agentpack-cli 0.1.23__tar.gz → 0.1.25__tar.gz

agentpack_cli-0.1.25/.gitignore

@@ -0,0 +1,33 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+build/
+.eggs/
+*.egg
+
+.venv/
+venv/
+env/
+
+# agentpack:start
+# AgentPack generated context/cache (safe to ignore)
+.agentpack/cache/
+.agentpack/snapshots/
+.agentpack/context*
+.agentpack/metrics.jsonl
+.agentpack/pack_metadata.json
+.agentpack/activity.log
+.agentpack/.gitignore
+.agentpack/.mcp_reminded
+.agentpack/session.json
+.agentpack/task.md
+.agentpack/benchmark_results.jsonl
+.agent/skills/agentpack/
+# agentpack:end
+
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+
+*.dist-info/

{agentpack_cli-0.1.23 → agentpack_cli-0.1.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentpack-cli
-Version: 0.1.23
+Version: 0.1.25
 Summary: Task-aware context packing for AI coding agents — Claude, Cursor, Windsurf, Codex, and Antigravity
 License: MIT
 License-File: LICENSE
@@ -44,7 +44,7 @@ Description-Content-Type: text/markdown
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![CI](https://github.com/vishal2612200/agentpack/actions/workflows/ci.yml/badge.svg)](https://github.com/vishal2612200/agentpack/actions/workflows/ci.yml)
 
-> **Status: alpha (v0.1.23).** Works, tested, used in real sessions. Python and JavaScript/TypeScript are the best-supported languages. Not yet validated across a wide range of repos. API may change before 1.0.
+> **Status: alpha (v0.1.25).** Works, tested, used in real sessions. Python and JavaScript/TypeScript are the best-supported languages. Not yet validated across a wide range of repos. API may change before 1.0.
 >
 > **Platform note:** macOS and Linux are fully supported. Windows support is not yet implemented (git hooks use POSIX shell; the Claude Code session hooks use `python3`/`rm -f`). Contributions welcome.
 
@@ -642,6 +642,7 @@ agentpack init --share-cache    # commit cache/ to git for team sharing
 
 Creates:
 ```
+.gitignore                # patched idempotently with AgentPack generated artifacts
 .agentignore              # gitignore-style file exclusion rules
 .agentpack/
   config.toml             # configuration (safe to commit)
@@ -896,6 +897,7 @@ Mode comparison: fix auth token expiry
 [[cases]]
 task = "fix auth token expiry"
 mode = "balanced"
+task_type = "backend-api"
 expected_files = [
   "src/auth/token.py",
   "src/auth/session.py",
@@ -909,6 +911,8 @@ expected_files = [
 
 Use `--misses` when recall is low. It prints each expected file that was not selected with status, rank, score, and scoring reasons, which helps separate ignored files, budget cuts, low scores, and missing dependency signals.
 
+Add `task_type` to group results by workflow area. Benchmark summaries report average precision, recall, F1, and token noise by type, so a repo can show "backend-api is good, frontend-web is noisy" instead of hiding that under one aggregate.
+
 ---
 
 ### `agentpack scan`
@@ -949,7 +953,7 @@ agentpack benchmark --compare --misses
 
 `--sample-fixtures` runs bundled FastAPI, Next.js, and mixed Python/TypeScript fixture evals from an AgentPack source checkout. It is a smoke test, not a claim about your repo.
 
-For an 8+ usefulness signal, use `benchmark.toml` with real third-party or customer-style repos: 5-20 historical tasks, the files actually changed for each task, and `--compare` results for recall, F1, rank@K, and token noise. That is better than trusting generic benchmarks because it tells you whether AgentPack selects the files that matter in code the package has never seen.
+For an 8+ usefulness signal, use `benchmark.toml` with real third-party or customer-style repos: 5-20 historical tasks, `task_type` labels, the files actually changed for each task, and `--compare` results for recall, F1, rank@K, and token noise. That is better than trusting generic benchmarks because it tells you whether AgentPack selects the files that matter in code the package has never seen.
 
 ---
 
@@ -1111,8 +1115,11 @@ Works like `.gitignore`. Default rules exclude:
 .agentignore              ✓ commit
 .agentpack/config.toml    ✓ commit
 .agentpack/cache/         ✓ commit if --share-cache (recommended for teams)
+.agentpack/.gitignore     ✗ gitignored
 .agentpack/snapshots/     ✗ gitignored
 .agentpack/context.*      ✗ gitignored
+.agentpack/task.md        ✗ gitignored (local current task)
+.agent/skills/agentpack/  ✗ gitignored (generated Antigravity context)
 ```
 
 ---

{agentpack_cli-0.1.23 → agentpack_cli-0.1.25}/README.md

@@ -5,7 +5,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![CI](https://github.com/vishal2612200/agentpack/actions/workflows/ci.yml/badge.svg)](https://github.com/vishal2612200/agentpack/actions/workflows/ci.yml)
 
-> **Status: alpha (v0.1.23).** Works, tested, used in real sessions. Python and JavaScript/TypeScript are the best-supported languages. Not yet validated across a wide range of repos. API may change before 1.0.
+> **Status: alpha (v0.1.25).** Works, tested, used in real sessions. Python and JavaScript/TypeScript are the best-supported languages. Not yet validated across a wide range of repos. API may change before 1.0.
 >
 > **Platform note:** macOS and Linux are fully supported. Windows support is not yet implemented (git hooks use POSIX shell; the Claude Code session hooks use `python3`/`rm -f`). Contributions welcome.
 
@@ -603,6 +603,7 @@ agentpack init --share-cache    # commit cache/ to git for team sharing
 
 Creates:
 ```
+.gitignore                # patched idempotently with AgentPack generated artifacts
 .agentignore              # gitignore-style file exclusion rules
 .agentpack/
   config.toml             # configuration (safe to commit)
@@ -857,6 +858,7 @@ Mode comparison: fix auth token expiry
 [[cases]]
 task = "fix auth token expiry"
 mode = "balanced"
+task_type = "backend-api"
 expected_files = [
   "src/auth/token.py",
   "src/auth/session.py",
@@ -870,6 +872,8 @@ expected_files = [
 
 Use `--misses` when recall is low. It prints each expected file that was not selected with status, rank, score, and scoring reasons, which helps separate ignored files, budget cuts, low scores, and missing dependency signals.
 
+Add `task_type` to group results by workflow area. Benchmark summaries report average precision, recall, F1, and token noise by type, so a repo can show "backend-api is good, frontend-web is noisy" instead of hiding that under one aggregate.
+
 ---
 
 ### `agentpack scan`
@@ -910,7 +914,7 @@ agentpack benchmark --compare --misses
 
 `--sample-fixtures` runs bundled FastAPI, Next.js, and mixed Python/TypeScript fixture evals from an AgentPack source checkout. It is a smoke test, not a claim about your repo.
 
-For an 8+ usefulness signal, use `benchmark.toml` with real third-party or customer-style repos: 5-20 historical tasks, the files actually changed for each task, and `--compare` results for recall, F1, rank@K, and token noise. That is better than trusting generic benchmarks because it tells you whether AgentPack selects the files that matter in code the package has never seen.
+For an 8+ usefulness signal, use `benchmark.toml` with real third-party or customer-style repos: 5-20 historical tasks, `task_type` labels, the files actually changed for each task, and `--compare` results for recall, F1, rank@K, and token noise. That is better than trusting generic benchmarks because it tells you whether AgentPack selects the files that matter in code the package has never seen.
 
 ---
 
@@ -1072,8 +1076,11 @@ Works like `.gitignore`. Default rules exclude:
 .agentignore              ✓ commit
 .agentpack/config.toml    ✓ commit
 .agentpack/cache/         ✓ commit if --share-cache (recommended for teams)
+.agentpack/.gitignore     ✗ gitignored
 .agentpack/snapshots/     ✗ gitignored
 .agentpack/context.*      ✗ gitignored
+.agentpack/task.md        ✗ gitignored (local current task)
+.agent/skills/agentpack/  ✗ gitignored (generated Antigravity context)
 ```
 
 ---

{agentpack_cli-0.1.23 → agentpack_cli-0.1.25}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "agentpack-cli"
-version = "0.1.23"
+version = "0.1.25"
 description = "Task-aware context packing for AI coding agents — Claude, Cursor, Windsurf, Codex, and Antigravity"
 readme = "README.md"
 requires-python = ">=3.10"

{agentpack_cli-0.1.23 → agentpack_cli-0.1.25}/src/agentpack/__init__.py

@@ -1,3 +1,3 @@
 """AgentPack — task-aware context packing for AI coding agents."""
 
-__version__ = "0.1.23"
+__version__ = "0.1.25"

{agentpack_cli-0.1.23 → agentpack_cli-0.1.25}/src/agentpack/analysis/ranking.py

@@ -16,6 +16,16 @@ _STOPWORDS = {
     "use", "using", "used", "how", "what", "when", "where", "why",
 }
 
+_GENERIC_TASK_TERMS = {
+    "add", "added", "change", "changed", "changes", "clean", "cleanup",
+    "code", "commit", "context", "debug", "dev", "development", "doc",
+    "docs", "eval", "evals", "feature", "fix", "freshness", "general",
+    "impl", "implement", "implementation", "improve", "issue", "metric", "metrics",
+    "noise", "noisy", "package", "pack", "packs", "release", "repo",
+    "source", "sync", "task", "tasks", "test", "tests", "update", "use",
+    "useful", "usefulness", "version", "workflow", "workflows",
+}
+
 _CONCEPT_MAP: dict[str, frozenset[str]] = {
     # rate limiting
     "rate": frozenset({"throttle", "ratelimit", "leaky", "bucket", "debounce", "backoff", "quota"}),
@@ -219,15 +229,18 @@ def extract_keyword_weights(task: str) -> dict[str, float]:
             continue
         if word in _STOPWORDS:
             continue
-        _add_keyword_weight(keyword_weights, word, 1.0)
+        literal_weight = 0.25 if word in _GENERIC_TASK_TERMS else 1.0
+        _add_keyword_weight(keyword_weights, word, literal_weight)
         if word in _VARIANTS:
-            _add_keyword_weight(keyword_weights, _VARIANTS[word], 0.75)
+            variant = _VARIANTS[word]
+            variant_weight = 0.25 if variant in _GENERIC_TASK_TERMS else min(0.75, literal_weight)
+            _add_keyword_weight(keyword_weights, variant, variant_weight)
 
     # Expand via concept map one level only. Expanded concepts are weaker than
     # literal task words so broad terms like "task" do not dominate ranking.
     expanded: dict[str, float] = {}
     for kw in keyword_weights:
-        if kw in _CONCEPT_MAP:
+        if kw in _CONCEPT_MAP and kw not in _GENERIC_TASK_TERMS:
             for synonym in _CONCEPT_MAP[kw]:
                 _add_keyword_weight(expanded, synonym, 0.35)
                 if synonym in _VARIANTS:
@@ -237,6 +250,17 @@ def extract_keyword_weights(task: str) -> dict[str, float]:
     return keyword_weights
 
 
+def generic_task_term_ratio(task: str) -> float:
+    words = [
+        word for word in re.split(r"[^a-zA-Z0-9]+", task.lower())
+        if len(word) >= 3 and word not in _STOPWORDS
+    ]
+    if not words:
+        return 0.0
+    generic = sum(1 for word in words if word in _GENERIC_TASK_TERMS)
+    return generic / len(words)
+
+
 def extract_keywords(task: str) -> set[str]:
     return set(extract_keyword_weights(task))
 

{agentpack_cli-0.1.23 → agentpack_cli-0.1.25}/src/agentpack/application/pack_service.py

@@ -16,12 +16,14 @@ from agentpack.core import git
 from agentpack.core.context_pack import select_files, save_pack_metadata
 from agentpack.core.models import ContextPack, DependencyGraph, FileInfo, ScanResult, SelectedFile, Receipt
 from agentpack.core.token_estimator import estimate_tokens
+from agentpack.renderers.markdown import render_generic
 from agentpack.analysis.ranking import (
     score_files,
     extract_keyword_weights,
     enrich_keyword_weights_from_files,
     boost_paired_tests,
     boost_cross_layer_related,
+    generic_task_term_ratio,
 )
 from agentpack.analysis.tests import find_related_tests
 from agentpack.analysis import dependency_graph as dep_graph_mod
@@ -37,6 +39,7 @@ class PackRequest:
     budget: int
     since: str | None
     refresh: bool
+    task_source: str = "explicit"
 
 
 @dataclass
@@ -57,6 +60,7 @@ class ChangeSet:
     all_changed: set[str]
     git_staged: set[str]
     recently_modified: list[str]
+    source: str
     current_snap: dict[str, Any] = field(default_factory=dict)
 
 
@@ -64,6 +68,7 @@ class ChangeSet:
 class RankResult:
     """Result of keyword extraction and file scoring."""
     keywords: set[str]
+    generic_ratio: float
     scored: list[tuple[Any, float, list[str]]]
 
 
@@ -80,6 +85,8 @@ class PackPlan:
     git_staged: set[str]
     recently_modified: list[str]
     keywords: set[str]
+    generic_task_ratio: float
+    changed_files_source: str
     scored: list[tuple[Any, float, list[str]]]
     selected: list[SelectedFile]
     receipts: list[Receipt]
@@ -119,6 +126,7 @@ class ChangeDetector:
             all_changed=changed_from_snap | git_changed,
             git_staged=git_staged,
             recently_modified=recently_modified,
+            source=_change_source(root, since, changed_from_snap, git_changed),
             current_snap=current_snap,
         )
 
@@ -140,6 +148,7 @@ class FileRanker:
         keyword_weights = extract_keyword_weights(task)
         keyword_weights = enrich_keyword_weights_from_files(keyword_weights, changes.all_changed, packable)
         keywords = set(keyword_weights)
+        generic_ratio = generic_task_term_ratio(task)
         all_paths = {f.path for f in packable}
 
         for fi in packable:
@@ -165,7 +174,7 @@ class FileRanker:
         )
         scored = boost_cross_layer_related(scored, keyword_weights, weights=cfg.scoring)
         scored = boost_paired_tests(scored, weights=cfg.scoring)
-        return RankResult(keywords=keywords, scored=scored)
+        return RankResult(keywords=keywords, generic_ratio=generic_ratio, scored=scored)
 
 
 class PackPlanner:
@@ -185,6 +194,7 @@ class PackPlanner:
             previous_snapshot=previous_snap,
             include_globs=cfg.project.include_globs or None,
             exclude_globs=cfg.project.exclude_globs or None,
+            always_skip_paths=AdapterRegistry.generated_output_paths(root, cfg),
         )
         phase_times["scan"] = time.perf_counter() - t0
 
@@ -217,8 +227,8 @@ class PackPlanner:
             budget=effective_budget,
             max_file_tokens=cfg.context.max_file_tokens,
             keywords=rank_result.keywords,
-            min_summary_score=cfg.context.min_summary_score,
-            max_summary_files=_summary_cap_for_mode(cfg, request.mode),
+            min_summary_score=_summary_score_floor(cfg, rank_result.generic_ratio),
+            max_summary_files=_summary_cap_for_mode(cfg, request.mode, rank_result.generic_ratio),
         )
         phase_times["select"] = time.perf_counter() - t0
 
@@ -233,6 +243,8 @@ class PackPlanner:
             git_staged=changes.git_staged,
             recently_modified=changes.recently_modified,
             keywords=rank_result.keywords,
+            generic_task_ratio=rank_result.generic_ratio,
+            changed_files_source=changes.source,
             scored=rank_result.scored,
             selected=selected,
             receipts=receipts,
@@ -245,7 +257,7 @@ class AdapterRegistry:
     """Maps agent names to adapter instances; extensible without touching PackService."""
 
     @staticmethod
-    def get(agent: str, cfg: Any) -> Any:
+    def _factories(cfg: Any) -> dict[str, Any]:
         from agentpack.adapters.antigravity import AntigravityAdapter
         from agentpack.adapters.claude import ClaudeAdapter
         from agentpack.adapters.codex import CodexAdapter
@@ -253,15 +265,33 @@ class AdapterRegistry:
         from agentpack.adapters.windsurf import WindsurfAdapter
         from agentpack.adapters.generic import GenericAdapter
 
-        adapters = {
+        return {
             "antigravity": lambda: AntigravityAdapter(),
             "claude": lambda: ClaudeAdapter(cfg.agents.claude.output),
             "cursor": lambda: CursorAdapter(cfg.agents.generic.output),
             "windsurf": lambda: WindsurfAdapter(cfg.agents.generic.output),
             "codex": lambda: CodexAdapter(cfg.agents.generic.output),
+            "generic": lambda: GenericAdapter(cfg.agents.generic.output),
         }
+
+    @staticmethod
+    def get(agent: str, cfg: Any) -> Any:
+        from agentpack.adapters.generic import GenericAdapter
+
+        adapters = AdapterRegistry._factories(cfg)
         return adapters.get(agent, lambda: GenericAdapter(cfg.agents.generic.output))()
 
+    @staticmethod
+    def generated_output_paths(root: Path, cfg: Any) -> set[str]:
+        paths: set[str] = set()
+        for factory in AdapterRegistry._factories(cfg).values():
+            try:
+                out_path = factory().output_path(root)
+                paths.add(str(out_path.relative_to(root)).replace("\\", "/"))
+            except (OSError, ValueError):
+                continue
+        return paths
+
 
 class PackService:
     """Materializes a plan from PackPlanner into a written context file."""
@@ -279,6 +309,13 @@ class PackService:
         saving_pct = (1 - packed_tokens / all_tokens) * 100 if all_tokens > 0 else 0.0
 
         all_redaction_warnings = [w for sf in plan.selected for w in sf.redaction_warnings]
+        freshness = _build_freshness_metadata(
+            root,
+            request=request,
+            plan=plan,
+            snapshot_root_hash=plan.current_snap["root_hash"],
+        )
+        freshness_warnings = _freshness_warnings(root, request, freshness)
 
         pack_obj = ContextPack(
             task=request.task,
@@ -294,12 +331,15 @@ class PackService:
             receipts=plan.receipts if cfg.context.include_receipts else [],
             redaction_warnings=all_redaction_warnings,
             stale=False,
+            freshness=freshness,
+            freshness_warnings=freshness_warnings,
         )
 
         adapter = AdapterRegistry.get(request.agent, cfg)
 
         t0 = time.perf_counter()
         out_path = adapter.write(pack_obj, root)
+        _write_canonical_context(pack_obj, root, out_path)
         plan.phase_times["render"] = time.perf_counter() - t0
 
         save_snapshot(plan.current_snap, root)
@@ -312,6 +352,9 @@ class PackService:
             mode=request.mode,
             budget=plan.budget,
             token_estimate=packed_tokens,
+            freshness=freshness,
+            freshness_warnings=freshness_warnings,
+            selected_files=_selected_file_metadata(plan.selected),
         )
         excluded_receipts = [r for r in plan.receipts if r.action == "excluded"]
         # Budget-cut: files that scored OK but didn't fit — more useful signal than "score too low"
@@ -347,6 +390,33 @@ class PackService:
         )
 
 
+def _write_canonical_context(pack: ContextPack, root: Path, out_path: Path) -> None:
+    """Keep .agentpack/context.md fresh even when the target agent writes elsewhere."""
+    canonical_path = root / ".agentpack" / "context.md"
+    try:
+        if out_path.resolve() == canonical_path.resolve():
+            return
+    except OSError:
+        if out_path == canonical_path:
+            return
+    canonical_path.parent.mkdir(parents=True, exist_ok=True)
+    canonical_path.write_text(render_generic(pack), encoding="utf-8")
+
+
+def _selected_file_metadata(selected: list[SelectedFile]) -> list[dict[str, Any]]:
+    return [
+        {
+            "path": sf.path,
+            "mode": sf.include_mode,
+            "score": round(sf.score, 1),
+            "why": sf.reasons[0] if sf.reasons else "",
+            "reasons": sf.reasons,
+            "tokens": _sf_tokens(sf),
+        }
+        for sf in selected
+    ]
+
+
 def _sf_tokens(sf: SelectedFile) -> int:
     if sf.content:
         return estimate_tokens(sf.content)
@@ -359,14 +429,104 @@ def _sf_tokens(sf: SelectedFile) -> int:
     return estimate_tokens("\n".join(parts)) if parts else 50
 
 
-def _summary_cap_for_mode(cfg: Any, mode: str) -> int:
+def _summary_score_floor(cfg: Any, generic_ratio: float) -> float:
+    floor = cfg.context.min_summary_score
+    if generic_ratio >= 0.5:
+        return floor + 15
+    if generic_ratio >= 0.35:
+        return floor + 8
+    return floor
+
+
+def _summary_cap_for_mode(cfg: Any, mode: str, generic_ratio: float = 0.0) -> int:
     if mode == "minimal":
-        return cfg.context.max_summary_files_minimal
-    if mode == "balanced":
-        return cfg.context.max_summary_files_balanced
-    if mode == "deep":
-        return cfg.context.max_summary_files_deep
-    return 0
+        cap = cfg.context.max_summary_files_minimal
+    elif mode == "balanced":
+        cap = cfg.context.max_summary_files_balanced
+    elif mode == "deep":
+        cap = cfg.context.max_summary_files_deep
+    else:
+        cap = 0
+    if cap > 0 and generic_ratio >= 0.5:
+        return max(8, cap // 2)
+    if cap > 0 and generic_ratio >= 0.35:
+        return max(12, int(cap * 0.75))
+    return cap
+
+
+def _change_source(root: Path, since: str | None, snapshot_changed: set[str], git_changed: set[str]) -> str:
+    if not git.is_git_repo(root):
+        return "snapshot diff"
+    if since:
+        return f"git diff since {since} + snapshot diff"
+    if git_changed and snapshot_changed:
+        return "git working tree + snapshot diff"
+    if git_changed:
+        return "git working tree"
+    if snapshot_changed:
+        return "snapshot diff"
+    return "no live changes; ranking used task keywords and history"
+
+
+def _task_md_body(root: Path) -> str | None:
+    task_md_path = root / ".agentpack" / "task.md"
+    if not task_md_path.exists():
+        return None
+    try:
+        content = task_md_path.read_text(encoding="utf-8").strip()
+    except OSError:
+        return None
+    lines = [ln for ln in content.splitlines() if ln.strip() and not ln.startswith("#")]
+    body = lines[0].strip() if lines else ""
+    placeholder = "Write or update the current coding task here."
+    if body and placeholder not in body:
+        return body
+    return None
+
+
+def _build_freshness_metadata(
+    root: Path,
+    *,
+    request: PackRequest,
+    plan: PackPlan,
+    snapshot_root_hash: str,
+) -> dict[str, Any]:
+    dirty = git.dirty_files(root) if git.is_git_repo(root) else set()
+    metadata: dict[str, Any] = {
+        "generated_at": datetime.now(timezone.utc).isoformat(),
+        "task_source": request.task_source,
+        "changed_files_source": plan.changed_files_source,
+        "snapshot_root_hash": snapshot_root_hash,
+        "generic_task_ratio": round(plan.generic_task_ratio, 3),
+        "dirty_files_count": len(dirty),
+    }
+    if git.is_git_repo(root):
+        metadata["git_sha"] = git.current_sha(root)
+        metadata["git_branch"] = git.current_branch(root)
+    if dirty:
+        metadata["dirty_files_sample"] = sorted(dirty)[:8]
+    task_md = _task_md_body(root)
+    if task_md:
+        metadata["task_md"] = task_md
+    return metadata
+
+
+def _freshness_warnings(root: Path, request: PackRequest, freshness: dict[str, Any]) -> list[str]:
+    warnings: list[str] = []
+    task_md = freshness.get("task_md")
+    if task_md and task_md != request.task:
+        warnings.append(
+            ".agentpack/task.md differs from the packed task; rerun with --task auto if task.md should win."
+        )
+    if freshness.get("changed_files_source") == "no live changes; ranking used task keywords and history":
+        warnings.append("No live changed files were detected; treat selected files as keyword-based hints.")
+    if freshness.get("generic_task_ratio", 0) >= 0.5:
+        warnings.append("Task terms are broad/generic; pack tightened weak-summary selection.")
+    saved_sha = freshness.get("git_sha")
+    current_sha = git.current_sha(root) if git.is_git_repo(root) else None
+    if saved_sha and current_sha and saved_sha != current_sha:
+        warnings.append("Git HEAD changed since this pack was generated.")
+    return warnings
 
 
 def _load_last_record(metrics_path: Path) -> dict[str, Any] | None: