claude-dev-env 2.12.0 → 2.13.0

package/scripts/test_invoke_code_review_cli.py

@@ -1,4 +1,4 @@
-"""CLI JSON output for in-session, error, effort, and record-stamp paths."""
+"""CLI JSON output for in-session, error, and effort paths."""
 
 from __future__ import annotations
 
@@ -9,8 +9,6 @@ import pytest
 
 import invoke_code_review as invoker
 from _code_review_test_support import (
-    DriftingReview,
-    EFFORT_LOW,
     FIXTURE_CHAIN_CONFIG_ERROR_MESSAGE,
     FIXTURE_HOST_PROFILE_ERROR_MESSAGE,
     FIXTURE_SESSION_OPUS,
@@ -19,8 +17,6 @@ from _code_review_test_support import (
     REJECTED_ULTRA_EFFORT,
     init_git_repository,
     install_seams,
-    prepared_surface_repo,
-    run_record_stamp_cli,
     run_review_cli,
 )
 from claude_chain_runner import ChainConfigurationError
@@ -32,17 +28,12 @@ from dev_env_scripts_constants.code_review_constants import (
     HOST_PROFILE_ERROR_RETURNCODE,
     IN_SESSION_RETURNCODE,
     INVALID_EFFORT_RETURNCODE,
-    MAXIMUM_STAMP_MINT_PASSES,
     MODE_CHAIN,
     MODE_IN_SESSION,
-    RESULT_KEY_BOUND_HASH,
     RESULT_KEY_DIRTY_TREE,
     RESULT_KEY_MODE,
-    RESULT_KEY_PASS_COUNT,
     RESULT_KEY_RETURNCODE,
     RESULT_KEY_SERVED_COMMAND,
-    RESULT_KEY_STAMP_MINTED,
-    STAMP_DID_NOT_CONVERGE_RETURNCODE,
 )
 from dev_env_scripts_constants.grok_worker_constants import CWD_FLAG
 
@@ -103,7 +94,6 @@ def test_cli_emits_json_on_chain_configuration_error(
         returncode=CHAIN_CONFIG_ERROR_EXIT_CODE,
         is_dirty_tree=False,
     )
-    assert invoker.is_code_review_clean_stamp_allowed(config_error_outcome) is False
 
 
 def test_cli_emits_json_on_host_profile_value_error(
@@ -156,37 +146,3 @@ def test_cli_rejects_ultra_effort_with_nonzero_exit(
     )
     assert exit_code == INVALID_EFFORT_RETURNCODE
     assert REJECTED_ULTRA_EFFORT in capsys.readouterr().err
-
-
-def test_cli_record_stamp_returns_non_convergence_code_on_cap(
-    monkeypatch: pytest.MonkeyPatch,
-    tmp_path: Path,
-    capsys: pytest.CaptureFixture[str],
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "invoke_code_review", DriftingReview())
-    exit_code = run_record_stamp_cli(working_directory, effort=EFFORT_LOW)
-    assert exit_code == STAMP_DID_NOT_CONVERGE_RETURNCODE
-    parsed_payload = json.loads(capsys.readouterr().out)
-    assert parsed_payload[RESULT_KEY_STAMP_MINTED] is False
-    assert parsed_payload[RESULT_KEY_PASS_COUNT] == MAXIMUM_STAMP_MINT_PASSES
-    assert parsed_payload[RESULT_KEY_BOUND_HASH] is None
-
-
-def test_cli_record_stamp_reports_missing_store_dependency(
-    monkeypatch: pytest.MonkeyPatch,
-    tmp_path: Path,
-    capsys: pytest.CaptureFixture[str],
-) -> None:
-    def raise_missing_store(*all_args: object, **all_keywords: object) -> object:
-        del all_args, all_keywords
-        raise ModuleNotFoundError("store missing", name="code_review_stamp_store")
-
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "load_code_review_stamp_store", raise_missing_store)
-    exit_code = run_record_stamp_cli(working_directory, effort=EFFORT_LOW)
-    assert exit_code == INVALID_EFFORT_RETURNCODE
-    captured = capsys.readouterr()
-    assert "stamp store" in captured.err
-    parsed_payload = json.loads(captured.out)
-    assert parsed_payload[RESULT_KEY_STAMP_MINTED] is False

package/scripts/test_invoke_code_review_contract.py

@@ -1,4 +1,4 @@
-"""Argument contract, encoding, clean-stamp rules, effort tokens, and stamps."""
+"""Argument contract, outcome encoding, and effort-token behavior."""
 
 from __future__ import annotations
 
@@ -8,40 +8,30 @@ import pytest
 
 import invoke_code_review as invoker
 from _code_review_test_support import (
-    DriftingReview,
     EFFORT_LOW,
     FIXTURE_CHAIN_RETURNCODE,
     FIXTURE_FAILED_RETURNCODE,
     FIXTURE_SERVED_COMMAND,
     FIXTURE_SESSION_OPUS,
     HOST_PROFILE_THIRD_PARTY,
-    MISSING_STORE_FILE_NAME,
     REJECTED_ULTRA_EFFORT,
-    SINGLE_PASS_CAP,
     claude_failed,
     init_git_repository,
     install_seams,
-    prepared_surface_repo,
     run_review,
-    stable_clean_review,
-    surface_changing_review,
 )
 from dev_env_scripts_constants.code_review_constants import (
     CODE_REVIEW_MODEL_ALIAS,
     DEFAULT_CODE_REVIEW_EFFORT,
     IN_SESSION_RETURNCODE,
-    MAXIMUM_STAMP_MINT_PASSES,
     MODE_CHAIN,
     MODE_IN_SESSION,
     REVIEW_PERMISSION_MODE as PERMISSION_MODE_BYPASS,
     PERMISSION_MODE_FLAG,
-    RESULT_KEY_BOUND_HASH,
     RESULT_KEY_DIRTY_TREE,
     RESULT_KEY_MODE,
-    RESULT_KEY_PASS_COUNT,
     RESULT_KEY_RETURNCODE,
     RESULT_KEY_SERVED_COMMAND,
-    RESULT_KEY_STAMP_MINTED,
 )
 from dev_env_scripts_constants.grok_worker_constants import (
     MODEL_FLAG,
@@ -109,16 +99,6 @@ def test_chain_failure_preserves_returncode(
     assert review_outcome.returncode == FIXTURE_FAILED_RETURNCODE
     assert review_outcome.is_dirty_tree is False
     assert invoker.is_successful_code_review(review_outcome) is False
-    assert invoker.is_code_review_clean_stamp_allowed(review_outcome) is False
-
-
-def test_clean_stamp_allowed_only_on_successful_clean_serve() -> None:
-    assert invoker.is_code_review_clean_stamp_allowed(CLEAN_SUCCESS_OUTCOME) is True
-    assert invoker.is_code_review_clean_stamp_allowed(DIRTY_SUCCESS_OUTCOME) is False
-    assert invoker.is_code_review_clean_stamp_allowed(FAILED_SERVE_OUTCOME) is False
-    assert invoker.is_code_review_clean_stamp_allowed(IN_SESSION_READY_OUTCOME) is True
-    assert invoker.is_successful_code_review(FAILED_SERVE_OUTCOME) is False
-    assert invoker.is_successful_code_review(CLEAN_SUCCESS_OUTCOME) is True
 
 
 def test_encode_code_review_outcome_shape() -> None:
@@ -157,100 +137,3 @@ def test_validate_effort_token_rejects_unknown_token() -> None:
 def test_build_code_review_prompt_reads_as_slash_command() -> None:
     assert invoker.build_code_review_prompt(EFFORT_LOW) == "/code-review low --fix"
     assert invoker.build_code_review_prompt("xhigh") == "/code-review xhigh --fix"
-
-
-def test_encode_stamp_mint_outcome_includes_mint_metadata() -> None:
-    review_outcome = invoker.CodeReviewOutcome(
-        mode=MODE_CHAIN,
-        served_command=FIXTURE_SERVED_COMMAND,
-        returncode=FIXTURE_CHAIN_RETURNCODE,
-        is_dirty_tree=False,
-    )
-    mint_outcome = invoker.StampMintOutcome(
-        review_outcome=review_outcome,
-        is_stamp_minted=True,
-        pass_count=SINGLE_PASS_CAP,
-        bound_hash="abc123",
-    )
-    encoded_payload = invoker.encode_stamp_mint_outcome(mint_outcome)
-    assert encoded_payload[RESULT_KEY_STAMP_MINTED] is True
-    assert encoded_payload[RESULT_KEY_PASS_COUNT] == SINGLE_PASS_CAP
-    assert encoded_payload[RESULT_KEY_BOUND_HASH] == "abc123"
-
-
-def test_record_stamp_mints_on_surface_stable_clean_pass(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "invoke_code_review", stable_clean_review)
-    mint_outcome = invoker.invoke_code_review_and_record_stamp(
-        working_directory=working_directory,
-        session_model=CODE_REVIEW_MODEL_ALIAS,
-        timeout_seconds=DEFAULT_CODE_REVIEW_TIMEOUT_SECONDS,
-        effort=EFFORT_LOW,
-    )
-    assert mint_outcome.is_stamp_minted is True
-    assert mint_outcome.bound_hash is not None
-    store_module = invoker.load_code_review_stamp_store()
-    assert store_module.stamp_covers_surface(
-        str(working_directory), mint_outcome.bound_hash, EFFORT_LOW
-    )
-
-
-def test_record_stamp_does_not_mint_when_review_changes_surface(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "invoke_code_review", surface_changing_review)
-    mint_outcome = invoker.invoke_code_review_and_record_stamp(
-        working_directory=working_directory,
-        session_model=CODE_REVIEW_MODEL_ALIAS,
-        timeout_seconds=DEFAULT_CODE_REVIEW_TIMEOUT_SECONDS,
-        effort=EFFORT_LOW,
-        maximum_passes=SINGLE_PASS_CAP,
-    )
-    assert mint_outcome.is_stamp_minted is False
-    assert mint_outcome.pass_count == SINGLE_PASS_CAP
-    assert mint_outcome.bound_hash is None
-
-
-def test_record_stamp_hits_cap_without_minting(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    monkeypatch.setattr(invoker, "invoke_code_review", DriftingReview())
-    mint_outcome = invoker.invoke_code_review_and_record_stamp(
-        working_directory=working_directory,
-        session_model=CODE_REVIEW_MODEL_ALIAS,
-        timeout_seconds=DEFAULT_CODE_REVIEW_TIMEOUT_SECONDS,
-        effort=EFFORT_LOW,
-        maximum_passes=MAXIMUM_STAMP_MINT_PASSES,
-    )
-    assert mint_outcome.is_stamp_minted is False
-    assert mint_outcome.pass_count == MAXIMUM_STAMP_MINT_PASSES
-
-
-def test_load_code_review_stamp_store_records_and_covers_surface(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
-) -> None:
-    working_directory = prepared_surface_repo(monkeypatch, tmp_path)
-    store_module = invoker.load_code_review_stamp_store()
-    surface_hash = store_module.live_surface_hash(str(working_directory))
-    assert surface_hash is not None
-    stamp_path = store_module.record_clean_stamp(
-        str(working_directory), surface_hash, EFFORT_LOW
-    )
-    assert stamp_path.exists()
-    assert store_module.stamp_covers_surface(
-        str(working_directory), surface_hash, EFFORT_LOW
-    )
-
-
-def test_load_code_review_stamp_store_raises_when_file_absent(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    monkeypatch.setattr(
-        invoker, "STAMP_STORE_MODULE_FILE_NAME", MISSING_STORE_FILE_NAME
-    )
-    with pytest.raises(ModuleNotFoundError):
-        invoker.load_code_review_stamp_store()

package/settings.json

@@ -1,10 +1 @@
-{
-  "permissions": {
-    "deny": [
-      "Edit($HOME/.claude/verification/**)",
-      "Write($HOME/.claude/code-review-stamps/**)",
-      "Edit($HOME/.claude/code-review-stamps/**)",
-      "MultiEdit($HOME/.claude/code-review-stamps/**)"
-    ]
-  }
-}
+{}

package/skills/CLAUDE.md

@@ -42,6 +42,14 @@ contracts, runtime scripts). Map: `skills/_shared/CLAUDE.md`. End-of-run gotchas
 - `pr-loop-lifecycle` — opens and closes a PR-loop run (grant, teardown, PR description, revoke, report)
 - `pr-loop-cloud-transport` — six-step transport workflow that lets any PR-loop skill run in a session whose `gh` CLI is absent or cannot act on the PR (MCP schema load, origin/HEAD fix, identity rules, the gh-to-MCP substitution matrix, the Copilot status rule, and the post self-check)
 
+**Code review guides (Google eng-practices, adapted for an AI reviewer)**
+- `small-cl` — the Small CLs guide; refs: handling reviewer comments
+- `comments` — writing review comments and handling reviewer comments; refs: the review standard, pushback, respectful code reviews
+- `reviews` — the reviewer guide: standard, what to look for, navigating a CL, speed, pushback; refs: CL descriptions, review comments, emergencies, style guides, the two guide indexes
+- `descriptions` — writing good CL descriptions
+- `emergencies` — what counts as an emergency change; refs: what to look for, speed
+- Focused pull request guidance: [`small-cl/SKILL.md`](small-cl/SKILL.md)
+
 **Research and discovery**
 - `recall` — retrieves facts from memory files
 - `remember` — saves a decision, gotcha, or architectural choice to the Obsidian vault

package/skills/autoconverge/reference/CLAUDE.md

@@ -9,7 +9,7 @@ Reference documentation for the `autoconverge` skill. The `converge.mjs` workflo
 | `convergence.md` | Round shape: the static sweep, the three parallel internal lenses (code-review, bug-audit, self-review), deduplication, the fix commit step, the terminal Bugbot, Copilot, and Codex gates, and the definition of a clean convergence. |
 | `copilot-findings.md` | The Copilot gate tiering, per-finding verification, and the `userReview` return contract. |
 | `stop-conditions.md` | Every condition that ends the run short of ready: budget cap, iteration cap, blocker exit, static-sweep stall, Bugbot, Copilot, and Codex bypass. |
-| `gotchas.md` | Hard-won lessons from failed runs: PR title validation, conflicting PRs, worktree branch lock, resumed sessions rerooting, and minter issues. |
+| `gotchas.md` | Current operating guidance for PR title validation, conflicting PRs, worktree branch lock, resumed sessions, and commit or push failures. |
 | `closing-report.md` | The closing HTML convergence report the teardown step builds and publishes: data source, build steps, publishing. |
 | `multi-pr.md` | The several-PRs path: per-PR worktrees, the `converge_multi.mjs` launch, per-PR teardown. |
 | `self-closing-loop.md` | The deferred-PR generations the orchestrator converges after teardown, and the Conventional-Commit title rule on hardening PRs. |

package/skills/autoconverge/reference/convergence.md

@@ -5,9 +5,9 @@
 Before the first round, the workflow checks once whether the PR branch conflicts
 with `origin/main`. When GitHub reports a conflict (`mergeable` false or
 `mergeable_state` dirty), one `clean-coder` rebases the branch onto `origin/main`
-and resolves every conflict — gated the same way as every other code change: the
-edit leaves the rebase in the working tree, a `code-verifier` binds a verdict to
-it, and the commit step force-pushes with lease. The bug checks then run on a
+and resolves every conflict — the edit remains in the working tree, review and
+verification follow the [review guide](../../reviews/SKILL.md#review-workflow),
+and the commit step force-pushes with lease. The bug checks then run on a
 conflict-free diff.
 
 A PR that merges cleanly skips the rebase. A conflict that surfaces mid-run, when
@@ -61,8 +61,8 @@ confirmation gates that are expected to return zero.
    the round re-runs, so the reading lenses only ever review sweep-clean code.
 3. Run three reading lenses in parallel on that HEAD, each over the full
    `origin/main...HEAD` diff. Each lens receives the preflight's changed-file
-   list and diffstat and reads only the files it needs from that list rather than
-   re-deriving the diff; each lens forms its own review judgment.
+list and diffstat and reads only the files it needs from that list rather than
+re-deriving the diff; each lens applies the [review guide](../../reviews/SKILL.md#review-judgment).
    - **Code-review lens** — a correctness-focused review pass (`code-quality-agent`),
      report-only workflow agent — see runCodeReviewLens in workflow/converge.mjs for its configuration.
      The built-in `/code-review` command is a separate surface outside this
@@ -113,8 +113,8 @@ When the already-deduped findings for a phase are all severity P2 (and not
 standards-only), the phase still applies the fixes once. If the fix does **not**
 move HEAD (for example `resolvedWithoutCommit`), the phase treats that HEAD as
 clean and advances forward. If the fix **does** move HEAD, the run re-enters
-CONVERGE on the fixed SHA so HEAD-bound CLEAN/review stamps rebuild before
-FINALIZE — those stamps are SHA-specific. The three CONVERGE reading lenses stay
+CONVERGE on the fixed SHA so the current review state rebuilds before
+FINALIZE. The three CONVERGE reading lenses stay
 parallel; the P2-only decision is a routing branch on the deduped set after
 `resolveRoundOutcome` / gate classification. Mixed P0/P1 findings keep the
 existing fix + re-converge path.

package/skills/autoconverge/reference/gotchas.md

@@ -50,16 +50,9 @@ fails in a new way.
   account, pin the token with `--user <login>`; `gh auth token` alone can return
   another account's token after a switch.
 
-- **The verified-commit gate can block the fix from landing.** The fix lens
-  commits and pushes through the `verified_commit_gate` hook, which denies a
-  `git commit`/`git push` until a `code-verifier` verdict covers the branch
-  surface. A run can reach a clean fix yet fail to land it — the push stays
-  blocked when no verdict is minted for that surface. A manual override exists:
-  a trailing `# verify-skip` comment on the commit or push command skips the
-  gate for that one command. Autoconverge must never apply that override on its
-  own. When landing a fix needs it, stop and tell the user the verified-commit
-  gate is blocking the push and that going forward needs either a `# verify-skip`
-  bypass or a switch to `/pr-converge`, then let the user decide.
+- **Commit or push fails after a repair.** Read the hook or command output,
+  repair the named issue, and record the rerun. Apply the
+  [review guide](../../reviews/SKILL.md#review-workflow) before retrying.
 
 - **A Copilot "down" verdict is valid only after the full poll budget.** A
   successful review request means the review is in flight — Copilot typically