claude-dev-env 1.35.0 → 1.36.1

package/skills/bugteam/test_team_lifecycle.py

@@ -0,0 +1,103 @@
+"""Markdown assertion tests for bugteam team-lifecycle decoupling.
+
+Locks in the contract that the bugteam skill must:
+  - support three team lifecycle modes (`owned`, `attach`, `auto`)
+  - default to `auto` (back-compat for solo invocations, safe for nested ones)
+  - skip `TeamDelete` when the invocation did not create the team
+  - parse the runtime's `Already leading team "<name>"` error and attach
+"""
+
+from __future__ import annotations
+
+import pathlib
+
+
+def _read(relative_path: str) -> str:
+    here = pathlib.Path(__file__).parent
+    return (here / relative_path).read_text(encoding="utf-8")
+
+
+def _skill_text() -> str:
+    return _read("SKILL.md")
+
+
+def _path_a_text() -> str:
+    return _read("reference/workflow-path-a-orchestrated-teams.md")
+
+
+def _constraints_text() -> str:
+    return _read("CONSTRAINTS.md")
+
+
+def test_skill_documents_three_team_lifecycle_modes():
+    skill_text = _skill_text()
+    assert "BUGTEAM_TEAM_LIFECYCLE" in skill_text
+    assert "owned" in skill_text
+    assert "attach" in skill_text
+    assert "auto" in skill_text
+
+
+def test_skill_documents_auto_as_default_lifecycle():
+    skill_text = _skill_text()
+    assert "default" in skill_text.lower()
+    assert "BUGTEAM_TEAM_LIFECYCLE" in skill_text
+    auto_default_phrases = [
+        "default: `auto`",
+        "default `auto`",
+        "defaults to `auto`",
+        "defaults to auto",
+        "default to `auto`",
+    ]
+    assert any(phrase in skill_text for phrase in auto_default_phrases)
+
+
+def test_skill_documents_BUGTEAM_TEAM_NAME_env_for_attach_mode():
+    skill_text = _skill_text()
+    assert "BUGTEAM_TEAM_NAME" in skill_text
+
+
+def test_path_a_workflow_handles_already_leading_team_error():
+    workflow_text = _path_a_text()
+    assert 'Already leading team "' in workflow_text
+    assert "team_owned" in workflow_text
+
+
+def test_path_a_workflow_step_4_skips_team_delete_when_not_owned():
+    workflow_text = _path_a_text()
+    assert "TeamDelete" in workflow_text
+    assert "team_owned" in workflow_text
+    skip_phrases = [
+        "skip `TeamDelete`",
+        "skip TeamDelete",
+        "omit `TeamDelete`",
+        "omit TeamDelete",
+        "do not call `TeamDelete`",
+        "do not call TeamDelete",
+    ]
+    assert any(phrase in workflow_text for phrase in skip_phrases)
+
+
+def test_path_a_workflow_documents_attach_mode_reuses_team_name():
+    workflow_text = _path_a_text()
+    assert "BUGTEAM_TEAM_NAME" in workflow_text
+    assert "attach" in workflow_text
+
+
+def test_constraints_lead_only_cleanup_includes_team_owned():
+    constraints_text = _constraints_text()
+    assert "team_owned" in constraints_text
+
+
+def test_constraints_warn_against_owned_mode_inside_orchestrator():
+    constraints_text = _constraints_text()
+    assert "orchestrator" in constraints_text.lower()
+    assert "attach" in constraints_text
+
+
+def test_skill_md_physical_lines_fit_eighty_column_limit():
+    skill_text = _skill_text()
+    for each_line_number, each_physical_line in enumerate(skill_text.splitlines(), 1):
+        assert len(each_physical_line) <= 80, (
+            "SKILL.md line %s exceeds 80 columns (%s chars)"
+            % (each_line_number, len(each_physical_line))
+        )

package/skills/findbugs/SKILL.md

@@ -121,7 +121,7 @@ When the agent returns, report concisely:
 - The cleared categories so the user can see coverage breadth
 - Any open questions the agent could not resolve from the diff alone
 
-Offer the next step without auto-executing it: `Want me to spawn clean-coder to fix the P0/P1 findings?`
+Offer the next step without auto-executing it: `Want me to run /fixbugs for the P0/P1 findings?`
 
 Delete the scoped temp diff at `<diff_temp_path>` after the audit completes (or moves to a fix flow). Temporary diff files do not belong in the working tree.
 
@@ -143,7 +143,7 @@ Verified clean: <category>, <category>, <category>
 Open questions:
   <if any>
 
-Want me to spawn clean-coder to fix the P0/P1 findings?
+Want me to run /fixbugs for the P0/P1 findings?
 ```
 
 ## Constraints
@@ -177,7 +177,7 @@ Claude: [resolves PR #42 from current branch, fetches full diff, spawns code-qua
 
 `Open questions: none`
 
-`Want me to spawn clean-coder to fix the P0 + P1s?`
+`Want me to run /fixbugs for the P0 + P1s?`
 </example>
 
 <example>

package/skills/fixbugs/SKILL.md

@@ -3,7 +3,7 @@ name: fixbugs
 description: >-
   Fixes the bugs surfaced by the most recent /findbugs invocation by handing
   the findings to /agent-prompt, which authors a structured XML prompt and
-  spawns a background sonnet clean-coder agent to implement every fix in one
+  spawns a background sonnet implementer (via /agent-prompt) to apply every fix in one
   commit on the existing branch. Default scope: all severities. Optional
   argument filters by severity (e.g. /fixbugs P0, /fixbugs P0+P1).
   Triggers: '/fixbugs', 'fix all the bugs', 'apply the audit fixes',
@@ -66,8 +66,8 @@ Fix the following bugs surfaced by /findbugs on
 [for each filtered finding, one bullet:]
 - [<severity>] <file:line> (<category>): <description>
 
-Deploy a clean-coder background agent (model: sonnet) to implement all fixes
-in one commit on the existing branch and push. Constraints:
+Deploy a background implementer (model: sonnet) to implement all fixes
+in one commit on the existing branch and push. The implementer must **Read** the clean-coder agent file first (`~/.claude/agents/clean-coder.md`; Windows `%USERPROFILE%\.claude\agents\clean-coder.md`) and treat it as binding; on Cursor use `Task` + `generalPurpose` with that Read in the prompt when `clean-coder` is not a valid `Task` subtype. Constraints:
 - Modify only the files referenced in the bug list above.
 - Do NOT change the PR base, do NOT rebase, do NOT amend, do NOT --force.
 - Do NOT skip git hooks (no --no-verify, no --no-gpg-sign).
@@ -106,7 +106,7 @@ When `/fixbugs` short-circuits (no findings, no PR, empty filter, zero bugs), th
 <example>
 User: `/findbugs` → returns `1 P0 / 2 P1 / 0 P2`
 User: `/fixbugs`
-Claude: [recovers all 3 findings, resolves PR scope, invokes /agent-prompt with a goal targeting all 3 bugs; /agent-prompt presents the XML + Outcome digest + AskUserQuestion; on Launch it, the background sonnet clean-coder spawns]
+Claude: [recovers all 3 findings, resolves PR scope, invokes /agent-prompt with a goal targeting all 3 bugs; /agent-prompt presents the XML + Outcome digest + AskUserQuestion; on Launch it, the background sonnet implementer spawns]
 </example>
 
 <example>

package/skills/monitor-open-prs/SKILL.md

@@ -19,6 +19,7 @@ description: >-
 
 - When this skill applies — refusal cases and trigger conditions
 - Discovery — live `gh search prs` across both owner scopes
+- Team lifecycle — single long-lived team for the whole sweep
 - Wrapping — `bws run` for GROQ_API_KEY injection
 - Dispatch — `/bugteam <numbers...>` with groq-coder + retrigger
 - Post-convergence polling — bugbot replies and re-invocation
@@ -40,6 +41,35 @@ Refusals — first match wins; respond with the quoted line exactly and stop:
 
 Call `scripts/discover_open_prs.discover_open_prs(all_owners=["jl-cmd", "JonEcho"])` to merge the live open-PR list across both scopes. The helper runs `gh search prs --owner <owner> --state open --json number,repository,url,headRefName,baseRefName` once per owner and flattens the result to a uniform dict shape with keys `number`, `owner`, `repo`, `head_ref`, `base_ref`, `url`. Empty scopes contribute empty lists; an entirely empty sweep returns `[]` and exits cleanly.
 
+## Team Lifecycle
+
+`/monitor-open-prs` dispatches one `/bugteam` per discovered PR — often more than ten in a sweep. Per-invocation `TeamCreate` / `TeamDelete` from each `/bugteam` would either collide on the runtime's `Already leading team` rule or tear down the wrong team mid-sweep, depending on dispatch order. The sweep instead owns a **single long-lived team for the whole sweep** and passes that team to every `/bugteam` invocation in attach mode. See [bugteam Team lifecycle](../bugteam/SKILL.md#team-lifecycle-path-a-only).
+
+**Before the first dispatch:**
+
+1. Capture `sweep_id = <YYYYMMDDHHMMSS>` once at sweep start. This is the same convention as bugteam's team-name timestamp.
+2. Compute `team_name = "bugteam-monitor-<sweep_id>"`.
+3. `TeamCreate(team_name=<team_name>, description="monitor-open-prs sweep <sweep_id>", agent_type="team-lead")`. The orchestrator (this session) becomes the lead.
+
+**For every `/bugteam` dispatch** (parallel fan-out or serial), prepend the two attach-mode env vars to the wrapped command so bugteam reuses the orchestrator's team and skips its own `TeamCreate` / `TeamDelete`:
+
+```bash
+bws run \
+  --project-id c69cedc5-aea1-4aa8-b350-b4300145d978 \
+  -- \
+  env BUGTEAM_TEAM_LIFECYCLE=attach \
+      BUGTEAM_TEAM_NAME=<team_name> \
+      BUGTEAM_FIX_IMPLEMENTER=groq-coder \
+  /bugteam --bugbot-retrigger <pr_numbers...>
+```
+
+**Teardown — only after every PR has exited polling** (see §Post-Convergence Polling): the sweep is done; no further `/bugteam` invocation will run. At that point, and only at that point:
+
+1. `TeamDelete()` (orchestrator is the lead; no arguments).
+2. Print one cleanup line into the §Final Report: `team teardown: TeamDelete <team_name>` (success) or the error message on failure.
+
+If a hard blocker or user stop ends the sweep early, the orchestrator is shutting down: still call `TeamDelete()` once after polling stops for the in-flight PRs.
+
 ## Secret Wrapping
 
 Every `/bugteam` dispatch runs inside `bws run` so `GROQ_API_KEY` is injected from Bitwarden Secrets Manager without touching the filesystem. The project and secret UUIDs are fixed for this skill:
@@ -59,9 +89,9 @@ The `bws run` subshell resolves the project's secrets and exports them for the w
 For each discovered PR:
 
 1. Resolve the PR's repo checkout (existing worktree or fresh `git clone`).
-2. From that checkout, invoke `/bugteam <pr_number>` under the `bws run` wrapper above.
+2. From that checkout, invoke `/bugteam <pr_number>` under the `bws run` wrapper from §Team Lifecycle (the wrapper already carries `BUGTEAM_TEAM_LIFECYCLE=attach` and `BUGTEAM_TEAM_NAME=<team_name>` so bugteam reuses the sweep-owned team).
 3. The `BUGTEAM_FIX_IMPLEMENTER=groq-coder` env var routes the FIX role to the `groq-coder` subagent. The `--bugbot-retrigger` flag tells bugteam to post `bugbot run` as an issue comment after every successful FIX push so Cursor's bugbot re-evaluates the new commit.
-4. Bugteam runs its own 10-loop audit/fix cycle per PR; this skill waits for each bugteam invocation to return before dispatching the next (or fanning out — see below).
+4. Bugteam runs its own 10-loop audit/fix cycle per PR; this skill waits for each bugteam invocation to return before dispatching the next (or fanning out — see below). Each invocation skips its own `TeamCreate` / `TeamDelete` because of attach mode — only the sweep owns team teardown (§Team Lifecycle).
 
 **Fan-out (optional):** when the discovered list has more than one PR, the skill may spawn `/bugteam` dispatches in parallel by issuing multiple `Agent` calls in a single assistant message. Each dispatch operates in its own per-PR worktree (bugteam Step 1.1). Serialize when the caller sets an explicit `--serial` flag.
 

package/skills/monitor-open-prs/test_team_lifecycle.py

@@ -0,0 +1,46 @@
+"""Markdown assertion tests for monitor-open-prs team lifecycle.
+
+Locks in the contract that the sweep must:
+  - own a single long-lived team for every dispatched /bugteam
+  - pass attach mode + the team name into each per-PR /bugteam dispatch
+  - tear down only after all PR polling completes
+"""
+
+from __future__ import annotations
+
+import pathlib
+
+
+def _skill_text() -> str:
+    here = pathlib.Path(__file__).parent
+    return (here / "SKILL.md").read_text(encoding="utf-8")
+
+
+def test_skill_creates_one_team_for_the_whole_sweep():
+    skill_text = _skill_text()
+    assert "TeamCreate" in skill_text
+    sweep_phrases = [
+        "one team for the whole sweep",
+        "single team for the sweep",
+        "single long-lived team",
+    ]
+    assert any(phrase in skill_text for phrase in sweep_phrases)
+
+
+def test_skill_passes_attach_lifecycle_to_each_bugteam_dispatch():
+    skill_text = _skill_text()
+    assert "BUGTEAM_TEAM_LIFECYCLE" in skill_text
+    assert "attach" in skill_text
+    assert "BUGTEAM_TEAM_NAME" in skill_text
+
+
+def test_skill_tears_down_team_after_polling_completes():
+    skill_text = _skill_text()
+    assert "TeamDelete" in skill_text
+    teardown_phrases = [
+        "after every PR has exited polling",
+        "after polling completes",
+        "after the sweep",
+        "after all polling",
+    ]
+    assert any(phrase in skill_text for phrase in teardown_phrases)