prizmkit 1.1.102 → 1.1.105

package/bundled/dev-pipeline/templates/bootstrap-tier3.md

@@ -1,4 +1,4 @@
-# Dev-Pipeline Session Bootstrap — Tier 3 (Full Team)
+# Dev-Pipeline Session Bootstrap — Tier 3 (Orchestrator + Critic/Reviewer)
 
 ## Session Context
 
@@ -10,14 +10,14 @@
 
 You are the **session orchestrator**. Implement Feature {{FEATURE_ID}}: "{{FEATURE_TITLE}}".
 
-**CRITICAL**: You MUST NOT exit until ALL work is complete and committed. When you spawn normal work subagents, wait for each to finish (run_in_background=false). Do NOT spawn work agents in background and exit — that kills the session.
+**CRITICAL**: You MUST NOT exit until ALL work is complete and committed. When you spawn Critic or Reviewer agents, wait for each to finish (run_in_background=false). Do NOT spawn agents in background and exit — that kills the session.
 
-**Tier 3 — Full Team**: For complex features, use the full pipeline (Phase 0–6) with Dev + Reviewer agents spawned via the Agent tool.
+**Tier 3 — Orchestrator + Critic/Reviewer**: For complex features, the main orchestrator handles context, planning, and implementation directly. Critic challenges the plan and Reviewer reviews. Do not spawn a top-level Dev implementation agent.
 
 **Agent spawn failure policy (all Agent tool calls)**:
-- If spawning Dev, Reviewer, or Critic fails with team/config/lock errors, retry at most once.
+- If spawning Reviewer or Critic fails with team/config/lock errors, retry at most once.
 - If the second attempt fails, do not keep spawning variants and do not enter artifact polling for Implementation Log, challenge report, or review report markers.
-- Use the documented inline/recovery fallback for that phase: write the required report yourself where possible, complete remaining Dev work directly in the orchestrator when safe, or write `failure-log.md` with the spawn error and last observable state before stopping for recovery.
+- Use the documented inline/recovery fallback for that phase: write the required report yourself where possible, complete remaining work directly in the orchestrator when safe, or write `failure-log.md` with the spawn error and last observable state before stopping for recovery.
 - Apply the same cap to any re-spawn for report repair or resume prompts; do not burn multiple minutes on identical team/config/lock failures.
 
 ### Feature Description
@@ -71,12 +71,12 @@ You are running in **headless non-interactive mode** with a FINITE context windo
 ## PrizmKit Directory Convention
 
 ```
-.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md  ← orchestrator writes Sections 1-4; Dev appends Implementation Log; Reviewer appends Review Notes
+.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md  ← orchestrator writes Sections 1-4 + Implementation Log; Reviewer appends Review Notes
 .prizmkit/specs/{{FEATURE_SLUG}}/spec.md
 .prizmkit/specs/{{FEATURE_SLUG}}/plan.md              ← includes Tasks section
 ```
 
-**`context-snapshot.md`** is the shared knowledge base. Orchestrator writes Sections 1-4; Dev appends Implementation Log; Reviewer appends Review Notes. This eliminates redundant I/O across all agents.
+**`context-snapshot.md`** is the shared knowledge base. Orchestrator writes Sections 1-4 and the Implementation Log; Reviewer appends Review Notes. This eliminates redundant I/O across review and orchestration phases.
 
 ---
 
@@ -268,55 +268,64 @@ After all critics return, read all 3 reports:
 **CP-2.5**: Plan challenges reviewed and resolved.
 {{END_IF_CRITIC_ENABLED}}
 
-### Phase 4: Implement — Dev Agent
+### Implement — Orchestrator Direct (no Dev subagent)
 
-**Build artifacts rule** (passed to Dev): After any build/compile command (`go build`, `npm run build`, `tsc`, etc.), ensure the output binary or build directory is in `.gitignore`. Never commit compiled binaries, build output, or generated artifacts.
+**Rationale**: Development is deterministic plan execution — the orchestrator already built full context in Phase 1-2. Spawning a Dev subagent forces it to rebuild context (re-reading files the orchestrator already read), wastes context, and risks worktree double-edit. The orchestrator implements directly.
 
-Before spawning Dev, check plan.md Tasks section:
+Before starting, check plan.md Tasks:
 ```bash
 grep -c '^\- \[ \]' .prizmkit/specs/{{FEATURE_SLUG}}/plan.md 2>/dev/null || true
 ```
-- If result is `0` (all tasks already `[x]`) → **SKIP Phase 4**, go directly to Phase 5. Do NOT spawn Dev.
-- If result is non-zero → spawn Dev agent below.
+- If result is `0` (all tasks already `[x]`) → **SKIP to Review**.
+- If non-zero → implement directly below.
 
-Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false).
+**Build artifacts rule**: After any build/compile command, ensure output is in `.gitignore`. Never commit binaries/build output.
 
-Spawn failure cap: for team/config/lock errors, retry at most once for this Dev spawn. If the second attempt fails, do not poll for `## Implementation Log`; write `failure-log.md` and either implement remaining tasks directly in the orchestrator or stop for recovery.
-
-Prompt:
-> "Read {{DEV_SUBAGENT_PATH}}. Implement feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}).
-> **IMPORTANT**: Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has Prizm Context (TRAPS/RULES), Section 4 has File Manifest with paths and interfaces.
-> ⚠️ DO NOT re-read source files already listed in Section 4 File Manifest unless you need implementation detail beyond the interface summary.
-> 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` for full context.
-> 2. Run `/prizmkit-implement` to execute the tasks in plan.md. Run tests with: `{{TEST_CMD}}`. Known baseline failures (pre-existing, not your fault): `{{BASELINE_FAILURES}}`.
-> 3. If plan.md has more than 5 tasks: update durable checkpoints/artifacts after every 3 tasks, minimize output, and rely on runner continuation if context overflow occurs. In an interactive Claude Code session operated manually outside the headless pipeline, `/compact` may be used as an optional convenience only.
-> 4. **Verification Gate Self-Check (BLOCKING)**: before returning, write a `### Gate Evidence` section to Implementation Log — one evidence line per gate (test name / file:line / fixture path). Any gate without evidence is BLOCKED, not success.
-> 5. **Layered test strategy**: debug with single-file tests (`npx vitest run <file> -t '<name>'`), only run full suite as gate when single-file is green. Never run full suite while a single-file test is still red.
-> 6. **Anti re-read**: 20-step window (full Read forbidden within 20 tool calls of last read), 3-strike (3 full Reads same file → BLOCKED). Use `grep -n`+`sed -n` for specific lines.
-> 7. **Read offset safety**: if Read returns "shorter than offset"/"empty"/"wasted" — run `wc -l` then `sed -n`, do NOT retry same offset. 2 consecutive → STOP Reading that file.
-> 8. **Hard Round Cap**: after 6 total test-fix rounds, STOP trial-and-error. Write failure-log. Switch to read-once-then-rewrite strategy. Do NOT exceed 7 rounds.
-> 9. After implement completes, verify the '## Implementation Log' section (with Gate Evidence) was written to context-snapshot.md.
-> 10. Do NOT execute any git commands (no git add/commit/reset/push).
-> Do NOT exit until all tasks are [x] and the '## Implementation Log' section (with Gate Evidence) is written in context-snapshot.md."
-
-**Gate Check — Implementation Log**:
-After Dev agent returns, verify the Implementation Log was written:
+**3a.** Detect test commands and record baseline:
 ```bash
-grep -q "## Implementation Log" .prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md && echo "GATE:PASS" || echo "GATE:MISSING"
+($TEST_CMD) 2>&1 | tee /tmp/test-baseline.txt | tail -20
+```
+Save pre-existing failing tests as `BASELINE_FAILURES`.
+
+**3b.** Run `/prizmkit-implement` directly — you (the orchestrator) execute the full cycle:
+- Read plan.md Tasks from `.prizmkit/specs/{{FEATURE_SLUG}}/`
+- Use context-snapshot.md Section 4 File Manifest for targeted reads — do NOT re-read files already summarized there
+- Implements task-by-task, marking each `[x]` immediately
+- Creates/updates L2 `.prizm` docs when creating new modules
+- Defers scoped/full test execution until after the code-review loop completes
+- If plan.md has >5 tasks: update checkpoints after every 3 tasks
+
+**3c. Focused checks only (no test gate here)**:
+- During implementation, do not run mandatory periodic or full-suite tests.
+- If a tiny targeted check is needed to understand a local failure, run only the smallest relevant command and capture output to `/tmp/test-out.txt`.
+- The scoped feature test gate runs after code review; do not declare implementation success based on an early full-suite run.
+
+**3d. Verification Gate Self-Check (BLOCKING — before declaring implement done)**:
+For each Verification Gate from the Task Contract, write one evidence line to Implementation Log:
+```
+### Gate Evidence
+- [x] G1: <gate text> — Evidence: <test name / file:line / fixture path>
+- [ ] G3: <gate text> — BLOCKED: <reason>  ← no evidence = BLOCKED, not success
 ```
-If GATE:MISSING — send message to Dev (re-spawn if needed): "Write the '## Implementation Log' section to context-snapshot.md before I can proceed to review. Include: files changed/created, key decisions, deviations from plan, notable discoveries."
 
-Wait for Dev to return. **If Dev times out before all tasks are `[x]`**:
-1. Check progress: `grep -c '^\- \[ \]' .prizmkit/specs/{{FEATURE_SLUG}}/plan.md`
-2. If any tasks remain: re-spawn Dev with this recovery prompt:
-   > "Read {{DEV_SUBAGENT_PATH}}. You are resuming implementation of feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}).
-   > 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` — Section 4 has File Manifest, 'Implementation Log' (if present) shows what was already done.
-   > 2. Run `git diff HEAD` to see actual code changes already made.
-   > 3. Run `/prizmkit-implement` to complete the remaining `[ ]` tasks. Run tests with: `{{TEST_CMD}}`.
-   > 4. Do NOT execute any git commands."
-3. Max 2 recovery retries. After 2 failures, orchestrator implements remaining tasks directly.
+**3e.** Append `## Implementation Log` (with Gate Evidence) to `context-snapshot.md`:
+- files changed/created
+- key decisions
+- deviations from plan
+- test results
+- Gate Evidence section
+- unresolved blockers
+
+**CP-2**: All tasks `[x]`, Implementation Log written with Gate Evidence, and blocked gates documented in `failure-log.md`. Test execution is deferred until after code review.
+
+**Checkpoint update**:
+```bash
+python3 $PIPELINE_DIR/scripts/update-checkpoint.py \
+  --checkpoint-path .prizmkit/specs/{{FEATURE_SLUG}}/workflow-checkpoint.json \
+  --step prizmkit-implement \
+  --status completed
+```
 
-All tasks `[x]`, tests pass.
 
 ### Scoped Feature Test Gate — PrizmKit Test
 
@@ -618,7 +627,6 @@ Rules for writing completion notes:
 | Feature Artifacts Dir | `.prizmkit/specs/{{FEATURE_SLUG}}/` |
 | Context Snapshot | `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` |
 | Team Config | `{{TEAM_CONFIG_PATH}}` |
-| Dev Agent Def | {{DEV_SUBAGENT_PATH}} |
 | Reviewer Agent Def | {{REVIEWER_SUBAGENT_PATH}} |
 {{IF_CRITIC_ENABLED}}
 | Critic Agent Def | {{CRITIC_SUBAGENT_PATH}} |
@@ -645,10 +653,10 @@ If you encounter an unrecoverable error, context overflow, or are about to exit
 
 ## Reminders
 
-- Tier 3: full team — Dev (implementation) → Reviewer (review) — spawn agents directly via Agent tool
-- context-snapshot.md is append-only: orchestrator writes Sections 1-4, Dev appends Implementation Log, Reviewer appends Review Notes
+- Tier 3: orchestrator implements directly; Critic challenges plan; Reviewer reviews
+- context-snapshot.md is append-only: orchestrator writes Sections 1-4 + Implementation Log, Reviewer appends Review Notes
 - Gate checks enforce Implementation Log and Review Notes are written before proceeding
-- Do NOT use `run_in_background=true` when spawning normal work agents
+- Do NOT use `run_in_background=true` when spawning Critic or Reviewer agents
 - Commit phase must use `/prizmkit-committer`; do NOT replace with manual git commit commands
 - **NEVER delete, modify, or touch any file under `.prizmkit/state/`** — those are pipeline runtime files managed by the runner
 - NEVER run `rm -rf`, `git clean`, or any destructive filesystem operations

package/bundled/dev-pipeline/templates/sections/critical-paths-agent.md

@@ -4,7 +4,6 @@
 |----------|------|
 | Feature Artifacts Dir | `.prizmkit/specs/{{FEATURE_SLUG}}/` |
 | Context Snapshot | `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` |
-| Dev Agent Def | {{DEV_SUBAGENT_PATH}} |
 | Reviewer Agent Def | {{REVIEWER_SUBAGENT_PATH}} |
 | Critic Agent Def (if enabled) | {{CRITIC_SUBAGENT_PATH}} |
 | Project Root | {{PROJECT_ROOT}} |

package/bundled/dev-pipeline/templates/sections/critical-paths-full.md

@@ -5,7 +5,6 @@
 | Feature Artifacts Dir | `.prizmkit/specs/{{FEATURE_SLUG}}/` |
 | Context Snapshot | `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` |
 | Team Config | `{{TEAM_CONFIG_PATH}}` |
-| Dev Agent Def | {{DEV_SUBAGENT_PATH}} |
 | Reviewer Agent Def | {{REVIEWER_SUBAGENT_PATH}} |
 | Critic Agent Def | {{CRITIC_SUBAGENT_PATH}} |
 | Project Root | {{PROJECT_ROOT}} |

package/bundled/dev-pipeline/templates/sections/directory-convention-agent.md

@@ -1,8 +1,8 @@
 ## PrizmKit Directory Convention
 
 ```
-.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md  ← orchestrator writes Sections 1-4; Dev appends Implementation Log; Reviewer appends Review Notes
+.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md  ← orchestrator writes Sections 1-4 + Implementation Log; Reviewer appends Review Notes
 .prizmkit/specs/{{FEATURE_SLUG}}/plan.md              ← includes Tasks section
 ```
 
-**`context-snapshot.md`** is the shared knowledge base. Orchestrator writes Sections 1-4; Dev appends Implementation Log; Reviewer appends Review Notes. Append-only after initial creation.
+**`context-snapshot.md`** is the shared knowledge base. Orchestrator writes Sections 1-4 and the Implementation Log; Reviewer appends Review Notes. Append-only after initial creation.

package/bundled/dev-pipeline/templates/sections/directory-convention-full.md

@@ -1,9 +1,9 @@
 ## PrizmKit Directory Convention
 
 ```
-.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md  ← orchestrator writes Sections 1-4; Dev appends Implementation Log; Reviewer appends Review Notes
+.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md  ← orchestrator writes Sections 1-4 + Implementation Log; Reviewer appends Review Notes
 .prizmkit/specs/{{FEATURE_SLUG}}/spec.md
 .prizmkit/specs/{{FEATURE_SLUG}}/plan.md              ← includes Tasks section
 ```
 
-**`context-snapshot.md`** is the shared knowledge base. Orchestrator writes Sections 1-4; Dev appends Implementation Log; Reviewer appends Review Notes. This eliminates redundant I/O across all agents.
+**`context-snapshot.md`** is the shared knowledge base. Orchestrator writes Sections 1-4 and the Implementation Log; Reviewer appends Review Notes. This eliminates redundant I/O across review and orchestration phases.

package/bundled/dev-pipeline/templates/sections/phase-implement-agent.md

@@ -22,6 +22,7 @@ grep -c '^\- \[ \]' .prizmkit/specs/{{FEATURE_SLUG}}/plan.md 2>/dev/null || true
 - Implements task-by-task, marking each `[x]` immediately
 - Creates/updates L2 `.prizm` docs when creating new modules
 - Defers scoped/full test execution until after the code-review loop completes
+- Preserves Reviewer/Critic behavior; only the top-level implementation Dev handoff is removed
 - If plan.md has >5 tasks: update checkpoints after every 3 tasks
 
 **3c. Focused checks only (no test gate here)**:

package/bundled/dev-pipeline/templates/sections/phase-implement-full.md

@@ -23,6 +23,7 @@ Save pre-existing failing tests as `BASELINE_FAILURES`.
 - Implements task-by-task, marking each `[x]` immediately
 - Creates/updates L2 `.prizm` docs when creating new modules
 - Defers scoped/full test execution until after the code-review loop completes
+- Preserves Reviewer/Critic behavior; only the top-level implementation Dev handoff is removed
 - If plan.md has >5 tasks: update checkpoints after every 3 tasks
 
 **3c. Focused checks only (no test gate here)**:

package/bundled/dev-pipeline/tests/test_generate_bootstrap_prompt.py

@@ -8,6 +8,7 @@ from argparse import Namespace
 from pathlib import Path
 
 from generate_bootstrap_prompt import (
+    ACTIVE_AGENT_PROMPTS,
     compute_feature_slug,
     find_feature,
     format_acceptance_criteria,
@@ -21,6 +22,7 @@ from generate_bootstrap_prompt import (
     build_replacements,
     generate_checkpoint_definition,
     merge_checkpoint_state,
+    load_active_agent_prompts,
     load_log_size_section,
     main as generate_bootstrap_main,
 )
@@ -809,6 +811,50 @@ class TestHeadlessRecoveryReframing:
             assert "run `/compact` after" not in rendered
 
 
+class TestDirectOrchestratorImplementationPrompts:
+    def test_active_agent_prompt_loader_excludes_retired_dev_implement_prompt(self):
+        templates_dir = Path("dev-pipeline/templates").resolve()
+
+        replacements = load_active_agent_prompts(str(templates_dir))
+
+        assert "dev-implement.md" not in ACTIVE_AGENT_PROMPTS
+        assert "{{AGENT_PROMPT_DEV_IMPLEMENT}}" not in replacements
+        assert "{{AGENT_PROMPT_CRITIC_PLAN_CHALLENGE}}" in replacements
+        assert (templates_dir / "agent-prompts" / "dev-implement.md").exists() is False
+
+    def test_sections_all_modes_use_direct_orchestrator_implementation(self):
+        sections_dir = Path("dev-pipeline/templates/sections").resolve()
+
+        for mode in ("lite", "standard", "full"):
+            rendered = "\n".join(
+                section for _name, section in assemble_sections(
+                    mode, str(sections_dir), init_done=True, is_resume=False,
+                    critic_enabled=(mode == "full"), browser_enabled=False,
+                )
+            )
+
+            assert "/prizmkit-implement" in rendered
+            assert "orchestrator) execute" in rendered or "Run `/prizmkit-implement`" in rendered
+            assert "Spawn Dev subagent" not in rendered
+            assert "Spawn Dev agent" not in rendered
+            assert "Implement — Dev" not in rendered
+            assert "{{AGENT_PROMPT_DEV_IMPLEMENT}}" not in rendered
+            assert "dev-implement.md" not in rendered
+            assert "Reviewer Agent → filter → Dev Agent fix" in rendered
+
+    def test_legacy_tier_templates_use_direct_orchestrator_implementation(self):
+        for template_name in ("bootstrap-tier2.md", "bootstrap-tier3.md"):
+            rendered = (Path("dev-pipeline/templates") / template_name).read_text(encoding="utf-8")
+
+            assert "/prizmkit-implement" in rendered
+            assert "Implement — Orchestrator Direct" in rendered
+            assert "Spawn Dev subagent" not in rendered
+            assert "Spawn Dev agent" not in rendered
+            assert "Implement — Dev" not in rendered
+            assert "{{AGENT_PROMPT_DEV_IMPLEMENT}}" not in rendered
+            assert "dev-implement.md" not in rendered
+
+
 # ---------------------------------------------------------------------------
 # continuation handoff
 # ---------------------------------------------------------------------------

package/bundled/dev-pipeline/tests/test_python_runner_parity.py

@@ -103,7 +103,7 @@ def test_python_parity_suite_declares_coverage_for_all_legacy_unix_snapshot_scen
         "envResolution": {
             "verboseAndStreamJson": ["test_python_env_resolution_scenarios_match_snapshot_contracts"],
             "effortModelAndCli": ["test_ai_session_command_builders_match_unix_runtime_snapshot"],
-            "worktreeIgnored": ["test_runner_environment_enables_worktree_by_default_and_accepts_falsey_opt_out"],
+            "worktreeIgnored": ["test_runner_environment_disables_worktree_by_default_and_accepts_truthy_opt_in"],
             "autoPushFlag": ["test_successful_worktree_session_merges_cleans_branch_and_honors_auto_push"],
         },
         "aiCliCommands": {
@@ -320,13 +320,14 @@ def test_runner_models_parse_legacy_args_and_environment(tmp_path):
     assert env.strict_behavior_check is False
 
 
-def test_runner_environment_enables_worktree_by_default_and_accepts_falsey_opt_out():
+def test_runner_environment_disables_worktree_by_default_and_accepts_truthy_opt_in():
     from prizmkit_runtime.runner_models import RunnerEnvironment
 
-    assert RunnerEnvironment.from_env({}).use_worktree is True
-    assert RunnerEnvironment.from_env({"USE_WORKTREE": "1"}).use_worktree is True
-    assert RunnerEnvironment.from_env({"USE_WORKTREE": "true"}).use_worktree is True
-    assert RunnerEnvironment.from_env({"USE_WORKTREE": "unexpected"}).use_worktree is True
+    assert RunnerEnvironment.from_env({}).use_worktree is False
+    assert RunnerEnvironment.from_env({"USE_WORKTREE": "unexpected"}).use_worktree is False
+
+    for truthy in ("1", "true", "yes", "on"):
+        assert RunnerEnvironment.from_env({"USE_WORKTREE": truthy}).use_worktree is True
 
     for falsey in ("0", "false", "no", "off"):
         assert RunnerEnvironment.from_env({"USE_WORKTREE": falsey}).use_worktree is False
@@ -639,10 +640,11 @@ def _install_runner_session_fakes(monkeypatch, runners, *, statuses=("success",)
 
 
 @pytest.mark.parametrize(("kind", "item_id", "branch"), [("feature", "F-001", "dev/F-001-test"), ("bugfix", "B-001", "bugfix/B-001-test")])
-def test_feature_and_bugfix_default_worktree_launches_from_worktree_and_renders_worktree_root(monkeypatch, tmp_path, kind, item_id, branch):
+def test_feature_and_bugfix_explicit_worktree_launches_from_worktree_and_renders_worktree_root(monkeypatch, tmp_path, kind, item_id, branch):
     from prizmkit_runtime import runners
     from prizmkit_runtime.runner_models import family_for, parse_invocation
 
+    monkeypatch.setenv("USE_WORKTREE", "1")
     monkeypatch.setenv("DEV_BRANCH", branch)
     paths = _make_paths(tmp_path / kind)
     family = family_for(kind, paths)
@@ -672,6 +674,7 @@ def test_successful_worktree_session_merges_cleans_branch_and_honors_auto_push(m
     from prizmkit_runtime import runners
     from prizmkit_runtime.runner_models import family_for, parse_invocation
 
+    monkeypatch.setenv("USE_WORKTREE", "1")
     monkeypatch.setenv("DEV_BRANCH", "dev/F-001-test")
     monkeypatch.setenv("AUTO_PUSH", "1")
     paths = _make_paths(tmp_path)
@@ -692,6 +695,7 @@ def test_worktree_merge_conflict_writes_session_status_and_updates_merge_conflic
     from prizmkit_runtime import runners
     from prizmkit_runtime.runner_models import family_for, parse_invocation
 
+    monkeypatch.setenv("USE_WORKTREE", "1")
     monkeypatch.setenv("DEV_BRANCH", "dev/F-001-test")
     paths = _make_paths(tmp_path)
     family = family_for("feature", paths)
@@ -719,6 +723,7 @@ def test_terminal_worktree_failure_saves_wip_and_removes_worktree_without_deleti
     from prizmkit_runtime import runners
     from prizmkit_runtime.runner_models import family_for, parse_invocation
 
+    monkeypatch.setenv("USE_WORKTREE", "1")
     monkeypatch.setenv("DEV_BRANCH", "dev/F-001-test")
     paths = _make_paths(tmp_path)
     family = family_for("feature", paths)
@@ -735,7 +740,7 @@ def test_terminal_worktree_failure_saves_wip_and_removes_worktree_without_deleti
     assert observed.updates[-1][0] == "crashed"
 
 
-def test_default_worktree_materializes_ignored_support_assets_before_prompt_and_launch(monkeypatch, tmp_path):
+def test_explicit_worktree_materializes_ignored_support_assets_before_prompt_and_launch(monkeypatch, tmp_path):
     from prizmkit_runtime import runners
     from prizmkit_runtime.paths import resolve_runtime_paths
     from prizmkit_runtime.runner_models import PromptGenerationResult, SessionClassification, family_for, parse_invocation
@@ -766,6 +771,7 @@ def test_default_worktree_materializes_ignored_support_assets_before_prompt_and_
     invocation = invocation.__class__(**{**invocation.__dict__, "list_path": paths.feature_plan})
     launch_cwds = []
 
+    monkeypatch.setenv("USE_WORKTREE", "1")
     monkeypatch.setenv("DEV_BRANCH", "dev/F-001-support-assets")
     monkeypatch.setattr(
         runners,
@@ -830,11 +836,10 @@ def test_default_worktree_materializes_ignored_support_assets_before_prompt_and_
     assert not launch_cwds[0].exists()
 
 
-def test_use_worktree_false_preserves_main_worktree_branch_launch(monkeypatch, tmp_path):
+def test_default_no_worktree_preserves_main_worktree_branch_launch(monkeypatch, tmp_path):
     from prizmkit_runtime import runners
     from prizmkit_runtime.runner_models import family_for, parse_invocation
 
-    monkeypatch.setenv("USE_WORKTREE", "0")
     monkeypatch.setenv("DEV_BRANCH", "dev/F-001-test")
     paths = _make_paths(tmp_path)
     family = family_for("feature", paths)
@@ -859,10 +864,103 @@ def test_use_worktree_false_preserves_main_worktree_branch_launch(monkeypatch, t
     assert "branch_merge" in plan_names
 
 
+def test_no_worktree_runner_ignores_recovery_side_effect_branch(monkeypatch, tmp_path):
+    from prizmkit_runtime import runners
+    from prizmkit_runtime.runner_models import family_for, parse_invocation
+
+    monkeypatch.delenv("DEV_BRANCH", raising=False)
+    paths = _make_paths(tmp_path)
+    family = family_for("feature", paths)
+    invocation = parse_invocation(family, "run", ())
+    invocation = invocation.__class__(**{**invocation.__dict__, "list_path": paths.feature_plan})
+    observed = _install_runner_session_fakes(monkeypatch, runners)
+    branch_names = []
+
+    monkeypatch.setenv("DEV_BRANCH", "dev/F-001-recovery-20260707")
+    monkeypatch.setattr(runners, "current_branch", lambda _root: "dev/F-001-recovery-20260707")
+
+    def fake_run_git_plan(project_root, plan):
+        if plan.name == "branch_create":
+            branch_names.append(plan.commands[1].args[2])
+        return SimpleNamespace(ok=True, plan=plan, results=())
+
+    monkeypatch.setattr(runners, "run_git_plan", fake_run_git_plan)
+
+    status = runners._process_item(family, invocation, "F-001", paths, initial_metadata={})
+
+    assert status == "completed"
+    assert branch_names and branch_names[0].startswith("dev/F-001-")
+    assert "recovery" not in branch_names[0]
+    assert observed.updates[-1][2]["active_dev_branch"] == branch_names[0]
+    assert observed.updates[-1][2]["base_branch"] == "main"
+
+
+def test_foreground_runner_emits_structured_feature_progress(monkeypatch, tmp_path, capsys):
+    from prizmkit_runtime import runners
+    from prizmkit_runtime.runner_models import family_for, parse_invocation
+
+    monkeypatch.setenv("DEV_BRANCH", "dev/F-001-output")
+    paths = _make_paths(tmp_path)
+    family = family_for("feature", paths)
+    invocation = parse_invocation(family, "run", ())
+    invocation = invocation.__class__(**{**invocation.__dict__, "list_path": paths.feature_plan})
+    _install_runner_session_fakes(monkeypatch, runners)
+    monkeypatch.setattr(runners, "run_git_plan", lambda project_root, plan: SimpleNamespace(ok=True, plan=plan, results=()))
+
+    status = runners._process_item(
+        family,
+        invocation,
+        "F-001",
+        paths,
+        initial_metadata={"title": "Readable output", "retry_count": 1, "infra_error_count": 2},
+    )
+
+    captured = capsys.readouterr()
+    assert status == "completed"
+    assert "────────────────────────────────────────────────────" in captured.err
+    assert "Feature: F-001 — Readable output" in captured.err
+    assert "Code retry: 1 / 3" in captured.err
+    assert "Infrastructure retry: 2 / 3" in captured.err
+    assert "Pipeline mode: lite (Tier 1 — Single Agent)" in captured.err
+    assert "Agents: 1 (critic: disabled)" in captured.err
+    assert "Spawning AI CLI session: F-001-session-1" in captured.err
+    assert "Session result: success" in captured.err
+
+
+def test_no_worktree_interrupt_saves_wip_and_returns_to_base(monkeypatch, tmp_path):
+    from prizmkit_runtime import runners
+    from prizmkit_runtime.runner_models import family_for, parse_invocation
+
+    monkeypatch.setenv("DEV_BRANCH", "dev/F-001-interrupt")
+    paths = _make_paths(tmp_path)
+    family = family_for("feature", paths)
+    invocation = parse_invocation(family, "run", ())
+    invocation = invocation.__class__(**{**invocation.__dict__, "list_path": paths.feature_plan})
+    _install_runner_session_fakes(monkeypatch, runners)
+    ensure_calls = []
+    monkeypatch.setattr(runners, "run_git_plan", lambda project_root, plan: SimpleNamespace(ok=True, plan=plan, results=()))
+    monkeypatch.setattr(runners, "branch_ensure_return", lambda project_root, base, branch: ensure_calls.append((base, branch)))
+
+    class InterruptingLauncher:
+        def __init__(self, config):
+            self.config = config
+
+        def run(self):
+            raise KeyboardInterrupt
+
+    monkeypatch.setattr(runners, "AISessionLauncher", InterruptingLauncher)
+
+    with pytest.raises(KeyboardInterrupt):
+        runners._process_item(family, invocation, "F-001", paths, initial_metadata={})
+
+    assert ensure_calls == [("main", "dev/F-001-interrupt")]
+
+
 def test_context_overflow_reuses_worktree_and_skips_cleanup_until_terminal_outcome(monkeypatch, tmp_path):
     from prizmkit_runtime import runners
     from prizmkit_runtime.runner_models import family_for, parse_invocation
 
+    monkeypatch.setenv("USE_WORKTREE", "1")
     monkeypatch.setenv("DEV_BRANCH", "dev/F-001-test")
     paths = _make_paths(tmp_path)
     family = family_for("feature", paths)
@@ -958,6 +1056,14 @@ def test_classification_stalls_after_repeated_no_progress_context_overflow(tmp_p
     assert classification.no_progress_count == 2
 
 
+def test_recovery_prompt_keeps_existing_branch_instead_of_recovery_suffix():
+    text = (PIPELINE_ROOT / "scripts" / "generate-recovery-prompt.py").read_text(encoding="utf-8")
+
+    assert "fix/{bug_id}-recovery" not in text
+    assert "do not create an additional" in text
+    assert "last-resort fallback" in text
+
+
 def test_recovery_detector_resolver_prefers_installed_platform_asset(tmp_path):
     from prizmkit_runtime.paths import resolve_runtime_paths
     from prizmkit_runtime.runner_recovery import RecoveryDetectorResolver
@@ -1117,6 +1223,7 @@ def test_python_daemon_controlled_start_status_stop_matches_snapshot(tmp_path):
         "#!/usr/bin/env python3\n"
         "import os, sys, time\n"
         "print('payload env=' + os.environ.get('FOO', ''))\n"
+        "print('payload live=' + os.environ.get('PRIZMKIT_LIVE_OUTPUT', ''))\n"
         "print('payload args=' + ' '.join(sys.argv[1:]))\n"
         "sys.stdout.flush()\n"
         "time.sleep(30)\n",
@@ -1147,6 +1254,7 @@ def test_python_daemon_controlled_start_status_stop_matches_snapshot(tmp_path):
     assert json.loads(stop.render())["message"] in {"stopped", "already exited", "not running"}
     log_text = (paths.feature_state_dir / "pipeline-daemon.log").read_text(encoding="utf-8")
     assert "FOO=bar" in log_text or "payload env=bar" in log_text
+    assert "payload live=0" in log_text
     assert "--project-root" in log_text
 
 

package/bundled/dev-pipeline/tests/test_unified_cli.py

@@ -617,6 +617,82 @@ def test_session_dual_writes_progress_and_recovers_backup(tmp_path):
     assert second_log.read_text(encoding="utf-8") == "larger recovered log"
 
 
+def test_session_live_output_prints_paths_and_verbose_cli_output(tmp_path, capsys):
+    from prizmkit_runtime.sessions import AISessionConfig, AISessionLauncher
+
+    fake_cli = tmp_path / "live_cli.py"
+    fake_cli.write_text(
+        "#!/usr/bin/env python3\n"
+        "print('live-line', flush=True)\n",
+        encoding="utf-8",
+    )
+    fake_cli.chmod(0o755)
+    prompt = tmp_path / "prompt.md"
+    prompt.write_text("hello", encoding="utf-8")
+    session_log = tmp_path / "state" / "sessions" / "sess-live" / "logs" / "session.log"
+    progress = session_log.with_name("progress.json")
+    heartbeat = session_log.with_name("heartbeat.json")
+
+    result = AISessionLauncher(
+        AISessionConfig(
+            cli_command=str(fake_cli),
+            platform="codebuddy",
+            model=None,
+            prompt_path=prompt,
+            cwd=tmp_path,
+            log_path=session_log,
+            progress_path=progress,
+            heartbeat_path=heartbeat,
+            verbose=True,
+            live_output=True,
+        )
+    ).run()
+
+    captured = capsys.readouterr()
+    assert result.exit_code == 0
+    assert "live-line" in captured.out
+    assert "[prizmkit] AI session started" in captured.err
+    assert f"[prizmkit] Prompt: {prompt}" in captured.err
+    assert f"[prizmkit] Session log: {session_log}" in captured.err
+    assert f"[prizmkit] Progress: {progress}" in captured.err
+    assert f"[prizmkit] Heartbeat: {heartbeat}" in captured.err
+    assert "[prizmkit] AI session finished" in captured.err
+
+
+def test_session_live_output_does_not_forward_cli_output_without_verbose(tmp_path, capsys):
+    from prizmkit_runtime.sessions import AISessionConfig, AISessionLauncher
+
+    fake_cli = tmp_path / "quiet_cli.py"
+    fake_cli.write_text(
+        "#!/usr/bin/env python3\n"
+        "print('hidden-line', flush=True)\n",
+        encoding="utf-8",
+    )
+    fake_cli.chmod(0o755)
+    prompt = tmp_path / "prompt.md"
+    prompt.write_text("hello", encoding="utf-8")
+    session_log = tmp_path / "state" / "sessions" / "sess-quiet" / "logs" / "session.log"
+
+    result = AISessionLauncher(
+        AISessionConfig(
+            cli_command=str(fake_cli),
+            platform="codebuddy",
+            model=None,
+            prompt_path=prompt,
+            cwd=tmp_path,
+            log_path=session_log,
+            live_output=True,
+        )
+    ).run()
+
+    captured = capsys.readouterr()
+    assert result.exit_code == 0
+    assert "hidden-line" not in captured.out
+    assert "hidden-line" in session_log.read_text(encoding="utf-8")
+    assert "[prizmkit] AI session started" in captured.err
+    assert "[prizmkit] AI session finished" in captured.err
+
+
 def test_session_final_progress_merge_preserves_tracker_fatal_error(tmp_path):
     from prizmkit_runtime.sessions import AISessionConfig, AISessionLauncher
 

package/bundled/skills/_metadata.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.102",
+  "version": "1.1.105",
   "skills": {
     "prizm-kit": {
       "description": "Full-lifecycle dev toolkit. Covers spec-driven development, Prizm context docs, code quality, debugging, deployment, and knowledge management.",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prizmkit",
-  "version": "1.1.102",
+  "version": "1.1.105",
   "description": "Create a new PrizmKit-powered project with clean initialization — no framework dev files, just what you need.",
   "type": "module",
   "bin": {