prizmkit 1.1.111 → 1.1.113

package/bundled/VERSION.json

@@ -1,5 +1,5 @@
 {
-  "frameworkVersion": "1.1.111",
-  "bundledAt": "2026-07-08T07:06:52.766Z",
-  "bundledFrom": "1db214b"
+  "frameworkVersion": "1.1.113",
+  "bundledAt": "2026-07-09T01:22:22.762Z",
+  "bundledFrom": "09ad715"
 }

package/bundled/adapters/codex/skill-adapter.js

@@ -21,6 +21,10 @@ function applyCodexInteractionCompatibility(content) {
 
   return content
     .replace(/\bAskUserQuestion\b/g, 'request_user_input')
+    .replace(
+      /Use `request_user_input`; do not render path options as plain text\./g,
+      fallbackInstruction
+    )
     .replace(
       /Do NOT render options as plain text — the user must be able to click\/select\./g,
       fallbackInstruction

package/bundled/agents/prizm-dev-team-reviewer.md

@@ -25,7 +25,18 @@ You are the team's "senior engineer doing code review" — you diagnose problems
 2. If no `context-snapshot.md`: read `spec.md`, `plan.md` from the artifact directory, then `.prizmkit/prizm-docs/root.prizm` and relevant L1/L2 docs
 3. Identify changed files from `## Implementation Log` or completed tasks in plan.md
 
-**Worktree constraint**: You are spawned with default/no worktree isolation by the orchestrator. You review the active checkout's changes — the orchestrator provides workspace context (git status, diff summary, new-file paths). Do NOT request or create `.claude/worktrees/...` tool worktrees. Do NOT re-discover or re-index the whole repository; use the orchestrator-provided context as your review scope and request only targeted file reads.
+**Active Checkout Requirement**: You must review only the active checkout provided by the orchestrator. `/prizmkit-code-review` does not support worktree review.
+
+The orchestrator must provide the expected active checkout git top-level in the workspace context. Before reviewing, verify that your current git top-level matches that expected active checkout.
+
+If you detect that you are running inside a temporary worktree, `.claude/worktrees/...`, `.prizmkit/state/worktrees/...`, a remote workspace, a copied checkout, or any checkout whose git top-level does not match the orchestrator-provided active checkout root:
+- Stop immediately.
+- Do not read or review files.
+- Do not produce normal review findings.
+- Report `WRONG_CHECKOUT`.
+- State that `/prizmkit-code-review` cannot continue because the reviewer subagent was not started in the active checkout/no-worktree mode required by this skill.
+
+Do NOT request or create `.claude/worktrees/...` tool worktrees. Do NOT re-discover or re-index the whole repository; use the orchestrator-provided context as your review scope and request only targeted file reads.
 
 **File Reading Rule**: Read ONLY files listed in the Implementation Log for diagnosis — do not explore unrelated files. Exception: during Fix Strategy Formulation, you MAY read additional files to trace impact (callers, dependents, shared patterns).
 

package/bundled/dev-pipeline/SCHEMA_ANALYSIS.md

@@ -81,8 +81,8 @@ acceptance_criteria, status
 
 **Optional fields:**
 ```
-priority, affected_feature, affected_modules, environment, critic, 
-critic_count, model
+priority, dependencies, affected_feature, affected_modules, environment, critic, 
+critic_count, model, browser_interaction
 ```
 
 | Property | Type | Enum/Pattern | Notes |
@@ -95,7 +95,8 @@ critic_count, model
 | `error_source` | object | type enum: `stack_trace, user_report, failed_test, log_pattern, monitoring_alert` | ✓ REQUIRED |
 | `verification_type` | string | `automated, manual, hybrid` | ✓ REQUIRED |
 | `acceptance_criteria` | array | N/A | minItems: 1 |
-| `status` | string | `pending, triaging, reproducing, fixing, verifying, completed, failed, needs_info, skipped` | ✓ REQUIRED; more states than Feature |
+| `status` | string | `pending, in_progress, completed, failed, skipped, needs_info` | ✓ REQUIRED; external list status only |
+| `dependencies` | array | Pattern: `^B-\d{3}$` | Optional; bug IDs that must complete first |
 | `affected_feature` | string | Pattern: `^F-\d{3}(-[A-Z])?$` | Optional; link to original feature |
 | `affected_modules` | array | N/A | Optional; module names |
 | `environment` | object | N/A | Optional; os, runtime, browser, version |
@@ -209,12 +210,11 @@ design_system, ci_pipeline
 pending, in_progress, completed, failed, skipped, split, auto_skipped
 ```
 
-**Bug Fix Status (9 values):**
+**Bug Fix Status (6 external values):**
 ```
-pending, triaging, reproducing, fixing, verifying, completed, failed, needs_info, skipped
+pending, in_progress, completed, failed, skipped, needs_info
 ```
-*Includes intermediate workflow states: triaging, reproducing, fixing, verifying, needs_info*
-*NO "split" or "auto_skipped"*
+*External bug-list status stays coarse. Fine-grained triage/reproduction/fix/verification phases belong in logs, checkpoints, and session metadata, not `bugs[].status`.*
 
 **Refactor Status (5 values):**
 ```
@@ -227,10 +227,10 @@ pending, in_progress, completed, failed, skipped
 | Schema | Dependencies | Pattern |
 |--------|--------------|---------|
 | Feature | `dependencies` (required) | `^F-\d{3}(-[A-Z])?$` - can reference sub-features |
-| Bug Fix | N/A | No `dependencies` field ❌ |
+| Bug Fix | `dependencies` (optional) | `^B-\d{3}$` - can reference prerequisite bug fixes |
 | Refactor | `dependencies` (required) | `^R-\d{3}$` - ONLY refactor IDs, no sub-IDs |
 
-**Issue:** Bug Fix schema lacks dependency tracking. Bugs cannot declare prerequisites. Feature dependencies support sub-features; Refactor dependencies do not.
+**Contract:** Bug Fix dependencies are supported as optional prerequisites. Runtime selects eligible bugs in stable list order after dependencies are completed.
 
 ### 4.5 Acceptance Criteria vs Task Lists
 
@@ -493,7 +493,7 @@ Located in `/dev-pipeline/templates/`:
 
 ### Status Enums
 - **Feature**: `[pending, in_progress, completed, failed, skipped, split, auto_skipped]` (7 values)
-- **Bug Fix**: `[pending, triaging, reproducing, fixing, verifying, completed, failed, needs_info, skipped]` (9 values)
+- **Bug Fix**: `[pending, in_progress, completed, failed, skipped, needs_info]` (6 external values)
 - **Refactor**: `[pending, in_progress, completed, failed, skipped]` (5 values)
 
 ### Complexity/Estimated Complexity Enums

package/bundled/dev-pipeline/prizmkit_runtime/interoperability.py

@@ -33,6 +33,7 @@ UTILITY_ENTRYPOINTS = {
 
 UTILITY_LIBRARY_ONLY = {
     "continuation.py": "shared continuation helpers imported by prompt generators",
+    "prompt_framework.py": "shared prompt rendering and checkpoint helpers imported by prompt generators",
     "utils.py": "shared utility helpers imported by runtime scripts",
 }
 

package/bundled/dev-pipeline/scripts/generate-bootstrap-prompt.py

@@ -29,6 +29,7 @@ import sys
 
 from utils import enrich_global_context, helper_replacements, load_json_file, resolve_prompt_platform, setup_logging
 from continuation import add_continuation_args, append_continuation_handoff, is_continuation
+from prompt_framework import browser_enabled_from_item, detect_dev_server_port
 
 
 DEFAULT_MAX_RETRIES = 3
@@ -693,10 +694,13 @@ SECTION_TO_SKILL = {
     "phase-commit": None,  # special: split into retrospective + committer
 }
 
-# phase-commit is split into two steps
+# phase-commit is split into durable checkpoint steps. CLI flags are not
+# artifacts; only real files/globs belong in required_artifacts.
 _COMMIT_STEPS = [
     ("prizmkit-retrospective", "Retrospective", []),
-    ("prizmkit-committer", "Commit", ["--headless"]),
+    ("prizmkit-committer", "Commit", []),
+    ("completion-summary", "Completion Summary",
+     [".prizmkit/specs/{slug}/completion-summary.json"]),
 ]
 
 
@@ -1295,7 +1299,6 @@ def load_section(sections_dir, name):
 
 ACTIVE_AGENT_PROMPTS = {
     "critic-plan-challenge.md": "{{AGENT_PROMPT_CRITIC_PLAN_CHALLENGE}}",
-    "reviewer-review.md": "{{AGENT_PROMPT_REVIEWER_REVIEW}}",
 }
 
 
@@ -1834,48 +1837,16 @@ def build_replacements(args, feature, features, global_context, script_dir):
         )
         critic_enabled = False
 
-    # Browser interaction - extract from feature if present
-    browser_interaction = feature.get("browser_interaction")
-    browser_enabled = False
-    browser_verify_steps = ""
-    browser_tool = "auto"  # default: AI chooses at runtime
+    # Browser verification defaults to a mandatory attempt. It is disabled only
+    # by BROWSER_VERIFY=false or browser_interaction.enabled=false.
+    browser_enabled, browser_tool, browser_verify_steps, browser_blocking = browser_enabled_from_item(feature)
 
-    browser_verify_env = os.environ.get("BROWSER_VERIFY", "").lower()
-    if browser_verify_env == "false":
-        browser_interaction = None
-
-    if browser_interaction and isinstance(browser_interaction, bool):
-        # Simple boolean: browser verification enabled, no specific goals
-        browser_enabled = True
+    if browser_tool not in ("playwright-cli", "opencli", "auto"):
+        LOGGER.warning(
+            "Unknown browser_interaction.tool '%s', defaulting to 'auto'",
+            browser_tool,
+        )
         browser_tool = "auto"
-        browser_verify_steps = (
-            "   # (no specific verify goals — explore the app and "
-            "verify the feature works as expected)")
-    elif browser_interaction and isinstance(browser_interaction, dict):
-        # Extract tool preference (playwright-cli / opencli / auto)
-        browser_tool = browser_interaction.get("tool", "auto")
-        if browser_tool not in ("playwright-cli", "opencli", "auto"):
-            LOGGER.warning(
-                "Unknown browser_interaction.tool '%s', defaulting to 'auto'",
-                browser_tool,
-            )
-            browser_tool = "auto"
-
-        # browser_interaction only needs verify_steps — AI auto-detects
-        # dev server command, URL, and port from project config
-        steps = browser_interaction.get("verify_steps", [])
-        if steps:
-            browser_enabled = True
-            browser_verify_steps = "\n".join(
-                "   # Goal {}: {}".format(i + 1, step)
-                for i, step in enumerate(steps)
-            )
-        elif browser_interaction.get("url") or browser_interaction.get("enabled", True):
-            # Backward compat: old format had url/setup_command fields
-            browser_enabled = True
-            browser_verify_steps = (
-                "   # (no specific verify goals — explore the app and "
-                "verify the feature works as expected)")
 
     # Auto-detect test commands from project structure
     test_cmd = detect_test_commands(project_root)
@@ -1893,36 +1864,10 @@ def build_replacements(args, feature, features, global_context, script_dir):
     if isinstance(testing_config, dict):
         coverage_target = str(testing_config.get("coverage_target", 80))
 
-    # Detect dev server port from package.json
-    dev_port = "3000"  # Default fallback
-    try:
-        pkg_path = os.path.join(project_root, "package.json")
-        if os.path.isfile(pkg_path):
-            with open(pkg_path, "r", encoding="utf-8") as f:
-                pkg = json.load(f)
-            dev_script = pkg.get("scripts", {}).get("dev", "")
-            # Extract -p <port> from dev script
-            port_match = re.search(r"-p\s+(\d+)", dev_script)
-            if port_match:
-                dev_port = port_match.group(1)
-            else:
-                # Fallback: try NEXT_PUBLIC_SITE_URL from .env files
-                for env_file in [".env.local", ".env"]:
-                    env_path = os.path.join(project_root, env_file)
-                    if os.path.isfile(env_path):
-                        with open(env_path, "r", encoding="utf-8") as ef:
-                            for line in ef:
-                                m = re.match(
-                                    r"NEXT_PUBLIC_SITE_URL\s*=\s*.*?:([0-9]+)", line.strip()
-                                )
-                                if m:
-                                    dev_port = m.group(1)
-                                    break
-                        if dev_port != "3000":
-                            break
-    except Exception:
-        pass  # Keep default 3000 on any error
-    dev_url = f"http://localhost:{dev_port}"
+    # Detect dev server port from project config. Do not guess a default port;
+    # browser prompt sections require the agent to discover it when unknown.
+    dev_port = detect_dev_server_port(project_root)
+    dev_url = "http://localhost:{}".format(dev_port) if dev_port.isdigit() else "<UNKNOWN_DETECT_FROM_PROJECT_CONFIG>"
 
     replacements = {
         "{{RUN_ID}}": args.run_id,
@@ -1948,6 +1893,7 @@ def build_replacements(args, feature, features, global_context, script_dir):
         "{{SESSION_STATUS_PATH}}": session_status_abs,
         "{{PROJECT_ROOT}}": project_root,
         "{{FEATURE_SLUG}}": feature_slug,
+        "{{ARTIFACT_DIR}}": os.path.join(".prizmkit", "specs", feature_slug),
         "{{CHECKPOINT_PATH}}": os.path.join(
             ".prizmkit", "specs", feature_slug, "workflow-checkpoint.json",
         ),
@@ -1960,6 +1906,7 @@ def build_replacements(args, feature, features, global_context, script_dir):
         "{{HAS_PLAN}}": "true" if artifacts["has_plan"] else "false",
         "{{BROWSER_VERIFY_STEPS}}": browser_verify_steps,
         "{{BROWSER_TOOL}}": browser_tool,
+        "{{BROWSER_BLOCKING}}": "true" if browser_blocking else "false",
         "{{AC_CHECKLIST}}": format_ac_checklist(
             feature.get("acceptance_criteria", [])
         ),