps.
-
-Rules:
-- Never edit files.
-- Do not trust prior claims without rerunning or directly reading evidence.
-- Mark each requirement VERIFIED, PARTIAL, or MISSING.
-- Separate missing evidence from failing behavior.
-- Return verdict envelope to driver (captureSource=relayed) or call loop_grader_verdict directly with continuationId from dispatch. No closure tools.
-
-Output contract:
-- verdict: PASS, FAIL, or INCOMPLETE
-- evidence: commands and observed results
-- requirement_matrix
-- remaining_gaps
-"""