agentpack-cli 0.3.16__tar.gz → 0.3.18__tar.gz

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentpack-cli
-Version: 0.3.16
+Version: 0.3.18
 Summary: Local MCP context router for Claude Code, Codex, Cursor, and AI coding agents.
 License: MIT
 License-File: LICENSE
@@ -29,6 +29,7 @@ Requires-Dist: watchdog>=4.0.0; extra == 'all'
 Provides-Extra: dev
 Requires-Dist: mypy; extra == 'dev'
 Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: pytest-asyncio; extra == 'dev'
 Requires-Dist: pytest-cov; extra == 'dev'
 Requires-Dist: ruff; extra == 'dev'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'dev'
@@ -140,12 +141,12 @@ Suggested commands:
 
 - **Task-focused packing**: ranks files from git changes, task terms, symbols, imports, related tests, configs, churn, repo history, and deterministic offline summaries.
 - **Budget-aware compression**: emits `full`, `diff`, `symbols`, `skeleton`, or `summary` views instead of all-or-nothing file dumps.
-- **Rendered-token accounting**: budgets against the actual markdown context, not only file payloads.
-- **Reserve buckets**: changed files, tests, docs, and dependencies each get protected selection capacity so one dirty area cannot starve the others.
+- **Rendered-token accounting and reserve buckets**: budgets against actual markdown while protecting changed files, tests, docs, and dependencies.
 - **Execution state**: optional task state files and git-derived fallback status show whether work is planned, in progress, blocked, done, committed, or committed but not pushed.
 - **Thread-scoped context**: explicit `--thread <id>` or `--thread auto` isolates task/context files for multiple agents in one repo and warns on same-branch file overlap.
 - **Task router**: MCP and CLI surfaces route a task to relevant files, scoped rules, installed skills, suggested commands, and safety warnings without executing skills automatically.
-- **Learning layer**: turns task diffs into developer learning notes, skill evidence, and compact lessons future agents can reuse.
+- **Reversible registry and learning layer**: retrieves packed context by block ID, writes developer lessons, and feeds bounded selected-file miss feedback into future ranking.
+- **Runtime scorecard and output compression**: `perf --history` tracks activity, while `compress-output` preserves failures, paths, diffs, and search hits from noisy logs.
 - **Agent integrations**: installs Claude Code, Cursor, Windsurf, Codex, Antigravity, VS Code tasks, git hooks, and MCP configuration.
 - **Local and measurable**: no API calls for scan, summarize, rank, pack, stats, or benchmark; quality is measured with expected-file evals.
 
@@ -376,6 +377,7 @@ gate.
 | `agentpack guard --repair-stale --refresh-context` | Check freshness, repair stale rules, refresh context |
 | `agentpack status` | Show context freshness and git/task state |
 | `agentpack stats` | Show pack size, token savings, and top files |
+| `agentpack dashboard` | Local HTML control plane for context, skills, learning, and benchmark quality |
 | `agentpack explain --task auto` | Debug selected and omitted files |
 | `agentpack diagnose-selection` | Turn latest pack/benchmark signals into concrete tuning actions |
 | `agentpack ignore suggest|apply` | Suggest or apply `.agentignore` improvements |
@@ -459,6 +461,7 @@ AgentPack writes local artifacts under `.agentpack/`:
 | `.agentpack/learning.prompt.md` | optional source-backed prompt for external LLM refinement |
 | `.agentpack/pr-learning-comment.md` | optional PR-comment-ready learning summary |
 | `.agentpack/learning-dashboard.html` | optional static dashboard from `agentpack learn --dashboard` |
+| `.agentpack/dashboard.html` | local project dashboard from `agentpack dashboard` |
 | `.agentpack/team-lessons.md` | optional shared lesson export from `agentpack learn --team-export` |
 | `.agentpack/learning-feedback.jsonl` | optional local helpful/not-helpful feedback records |
 | `.agentpack/pack_metadata.json` | freshness and pack metadata |

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/README.md

@@ -100,12 +100,12 @@ Suggested commands:
 
 - **Task-focused packing**: ranks files from git changes, task terms, symbols, imports, related tests, configs, churn, repo history, and deterministic offline summaries.
 - **Budget-aware compression**: emits `full`, `diff`, `symbols`, `skeleton`, or `summary` views instead of all-or-nothing file dumps.
-- **Rendered-token accounting**: budgets against the actual markdown context, not only file payloads.
-- **Reserve buckets**: changed files, tests, docs, and dependencies each get protected selection capacity so one dirty area cannot starve the others.
+- **Rendered-token accounting and reserve buckets**: budgets against actual markdown while protecting changed files, tests, docs, and dependencies.
 - **Execution state**: optional task state files and git-derived fallback status show whether work is planned, in progress, blocked, done, committed, or committed but not pushed.
 - **Thread-scoped context**: explicit `--thread <id>` or `--thread auto` isolates task/context files for multiple agents in one repo and warns on same-branch file overlap.
 - **Task router**: MCP and CLI surfaces route a task to relevant files, scoped rules, installed skills, suggested commands, and safety warnings without executing skills automatically.
-- **Learning layer**: turns task diffs into developer learning notes, skill evidence, and compact lessons future agents can reuse.
+- **Reversible registry and learning layer**: retrieves packed context by block ID, writes developer lessons, and feeds bounded selected-file miss feedback into future ranking.
+- **Runtime scorecard and output compression**: `perf --history` tracks activity, while `compress-output` preserves failures, paths, diffs, and search hits from noisy logs.
 - **Agent integrations**: installs Claude Code, Cursor, Windsurf, Codex, Antigravity, VS Code tasks, git hooks, and MCP configuration.
 - **Local and measurable**: no API calls for scan, summarize, rank, pack, stats, or benchmark; quality is measured with expected-file evals.
 
@@ -336,6 +336,7 @@ gate.
 | `agentpack guard --repair-stale --refresh-context` | Check freshness, repair stale rules, refresh context |
 | `agentpack status` | Show context freshness and git/task state |
 | `agentpack stats` | Show pack size, token savings, and top files |
+| `agentpack dashboard` | Local HTML control plane for context, skills, learning, and benchmark quality |
 | `agentpack explain --task auto` | Debug selected and omitted files |
 | `agentpack diagnose-selection` | Turn latest pack/benchmark signals into concrete tuning actions |
 | `agentpack ignore suggest|apply` | Suggest or apply `.agentignore` improvements |
@@ -419,6 +420,7 @@ AgentPack writes local artifacts under `.agentpack/`:
 | `.agentpack/learning.prompt.md` | optional source-backed prompt for external LLM refinement |
 | `.agentpack/pr-learning-comment.md` | optional PR-comment-ready learning summary |
 | `.agentpack/learning-dashboard.html` | optional static dashboard from `agentpack learn --dashboard` |
+| `.agentpack/dashboard.html` | local project dashboard from `agentpack dashboard` |
 | `.agentpack/team-lessons.md` | optional shared lesson export from `agentpack learn --team-export` |
 | `.agentpack/learning-feedback.jsonl` | optional local helpful/not-helpful feedback records |
 | `.agentpack/pack_metadata.json` | freshness and pack metadata |

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "agentpack-cli"
-version = "0.3.16"
+version = "0.3.18"
 description = "Local MCP context router for Claude Code, Codex, Cursor, and AI coding agents."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -47,6 +47,7 @@ all = [
 
 dev = [
   "pytest",
+  "pytest-asyncio",
   "pytest-cov",
   "ruff",
   "mypy",
@@ -55,6 +56,7 @@ dev = [
 
 [tool.pytest.ini_options]
 pythonpath = ["src"]
+asyncio_default_fixture_loop_scope = "function"
 markers = [
     "slow: marks tests as slow (deselect with '-m \"not slow\"')",
 ]

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/__init__.py

@@ -1,3 +1,3 @@
 """AgentPack — task-aware context packing for AI coding agents."""
 
-__version__ = "0.3.16"
+__version__ = "0.3.18"

agentpack_cli-0.3.18/src/agentpack/analysis/python_ast.py

@@ -0,0 +1,12 @@
+from __future__ import annotations
+
+import ast
+import warnings
+from pathlib import Path
+
+
+def parse_python_source(source: str, path: Path | str) -> ast.Module:
+    """Parse scanned Python source without surfacing user-code SyntaxWarnings."""
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", SyntaxWarning)
+        return ast.parse(source, filename=str(path))

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/analysis/python_imports.py

@@ -3,11 +3,13 @@ from __future__ import annotations
 import ast
 from pathlib import Path
 
+from agentpack.analysis.python_ast import parse_python_source
+
 
 def extract_imports(path: Path, text: str | None = None) -> list[str]:
     try:
         source = text if text is not None else path.read_text(errors="replace")
-        tree = ast.parse(source)
+        tree = parse_python_source(source, path)
     except SyntaxError:
         return []
 

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/analysis/role_inference.py

@@ -6,6 +6,7 @@ from collections import defaultdict
 from dataclasses import dataclass, field
 from pathlib import Path
 
+from agentpack.analysis.python_ast import parse_python_source
 from agentpack.core.models import Symbol
 
 
@@ -239,7 +240,7 @@ def extract_failure_hints(text: str) -> list[str]:
 
 def _python_intelligence(path: str, text: str, symbols: list[Symbol]) -> CodeIntelligence:
     try:
-        tree = ast.parse(text)
+        tree = parse_python_source(text, path)
     except SyntaxError:
         return CodeIntelligence(defines=[s.name for s in symbols[:40]])
 

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/analysis/symbols.py

@@ -4,13 +4,14 @@ import ast
 import re
 from pathlib import Path
 
+from agentpack.analysis.python_ast import parse_python_source
 from agentpack.core.models import Symbol
 
 
 def extract_python_symbols(path: Path) -> list[Symbol]:
     try:
         source = path.read_text(errors="replace")
-        tree = ast.parse(source)
+        tree = parse_python_source(source, path)
     except (SyntaxError, OSError):
         return []
 

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/application/pack_service.py

@@ -27,6 +27,7 @@ from agentpack.core.models import (
     ScanResult,
     SelectedFile,
 )
+from agentpack.core.pack_registry import save_pack_registry
 from agentpack.core.task_freshness import read_task_md, task_metadata
 from agentpack.core.thread_context import (
     append_thread_index,
@@ -36,6 +37,7 @@ from agentpack.core.thread_context import (
     thread_paths,
 )
 from agentpack.core.token_estimator import estimate_tokens
+from agentpack.learning.feedback import ranking_feedback_boosts
 from agentpack.renderers.markdown import render_claude, render_generic
 from agentpack.analysis.ranking import (
     build_keyword_plan,
@@ -59,6 +61,7 @@ from agentpack.analysis.task_classifier import classify_task
 from agentpack.analysis.tests import find_related_tests
 from agentpack.analysis import dependency_graph as dep_graph_mod
 from agentpack.summaries.base import build_all_summaries
+from agentpack.session.events import record_event
 
 
 @dataclass
@@ -267,6 +270,7 @@ class FileRanker:
                 changes.all_changed,
                 generic_ratio=generic_ratio,
             )
+            scored = _apply_ranking_feedback_boosts(root, scored, task, changes.all_changed)
         return RankResult(
             keywords=keywords,
             keyword_plan=keyword_plan,
@@ -673,6 +677,9 @@ class AdapterRegistry:
                 cfg.learning.dashboard_output,
                 cfg.learning.team_lessons_output,
                 cfg.learning.feedback_output,
+                cfg.learning.ranking_feedback_output,
+                cfg.runtime.pack_registry_output,
+                cfg.runtime.session_events_output,
             }
         )
         return paths
@@ -789,6 +796,29 @@ class PackService:
             concurrent_context=pack_obj.concurrent_context,
             metadata_path=scoped_paths.metadata if scoped_paths else None,
         )
+        save_pack_registry(
+            root,
+            pack_obj,
+            packable,
+            output_path=cfg.runtime.pack_registry_output,
+            max_records=cfg.runtime.max_registry_records,
+        )
+        record_event(
+            root,
+            "pack",
+            {
+                "task": request.task,
+                "agent": request.agent,
+                "mode": plan.mode,
+                "packed_tokens": packed_tokens,
+                "raw_tokens": all_tokens,
+                "selected_files": len(pack_obj.selected_files),
+                "omitted_files": len(pack_obj.omitted_relevant_files),
+                "changed_files": len(pack_obj.changed_files),
+                "context_path": str(out_path.relative_to(root)),
+            },
+            output_path=cfg.runtime.session_events_output,
+        )
         if thread_row:
             append_thread_index(root, thread_row)
         excluded_receipts = [r for r in pack_obj.receipts if r.action == "excluded"]
@@ -1145,6 +1175,25 @@ def _apply_history_penalties(
     return adjusted
 
 
+def _apply_ranking_feedback_boosts(
+    root: Path,
+    scored: list[tuple[Any, float, list[str]]],
+    task: str,
+    changed_paths: set[str],
+) -> list[tuple[Any, float, list[str]]]:
+    boosts = ranking_feedback_boosts(root, task)
+    if not boosts:
+        return scored
+    adjusted: list[tuple[Any, float, list[str]]] = []
+    for fi, score, reasons in scored:
+        boost = boosts.get(fi.path, 0.0)
+        if boost <= 0 or fi.path in changed_paths:
+            adjusted.append((fi, score, reasons))
+            continue
+        adjusted.append((fi, score + boost, [*reasons, f"learning feedback miss boost +{boost:.0f}"]))
+    return adjusted
+
+
 def _history_noise_counts(root: Path, *, window: int = 20) -> dict[str, int]:
     metrics_path = root / ".agentpack" / "metrics.jsonl"
     if not metrics_path.exists():

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/cli.py

@@ -5,6 +5,8 @@ from agentpack.commands import (
     benchmark,
     claude_cmd,
     ci_cmd,
+    compress_output,
+    dashboard,
     dev_check,
     diagnose_selection,
     diff,
@@ -17,14 +19,17 @@ from agentpack.commands import (
     init,
     install,
     learn,
+    memory,
     mcp_cmd,
     migrate,
     monitor,
     next_cmd,
     pack,
+    perf,
     quickstart,
     release_cmd,
     release_check,
+    retrieve,
     repair,
     route,
     scan,
@@ -39,6 +44,7 @@ from agentpack.commands import (
     tune,
     verify_wheel,
     watch,
+    wrap,
     workflow_cmd,
 )
 from agentpack import __version__
@@ -70,9 +76,13 @@ for mod in [
     task_cmd,
     threads,
     stats,
+    dashboard,
     summarize,
+    compress_output,
     learn,
+    memory,
     pack,
+    perf,
     install,
     repair,
     route,
@@ -97,7 +107,9 @@ for mod in [
     skills,
     release_check,
     release_cmd,
+    retrieve,
     start_cmd,
+    wrap,
     workflow_cmd,
 ]:
     mod.register(app)

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/commands/benchmark.py

@@ -1930,21 +1930,21 @@ def benchmark(
     mode: str = typer.Option("balanced", "--mode", help="Mode for single-task run (lite|minimal|balanced|deep)."),
     workspace: str = typer.Option("", "--workspace", help="Restrict benchmark packs to a workspace, e.g. apps/web."),
     cases: str = typer.Option("", "--cases", help="Path to TOML cases file (default: .agentpack/benchmark.toml)."),
-    compare: bool = typer.Option(False, "--compare", is_flag=True, help="Compare minimal/balanced/deep for each task."),
-    init: bool = typer.Option(False, "--init", is_flag=True, help="Scaffold a benchmark.toml and exit."),
-    results_template: bool = typer.Option(False, "--results-template", is_flag=True, help="Create benchmarks/results/YYYY-MM-DD.md for publishing benchmark evidence."),
+    compare: bool = typer.Option(False, "--compare", help="Compare minimal/balanced/deep for each task."),
+    init: bool = typer.Option(False, "--init", help="Scaffold a benchmark.toml and exit."),
+    results_template: bool = typer.Option(False, "--results-template", help="Create benchmarks/results/YYYY-MM-DD.md for publishing benchmark evidence."),
     from_history: int = typer.Option(0, "--from-history", help="Sample last N unique tasks from metrics.jsonl history."),
     write_cases: bool = typer.Option(False, "--write-cases", help="Append --from-history cases to .agentpack/benchmark.toml."),
-    sample_fixtures: bool = typer.Option(False, "--sample-fixtures", is_flag=True, help="Run bundled FastAPI/Next.js/mixed-repo fixture evals from a source checkout."),
-    release_gate: bool = typer.Option(False, "--release-gate", is_flag=True, help="Run the public real-repo release gate."),
-    public_repos: bool = typer.Option(False, "--public-repos", is_flag=True, help="Run real public-repo commit cases from benchmarks/public-repos.toml."),
+    sample_fixtures: bool = typer.Option(False, "--sample-fixtures", help="Run bundled FastAPI/Next.js/mixed-repo fixture evals from a source checkout."),
+    release_gate: bool = typer.Option(False, "--release-gate", help="Run the public real-repo release gate."),
+    public_repos: bool = typer.Option(False, "--public-repos", help="Run real public-repo commit cases from benchmarks/public-repos.toml."),
     public_repos_file: str = typer.Option("", "--public-repos-file", help="Path to public repo benchmark manifest."),
     public_repos_cache: str = typer.Option("", "--public-repos-cache", help="Directory for cached public repo clones."),
-    refresh_public_repos: bool = typer.Option(False, "--refresh-public-repos", is_flag=True, help="Delete and reclone public repo benchmark cache before running."),
-    public_table: bool = typer.Option(False, "--public-table", is_flag=True, help="Write a publishable Markdown benchmark table under benchmarks/results/."),
+    refresh_public_repos: bool = typer.Option(False, "--refresh-public-repos", help="Delete and reclone public repo benchmark cache before running."),
+    public_table: bool = typer.Option(False, "--public-table", help="Write a publishable Markdown benchmark table under benchmarks/results/."),
     no_public_table: bool = typer.Option(False, "--no-public-table", help="Do not write a benchmark results markdown table."),
-    misses: bool = typer.Option(False, "--misses", is_flag=True, help="Show diagnostics for expected files that were not selected."),
-    prove_targets: bool = typer.Option(False, "--prove-targets", is_flag=True, help="Exit non-zero unless recall/token precision targets pass."),
+    misses: bool = typer.Option(False, "--misses", help="Show diagnostics for expected files that were not selected."),
+    prove_targets: bool = typer.Option(False, "--prove-targets", help="Exit non-zero unless recall/token precision targets pass."),
     min_recall: float = typer.Option(0.60, "--min-recall", help="Recall target for --prove-targets."),
     min_token_precision: float = typer.Option(0.50, "--min-token-precision", help="Token precision target for --prove-targets."),
 ) -> None:

agentpack_cli-0.3.18/src/agentpack/commands/compress_output.py

@@ -0,0 +1,33 @@
+from __future__ import annotations
+
+import sys
+
+import typer
+
+from agentpack.commands._shared import _root
+from agentpack.core.config import load_config
+from agentpack.output_compression import compress_output
+from agentpack.session.events import record_event
+
+
+def register(app: typer.Typer) -> None:
+    @app.command("compress-output")
+    def compress_output_cmd(
+        file: str = typer.Argument("-", help="Output file to summarize, or '-' for stdin."),
+        kind: str = typer.Option("auto", "--kind", help="Output kind: auto|pytest|npm|git-diff|rg|ls."),
+    ) -> None:
+        """Summarize noisy command output while preserving actionable lines."""
+        root = _root()
+        cfg = load_config(root)
+        if file == "-":
+            content = sys.stdin.read()
+        else:
+            content = (root / file).read_text(encoding="utf-8", errors="replace")
+        result = compress_output(content, kind=kind, max_items=cfg.runtime.max_output_summary_items)
+        record_event(
+            root,
+            "compress_output",
+            {"kind": kind, "input_chars": len(content), "output_chars": len(result)},
+            output_path=cfg.runtime.session_events_output,
+        )
+        typer.echo(result, nl=False)

agentpack_cli-0.3.18/src/agentpack/commands/dashboard.py

@@ -0,0 +1,43 @@
+from __future__ import annotations
+
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+import typer
+
+from agentpack.commands._shared import _atomic_write, _root, console
+from agentpack.dashboard.collectors import build_project_dashboard_snapshot
+from agentpack.dashboard.renderers import render_dashboard_html
+
+
+def register(app: typer.Typer) -> None:
+    @app.command()
+    def dashboard(
+        json_output: bool = typer.Option(False, "--json", help="Print normalized dashboard snapshot JSON."),
+        open_browser: bool = typer.Option(False, "--open", help="Open the generated HTML dashboard."),
+        output: str = typer.Option("", "--output", "-o", help="Dashboard HTML output path."),
+    ) -> None:
+        """Generate a local AgentPack dashboard."""
+        root = _root()
+        snapshot = build_project_dashboard_snapshot(root)
+        if json_output:
+            typer.echo(json.dumps(snapshot.model_dump(mode="json"), indent=2, sort_keys=True))
+            return
+
+        out = root / (output or ".agentpack/dashboard.html")
+        out.parent.mkdir(parents=True, exist_ok=True)
+        _atomic_write(out, render_dashboard_html(snapshot))
+        console.print(f"[green]✓[/] Wrote [bold]{out}[/]")
+        if open_browser:
+            _open_file(out)
+
+
+def _open_file(path: Path) -> None:
+    if sys.platform == "darwin":
+        subprocess.run(["open", str(path)], check=False)
+    elif sys.platform.startswith("win"):
+        subprocess.run(["cmd", "/c", "start", "", str(path)], check=False)
+    else:
+        subprocess.run(["xdg-open", str(path)], check=False)

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/commands/eval_cmd.py

@@ -28,25 +28,25 @@ from agentpack.core.evals import (
 def register(app: typer.Typer) -> None:
     @app.command(name="eval")
     def eval_command(
-        init: bool = typer.Option(False, "--init", is_flag=True, help="Scaffold .agentpack/evals.toml and exit."),
+        init: bool = typer.Option(False, "--init", help="Scaffold .agentpack/evals.toml and exit."),
         cases: str = typer.Option("", "--cases", help="Path to eval TOML file (default: .agentpack/evals.toml)."),
         case: str = typer.Option("", "--case", help="Run one eval case by id."),
-        prove_targets: bool = typer.Option(False, "--prove-targets", is_flag=True, help="Exit non-zero when any eval case fails."),
+        prove_targets: bool = typer.Option(False, "--prove-targets", help="Exit non-zero when any eval case fails."),
         capture: str = typer.Option("", "--capture", help="Append a case from current git diff using this id."),
         failure_class: str = typer.Option("context", "--failure-class", help=f"Failure class ({' | '.join(FAILURE_CLASSES)})."),
         failure_source: str = typer.Option("agent_failed", "--failure-source", help="Failure source for captured cases."),
         check: list[str] | None = typer.Option(None, "--check", help="Deterministic command check for --capture. Repeatable."),
         task: str = typer.Option("", "--task", help="Task text for --capture."),
         base_ref: str = typer.Option("HEAD", "--base-ref", help="Git base ref for diff checks."),
-        report: bool = typer.Option(False, "--report", is_flag=True, help="Write benchmarks/results/YYYY-MM-DD-eval.md."),
-        ci_template: bool = typer.Option(False, "--ci-template", is_flag=True, help="Scaffold .github/workflows/agentpack-eval.yml and exit."),
+        report: bool = typer.Option(False, "--report", help="Write benchmarks/results/YYYY-MM-DD-eval.md."),
+        ci_template: bool = typer.Option(False, "--ci-template", help="Scaffold .github/workflows/agentpack-eval.yml and exit."),
         variant: str = typer.Option("agentpack", "--variant", help="Result variant label, e.g. baseline or agentpack."),
         compare_variants: str = typer.Option("", "--compare-variants", help="Compare latest results as BASELINE:VARIANT."),
-        replay: bool = typer.Option(False, "--replay", is_flag=True, help="Run cases in isolated git worktrees using captured patch_file artifacts."),
-        watch: bool = typer.Option(False, "--watch", is_flag=True, help="Rerun evals when git diff state changes."),
+        replay: bool = typer.Option(False, "--replay", help="Run cases in isolated git worktrees using captured patch_file artifacts."),
+        watch: bool = typer.Option(False, "--watch", help="Rerun evals when git diff state changes."),
         interval: float = typer.Option(2.0, "--interval", help="Watch polling interval in seconds."),
         max_runs: int = typer.Option(0, "--max-runs", help="Maximum watch runs (0 = unlimited)."),
-        until_pass: bool = typer.Option(False, "--until-pass", is_flag=True, help="Stop watch mode after all cases pass."),
+        until_pass: bool = typer.Option(False, "--until-pass", help="Stop watch mode after all cases pass."),
         agent: str = typer.Option("", "--agent", help="Agent label to store with --capture metadata."),
         prompt_file: str = typer.Option("", "--prompt-file", help="Prompt artifact path to store with --capture."),
         context_file: str = typer.Option(".agentpack/context.md", "--context-file", help="Context artifact path to store with --capture."),

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/commands/explain.py

@@ -294,9 +294,9 @@ def register(app: typer.Typer) -> None:
         budget: int = typer.Option(0, "--budget", help="Token budget (0 = use config default)."),
         since: Optional[str] = typer.Option(None, "--since", help="Git ref to compare against (e.g. HEAD~1, main)."),
         file: Optional[str] = typer.Option(None, "--file", help="Show detailed score breakdown for a specific file."),
-        omitted: bool = typer.Option(False, "--omitted", is_flag=True, help="Show top-10 excluded files and why."),
-        why_noisy: bool = typer.Option(False, "--why-noisy", is_flag=True, help="Explain broad task terms and noisy selection signals."),
-        budget_plan: bool = typer.Option(False, "--budget-plan", is_flag=True, help="Show selected modes, token costs, and value per token."),
+        omitted: bool = typer.Option(False, "--omitted", help="Show top-10 excluded files and why."),
+        why_noisy: bool = typer.Option(False, "--why-noisy", help="Explain broad task terms and noisy selection signals."),
+        budget_plan: bool = typer.Option(False, "--budget-plan", help="Show selected modes, token costs, and value per token."),
     ) -> None:
         """Explain which files would be selected and why, without writing a context file."""
         if mode not in ("lite", "minimal", "balanced", "deep"):

{agentpack_cli-0.3.16 → agentpack_cli-0.3.18}/src/agentpack/commands/init.py

@@ -55,13 +55,9 @@ def _repo_gitignore_entries(share_cache: bool = False, agent: str = "generic") -
             ".agentpack/snapshots/",
             ".agentpack/context*",
             ".agentpack/metrics.jsonl",
+            ".agentpack/session-events.jsonl",
             ".agentpack/pack_metadata.json",
-            ".agentpack/activity.log",
-            ".agentpack/.gitignore",
-            ".agentpack/.mcp_reminded",
-            ".agentpack/session.json",
-            ".agentpack/task.md",
-            ".agentpack/benchmark_results.jsonl",
+            ".agentpack/pack-registry.json",
             ".agentpack/learning.md",
             ".agentpack/daily-summary.md",
             ".agentpack/skills-progress.json",
@@ -71,6 +67,18 @@ def _repo_gitignore_entries(share_cache: bool = False, agent: str = "generic") -
             ".agentpack/learning-dashboard.html",
             ".agentpack/team-lessons.md",
             ".agentpack/learning-feedback.jsonl",
+            ".agentpack/ranking-feedback.jsonl",
+            ".agentpack/learning-inputs.json",
+            ".agentpack/activity.log",
+            ".agentpack/.gitignore",
+            ".agentpack/.mcp_reminded",
+            ".agentpack/session.json",
+            ".agentpack/task.md",
+            ".agentpack/benchmark_results.jsonl",
+            ".agentpack/loop_state.json",
+            ".agentpack/progress.md",
+            ".agentpack/loop_events.jsonl",
+            ".agentpack/loop_failures.jsonl",
             ".agentignore",
         ]
     )
@@ -97,12 +105,9 @@ def _agentpack_gitignore_content(share_cache: bool = False) -> str:
             "snapshots/",
             "context.*",
             "metrics.jsonl",
+            "session-events.jsonl",
             "pack_metadata.json",
-            "activity.log",
-            ".mcp_reminded",
-            "session.json",
-            "task.md",
-            "benchmark_results.jsonl",
+            "pack-registry.json",
             "learning.md",
             "daily-summary.md",
             "skills-progress.json",
@@ -112,6 +117,17 @@ def _agentpack_gitignore_content(share_cache: bool = False) -> str:
             "learning-dashboard.html",
             "team-lessons.md",
             "learning-feedback.jsonl",
+            "ranking-feedback.jsonl",
+            "learning-inputs.json",
+            "activity.log",
+            ".mcp_reminded",
+            "session.json",
+            "task.md",
+            "benchmark_results.jsonl",
+            "loop_state.json",
+            "progress.md",
+            "loop_events.jsonl",
+            "loop_failures.jsonl",
         ]
     )
     return "\n".join(entries) + "\n"