prizmkit 1.1.114 → 1.1.115

package/bundled/dev-pipeline/templates/feature-list-schema.json

@@ -75,7 +75,7 @@
               "high",
               "critical"
             ],
-            "description": "Estimated implementation complexity. Determines pipeline execution tier: low/medium → lite (single agent), high → standard (orchestrator + dev + reviewer), critical → full (full team + critic)."
+            "description": "Estimated implementation complexity. Determines pipeline execution tier: low/medium → lite (single agent), high → standard (orchestrator + reviewer), critical → full (orchestrator + stronger guardrails)."
           },
           "dependencies": {
             "type": "array",
@@ -145,19 +145,6 @@
             "type": "string",
             "description": "AI model ID for this feature. Overrides $MODEL env var."
           },
-          "critic": {
-            "type": "boolean",
-            "description": "Enable adversarial plan challenge before implementation. Default: false.",
-            "default": false
-          },
-          "critic_count": {
-            "type": "integer",
-            "description": "Number of parallel critic agents. 1 = single critic, 3 = multi-critic voting. Default: 1.",
-            "enum": [
-              1,
-              3
-            ]
-          },
           "completion_notes": {
             "type": "array",
             "items": {
@@ -167,7 +154,9 @@
           },
           "user_context": {
             "type": "array",
-            "items": { "type": "string" },
+            "items": {
+              "type": "string"
+            },
             "description": "User-provided supplementary materials, preserved verbatim. Each entry is either inline content/rules (stored as-is) or a file reference (e.g. 'src/auth/login.ts:42-78', 'src/utils/ — focus on validation logic')."
           },
           "browser_interaction": {
@@ -176,7 +165,11 @@
             "properties": {
               "tool": {
                 "type": "string",
-                "enum": ["playwright-cli", "opencli", "auto"],
+                "enum": [
+                  "playwright-cli",
+                  "opencli",
+                  "auto"
+                ],
                 "default": "auto",
                 "description": "Browser tool to use. 'auto' (default) = AI chooses at runtime. 'playwright-cli' = local dev server verification in isolated browser. 'opencli' = reuses Chrome logged-in session, ideal for verifying third-party integrations or OAuth flows."
               },
@@ -188,8 +181,30 @@
                 }
               }
             }
+          },
+          "testing": {
+            "type": "object",
+            "description": "Testing expectations for this feature. Used by planning and scoped test gates.",
+            "properties": {
+              "required": {
+                "type": "boolean"
+              },
+              "coverage_target": {
+                "type": "integer"
+              },
+              "strategy": {
+                "type": "string"
+              },
+              "focus": {
+                "type": "array",
+                "items": {
+                  "type": "string"
+                }
+              }
+            }
           }
-        }
+        },
+        "additionalProperties": false
       }
     },
     "global_context": {

package/bundled/dev-pipeline/templates/refactor-bootstrap-prompt.md

@@ -118,22 +118,6 @@ If `DEV_PORT` is unknown, discover it from project config; do not guess port 300
 
 ---
 
-{{IF_CRITIC_ENABLED}}
-### Phase 2: Critic — Behavior Preservation Review
-
-Challenge the plan before implementation. Focus on:
-- behavior preservation gaps;
-- unsafe task ordering;
-- missing rollback strategy;
-- insufficient test evidence.
-
-Write the critic result into `.prizmkit/refactor/{{REFACTOR_ID}}/context-snapshot.md` or the plan notes, then update any unsafe plan details before implementation.
-
-**Checkpoint update**: set step `critic-plan-review` to `completed` in `{{CHECKPOINT_PATH}}`.
-
----
-
-{{END_IF_CRITIC_ENABLED}}
 ### Phase 3: Implement — Behavior-Preserving Refactoring
 
 Run `/prizmkit-implement` with `artifact_dir=.prizmkit/refactor/{{REFACTOR_ID}}/`.

package/bundled/dev-pipeline/templates/refactor-list-schema.json

@@ -186,29 +186,22 @@
           },
           "user_context": {
             "type": "array",
-            "items": { "type": "string" },
+            "items": {
+              "type": "string"
+            },
             "description": "User-provided supplementary materials, preserved verbatim. Each entry is either inline content/rules (stored as-is) or a file reference (e.g. 'src/auth/login.ts:42-78', 'src/utils/ — focus on validation logic')."
           },
-          "critic": {
-            "type": "boolean",
-            "description": "Enable adversarial plan challenge before implementation. Default: true for critical/high priority refactors, false for others.",
-            "default": false
-          },
-          "critic_count": {
-            "type": "integer",
-            "description": "Number of parallel critic agents. 1 = single critic, 3 = multi-critic voting. Default: 3 for critical, 1 for high, omit for others.",
-            "enum": [
-              1,
-              3
-            ]
-          },
           "browser_interaction": {
             "type": "object",
             "description": "Browser verification config for refactors affecting UI behavior. Supports playwright-cli and opencli. AI auto-detects dev server command, URL, and port from project config at runtime.",
             "properties": {
               "tool": {
                 "type": "string",
-                "enum": ["playwright-cli", "opencli", "auto"],
+                "enum": [
+                  "playwright-cli",
+                  "opencli",
+                  "auto"
+                ],
                 "default": "auto",
                 "description": "Browser tool to use. 'auto' (default) = AI chooses at runtime. 'playwright-cli' = local dev server verification in isolated browser. 'opencli' = reuses Chrome logged-in session, ideal for verifying refactors involving third-party integrations or OAuth flows."
               },
@@ -221,7 +214,8 @@
               }
             }
           }
-        }
+        },
+        "additionalProperties": false
       }
     },
     "global_context": {

package/bundled/dev-pipeline/templates/sections/bugfix-session-context.md

@@ -3,5 +3,5 @@
 - **Bug ID**: {{BUG_ID}} | **Session**: {{SESSION_ID}} | **Run**: {{RUN_ID}}
 - **Bug Title**: {{BUG_TITLE}}
 - **Severity**: {{SEVERITY}}
-- **Mode**: {{PIPELINE_MODE}} | **Critic**: {{CRITIC_ENABLED}}
+- **Mode**: {{PIPELINE_MODE}}
 - **Verification Type**: {{VERIFICATION_TYPE}}

package/bundled/dev-pipeline/templates/sections/context-budget-rules.md

@@ -6,7 +6,7 @@ You are running in **headless non-interactive mode** with a FINITE context windo
 
 1. **context-snapshot.md is your single source of truth** — After it is built, ALWAYS read context-snapshot.md instead of re-reading individual source files
 2. **Never re-read your own writes** — After you create/modify a file, do NOT read it back to verify. Trust your write was correct.
-3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files including those summarized in context-snapshot.md Section 4. Subagents (Critic, Reviewer) must receive context-snapshot.md and rely on it rather than independently re-reading the same files the orchestrator already read.
+3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files including those summarized in context-snapshot.md Section 4. Reviewer subagents must receive context-snapshot.md and rely on it rather than independently re-reading the same files the orchestrator already read.
 4. **Stay focused** — Do NOT explore code unrelated to this feature. No curiosity-driven reads.
 5. **One task at a time** — Complete and test one task before starting the next.
 6. **Minimize tool output** — Never load full command output into context. First capture command output to a temp file using the command/tool output option or the host-appropriate redirection, then inspect only the final relevant lines and use targeted search helpers to extract the information needed for the current task. Only read the filtered result — never the raw full output.

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

@@ -5,5 +5,4 @@
 | Feature Artifacts Dir | `.prizmkit/specs/{{FEATURE_SLUG}}/` |
 | Context Snapshot | `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` |
 | 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

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

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

@@ -17,7 +17,7 @@ Before starting, check plan.md Tasks:
 - 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
+- Preserves Reviewer behavior; only the top-level implementation Dev handoff is removed
 - If plan.md has >5 tasks: update checkpoints after every 3 tasks
 
 **3b. Focused checks only (no test gate here)**:

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

@@ -17,7 +17,7 @@ Before starting, check plan.md Tasks:
 - 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
+- Preserves Reviewer behavior; only the top-level implementation Dev handoff is removed
 - If plan.md has >5 tasks: update checkpoints after every 3 tasks
 
 **3b. Focused checks only (no test gate here)**:

package/bundled/dev-pipeline/templates/sections/refactor-session-context.md

@@ -4,4 +4,4 @@
 - **Title**: {{REFACTOR_TITLE}}
 - **Type**: {{REFACTOR_TYPE}}
 - **Priority**: {{PRIORITY}} | **Complexity**: {{COMPLEXITY}}
-- **Mode**: {{PIPELINE_MODE}} | **Critic**: {{CRITIC_ENABLED}}
+- **Mode**: {{PIPELINE_MODE}}

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

@@ -26,3 +26,4 @@ _load_hyphenated_module("generate_bootstrap_prompt", "generate-bootstrap-prompt.
 _load_hyphenated_module("generate_bugfix_prompt", "generate-bugfix-prompt.py")
 _load_hyphenated_module("generate_refactor_prompt", "generate-refactor-prompt.py")
 _load_hyphenated_module("update_feature_status", "update-feature-status.py")
+_load_hyphenated_module("update_checkpoint", "update-checkpoint.py")

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

@@ -0,0 +1,164 @@
+"""Tests for shared workflow checkpoint state semantics."""
+
+from __future__ import annotations
+
+import json
+
+from prizmkit_runtime.checkpoint_state import load_checkpoint_state, read_checkpoint_cursor
+from update_checkpoint import update_checkpoint
+
+
+def _checkpoint(steps):
+    return {"version": 1, "workflow_type": "feature-pipeline", "steps": steps}
+
+
+def _step(step_id, skill="skill", name="Step", status="pending", depends_on=None):
+    return {
+        "id": step_id,
+        "skill": skill,
+        "name": name,
+        "status": status,
+        "required_artifacts": [],
+        "depends_on": depends_on,
+    }
+
+
+def _write(path, data):
+    path.write_text(json.dumps(data), encoding="utf-8")
+    return path
+
+
+def test_valid_checkpoint_current_step_uses_first_non_terminal(tmp_path):
+    path = _write(tmp_path / "workflow-checkpoint.json", _checkpoint([
+        _step("S01", "plan", "Plan", "completed"),
+        _step("S02", "implement", "Implement", "in_progress", "S01"),
+        _step("S03", "review", "Review", "pending", "S02"),
+    ]))
+
+    state = load_checkpoint_state(path)
+
+    assert state.valid is True
+    assert state.current_step_name == "Implement"
+    assert state.cursor == 2
+    assert state.cursor_signature == "S02:implement:in_progress"
+    assert read_checkpoint_cursor(path) == 2
+
+
+def test_all_completed_checkpoint_has_complete_cursor(tmp_path):
+    path = _write(tmp_path / "workflow-checkpoint.json", _checkpoint([
+        _step("S01", "plan", "Plan", "completed"),
+        _step("S02", "commit", "Commit", "skipped", "S01"),
+    ]))
+
+    state = load_checkpoint_state(path)
+
+    assert state.valid is True
+    assert state.all_completed is True
+    assert state.current_step is None
+    assert state.current_step_name == ""
+    assert state.cursor == 2
+    assert state.cursor_signature == "complete"
+
+
+def test_missing_and_malformed_checkpoints_are_invalid(tmp_path):
+    missing = load_checkpoint_state(tmp_path / "missing.json")
+    assert missing.valid is False
+    assert missing.exists is False
+    assert missing.error_code == "missing"
+    assert missing.current_step_name == ""
+
+    malformed_path = tmp_path / "bad.json"
+    malformed_path.write_text("{not-json", encoding="utf-8")
+    malformed = load_checkpoint_state(malformed_path)
+    assert malformed.valid is False
+    assert malformed.exists is True
+    assert malformed.error_code == "malformed_json"
+    assert malformed.current_step_name == ""
+
+
+def test_structural_validation_error_codes(tmp_path):
+    cases = [
+        ("missing_steps", {}),
+        ("empty_steps", {"steps": []}),
+        ("duplicate_step_id", _checkpoint([_step("S01"), _step("S01")])),
+        ("invalid_status", _checkpoint([_step("S01", status="done")])),
+        ("invalid_depends_on", _checkpoint([_step("S01", depends_on="S99")])),
+        ("invalid_depends_on", _checkpoint([_step("S01", depends_on="S02"), _step("S02")])),
+        ("malformed_step_id", _checkpoint([_step("one")])),
+        ("invalid_step", {"steps": ["not-object"]}),
+    ]
+    for expected_code, payload in cases:
+        path = _write(tmp_path / f"{expected_code}.json", payload)
+        state = load_checkpoint_state(path)
+        assert state.valid is False
+        assert state.error_code == expected_code
+        assert state.current_step_name == ""
+        assert read_checkpoint_cursor(path) is None
+
+
+def test_failed_checkpoint_step_is_current_cursor(tmp_path):
+    path = _write(tmp_path / "workflow-checkpoint.json", _checkpoint([
+        _step("S01", "plan", "Plan", "completed"),
+        _step("S02", "review", "Review", "failed", "S01"),
+    ]))
+
+    state = load_checkpoint_state(path)
+
+    assert state.valid is True
+    assert state.current_step_name == "Review"
+    assert state.cursor == 2
+
+
+def test_duplicate_skills_are_reported_but_exact_ids_remain_valid(tmp_path):
+    path = _write(tmp_path / "workflow-checkpoint.json", _checkpoint([
+        _step("S01", "prizmkit-committer", "Commit First", "pending"),
+        _step("S02", "prizmkit-committer", "Commit Second", "pending", "S01"),
+    ]))
+
+    state = load_checkpoint_state(path)
+
+    assert state.valid is True
+    assert state.duplicate_skills == {"prizmkit-committer": ("S01", "S02")}
+
+
+def test_update_checkpoint_rejects_ambiguous_skill_without_mutation(tmp_path):
+    path = _write(tmp_path / "workflow-checkpoint.json", _checkpoint([
+        _step("S01", "prizmkit-committer", "Commit First", "pending"),
+        _step("S02", "prizmkit-committer", "Commit Second", "pending", "S01"),
+    ]))
+    before = path.read_text(encoding="utf-8")
+
+    result = update_checkpoint(str(path), "prizmkit-committer", "completed")
+
+    assert result["ok"] is False
+    assert "matches multiple checkpoint steps" in result["error"]
+    assert "Use an explicit step ID" in result["error"]
+    assert path.read_text(encoding="utf-8") == before
+
+
+def test_update_checkpoint_exact_id_updates_one_duplicate_skill_step(tmp_path):
+    path = _write(tmp_path / "workflow-checkpoint.json", _checkpoint([
+        _step("S01", "prizmkit-committer", "Commit First", "pending"),
+        _step("S02", "prizmkit-committer", "Commit Second", "pending", "S01"),
+    ]))
+
+    result = update_checkpoint(str(path), "S02", "completed")
+    data = json.loads(path.read_text(encoding="utf-8"))
+
+    assert result["ok"] is True
+    assert result["step_id"] == "S02"
+    assert data["steps"][0]["status"] == "pending"
+    assert data["steps"][1]["status"] == "completed"
+
+
+def test_update_checkpoint_invalid_checkpoint_fails_without_mutation(tmp_path):
+    path = _write(tmp_path / "workflow-checkpoint.json", _checkpoint([
+        _step("S01", "plan", "Plan", "done"),
+    ]))
+    before = path.read_text(encoding="utf-8")
+
+    result = update_checkpoint(str(path), "S01", "completed")
+
+    assert result["ok"] is False
+    assert "invalid_status" in result["error"]
+    assert path.read_text(encoding="utf-8") == before