prizmkit 1.1.193 → 1.1.195
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/bin/create-prizmkit.js +43 -12
- package/bundled/VERSION.json +3 -3
- package/bundled/dev-pipeline/.env.example +5 -0
- package/bundled/dev-pipeline/README.md +2 -1
- package/bundled/dev-pipeline/prizmkit_runtime/checkpoint_state.py +111 -30
- package/bundled/dev-pipeline/prizmkit_runtime/cli.py +44 -3
- package/bundled/dev-pipeline/prizmkit_runtime/commands.py +29 -9
- package/bundled/dev-pipeline/prizmkit_runtime/config.py +121 -44
- package/bundled/dev-pipeline/prizmkit_runtime/daemon.py +190 -37
- package/bundled/dev-pipeline/prizmkit_runtime/interoperability.py +1 -0
- package/bundled/dev-pipeline/prizmkit_runtime/iterate.py +2480 -0
- package/bundled/dev-pipeline/prizmkit_runtime/paths.py +3 -0
- package/bundled/dev-pipeline/prizmkit_runtime/runner_bookkeeping.py +32 -8
- package/bundled/dev-pipeline/prizmkit_runtime/runners.py +29 -12
- package/bundled/dev-pipeline/prizmkit_runtime/runtime_commit.py +13 -5
- package/bundled/dev-pipeline/prizmkit_runtime/status.py +166 -0
- package/bundled/dev-pipeline/scripts/feature_list_contract.py +964 -0
- package/bundled/dev-pipeline/scripts/generate-bootstrap-prompt.py +18 -40
- package/bundled/dev-pipeline/scripts/generate-bugfix-prompt.py +24 -19
- package/bundled/dev-pipeline/scripts/prompt_framework.py +24 -8
- package/bundled/dev-pipeline/templates/bootstrap-tier3.md +1 -63
- package/bundled/dev-pipeline/templates/bug-fix-list-schema.json +8 -6
- package/bundled/dev-pipeline/templates/bugfix-bootstrap-prompt.md +0 -10
- package/bundled/dev-pipeline/templates/feature-list-schema.json +8 -6
- package/bundled/dev-pipeline/templates/iterate/evaluate-prompt.md +97 -0
- package/bundled/dev-pipeline/templates/iterate/evaluation-schema.json +538 -0
- package/bundled/dev-pipeline/templates/iterate/headless-plan-prompt.md +66 -0
- package/bundled/dev-pipeline/templates/sections/phase-specify-plan-full.md +2 -2
- package/bundled/dev-pipeline/templates/sections/runtime-commit-handoff.md +13 -4
- package/bundled/rules/USAGE.md +15 -48
- package/bundled/rules/_rules-metadata.json +7 -14
- package/bundled/rules/general/coding-baseline.md +23 -0
- package/bundled/rules/prizm/prizm-progressive-loading.md +2 -2
- package/bundled/skills/_metadata.json +12 -42
- package/bundled/skills/app-planner/SKILL.md +2 -2
- package/bundled/skills/app-planner/references/generated-plan-review.md +2 -2
- package/bundled/skills/app-planner/references/project-state-detection.md +1 -1
- package/bundled/skills/app-planner/references/rules-configuration.md +158 -88
- package/bundled/skills/app-planner/scripts/validate-rules-configuration.py +543 -12
- package/bundled/skills/bug-planner/references/verification.md +4 -5
- package/bundled/skills/bugfix-pipeline-launcher/SKILL.md +20 -14
- package/bundled/skills/bugfix-pipeline-launcher/references/configuration.md +49 -9
- package/bundled/skills/feature-pipeline-launcher/SKILL.md +20 -14
- package/bundled/skills/feature-pipeline-launcher/references/configuration.md +49 -9
- package/bundled/skills/feature-planner/SKILL.md +3 -3
- package/bundled/skills/feature-planner/references/browser-interaction.md +9 -29
- package/bundled/skills/iterate-pipeline-launcher/SKILL.md +273 -0
- package/bundled/skills/iterate-pipeline-launcher/references/configuration.md +105 -0
- package/bundled/skills/prizmkit-code-review/SKILL.md +10 -8
- package/bundled/skills/prizmkit-code-review/references/independent-code-review.md +4 -1
- package/bundled/skills/prizmkit-code-review/references/review-report-template.md +2 -1
- package/bundled/skills/prizmkit-code-review/scripts/render_review_report.py +12 -8
- package/bundled/skills/prizmkit-implement/SKILL.md +2 -2
- package/bundled/skills/prizmkit-init/SKILL.md +10 -10
- package/bundled/skills/prizmkit-init/references/brownfield-deep-init.md +81 -0
- package/bundled/skills/prizmkit-plan/SKILL.md +2 -1
- package/bundled/skills/prizmkit-plan/assets/plan-template.md +2 -0
- package/bundled/skills/prizmkit-prizm-docs/SKILL.md +8 -4
- package/bundled/skills/prizmkit-prizm-docs/assets/prizm-docs-format.md +8 -7
- package/bundled/skills/prizmkit-prizm-docs/references/op-init.md +33 -16
- package/bundled/skills/prizmkit-prizm-docs/references/op-validate.md +1 -1
- package/bundled/skills/prizmkit-retrospective/SKILL.md +29 -12
- package/bundled/skills/prizmkit-retrospective/references/retrospective-result-schema.json +126 -2
- package/bundled/skills/prizmkit-retrospective/references/rule-evolution-steps.md +86 -0
- package/bundled/skills/prizmkit-test/SKILL.md +2 -1
- package/bundled/skills/prizmkit-workflow/SKILL.md +8 -0
- package/bundled/skills/prizmkit-workflow/references/cold-start-rules.md +84 -0
- package/bundled/templates/project-memory-template.md +3 -3
- package/package.json +1 -1
- package/src/clean.js +2 -3
- package/src/config.js +52 -39
- package/src/index.js +29 -111
- package/src/prompts.js +20 -87
- package/src/runtime-passthrough.js +324 -0
- package/src/scaffold.js +41 -294
- package/src/upgrade.js +7 -39
- package/bundled/dev-pipeline/templates/sections/phase-browser-verification-auto.md +0 -127
- package/bundled/dev-pipeline/templates/sections/phase-browser-verification-opencli.md +0 -124
- package/src/external-skills.js +0 -103
|
@@ -514,7 +514,7 @@ def process_conditional_blocks(content, resume_phase):
|
|
|
514
514
|
|
|
515
515
|
|
|
516
516
|
def process_template_blocks(content, init_done, browser_interaction=False,
|
|
517
|
-
browser_tool="
|
|
517
|
+
browser_tool="playwright-cli"):
|
|
518
518
|
"""Process init and browser blocks in an explicit custom template."""
|
|
519
519
|
# Init blocks
|
|
520
520
|
if init_done:
|
|
@@ -544,28 +544,17 @@ def process_template_blocks(content, init_done, browser_interaction=False,
|
|
|
544
544
|
pattern = re.escape(browser_open) + r".*?" + re.escape(browser_close) + r"\n?"
|
|
545
545
|
content = re.sub(pattern, "", content, flags=re.DOTALL)
|
|
546
546
|
|
|
547
|
-
#
|
|
548
|
-
|
|
549
|
-
|
|
550
|
-
|
|
551
|
-
"
|
|
552
|
-
|
|
553
|
-
"
|
|
554
|
-
|
|
555
|
-
|
|
556
|
-
|
|
557
|
-
|
|
558
|
-
tool_close = "{{{{END_IF_BROWSER_TOOL_{}}}}}".format(variant)
|
|
559
|
-
if variant == active_variant and browser_interaction:
|
|
560
|
-
# Keep content, remove tags
|
|
561
|
-
content = content.replace(tool_open + "\n", "")
|
|
562
|
-
content = content.replace(tool_open, "")
|
|
563
|
-
content = content.replace(tool_close + "\n", "")
|
|
564
|
-
content = content.replace(tool_close, "")
|
|
565
|
-
else:
|
|
566
|
-
# Remove entire block
|
|
567
|
-
pat = re.escape(tool_open) + r".*?" + re.escape(tool_close) + r"\n?"
|
|
568
|
-
content = re.sub(pat, "", content, flags=re.DOTALL)
|
|
547
|
+
# Unwrap optional legacy PLAYWRIGHT conditional block when browser verification is enabled
|
|
548
|
+
tool_open = "{{IF_BROWSER_TOOL_PLAYWRIGHT}}"
|
|
549
|
+
tool_close = "{{END_IF_BROWSER_TOOL_PLAYWRIGHT}}"
|
|
550
|
+
if browser_interaction:
|
|
551
|
+
content = content.replace(tool_open + "\n", "")
|
|
552
|
+
content = content.replace(tool_open, "")
|
|
553
|
+
content = content.replace(tool_close + "\n", "")
|
|
554
|
+
content = content.replace(tool_close, "")
|
|
555
|
+
else:
|
|
556
|
+
pat = re.escape(tool_open) + r".*?" + re.escape(tool_close) + r"\n?"
|
|
557
|
+
content = re.sub(pat, "", content, flags=re.DOTALL)
|
|
569
558
|
|
|
570
559
|
return content
|
|
571
560
|
|
|
@@ -806,7 +795,7 @@ def _canonical_reminders():
|
|
|
806
795
|
|
|
807
796
|
|
|
808
797
|
def assemble_sections(sections_dir, init_done, browser_enabled,
|
|
809
|
-
browser_tool="
|
|
798
|
+
browser_tool="playwright-cli"):
|
|
810
799
|
"""Assemble the canonical prompt sections and configured optional gates."""
|
|
811
800
|
sections = []
|
|
812
801
|
|
|
@@ -861,14 +850,8 @@ def assemble_sections(sections_dir, init_done, browser_enabled,
|
|
|
861
850
|
load_section(sections_dir, "phase-review-full.md")))
|
|
862
851
|
|
|
863
852
|
if browser_enabled:
|
|
864
|
-
if browser_tool == "opencli":
|
|
865
|
-
browser_section_file = "phase-browser-verification-opencli.md"
|
|
866
|
-
elif browser_tool == "playwright-cli":
|
|
867
|
-
browser_section_file = "phase-browser-verification.md"
|
|
868
|
-
else:
|
|
869
|
-
browser_section_file = "phase-browser-verification-auto.md"
|
|
870
853
|
sections.append(("phase-browser",
|
|
871
|
-
load_section(sections_dir,
|
|
854
|
+
load_section(sections_dir, "phase-browser-verification.md")))
|
|
872
855
|
|
|
873
856
|
sections.append(("phase-prizmkit-test",
|
|
874
857
|
load_section(sections_dir, "phase-prizmkit-test.md")))
|
|
@@ -1001,14 +984,9 @@ def build_replacements(args, feature, features, global_context, script_dir):
|
|
|
1001
984
|
|
|
1002
985
|
# Browser verification is opt-in through a browser_interaction object and
|
|
1003
986
|
# can always be disabled globally with BROWSER_VERIFY=false.
|
|
1004
|
-
browser_enabled, browser_tool, browser_verify_steps, browser_blocking = browser_enabled_from_item(
|
|
1005
|
-
|
|
1006
|
-
|
|
1007
|
-
LOGGER.warning(
|
|
1008
|
-
"Unknown browser_interaction.tool '%s', defaulting to 'auto'",
|
|
1009
|
-
browser_tool,
|
|
1010
|
-
)
|
|
1011
|
-
browser_tool = "auto"
|
|
987
|
+
browser_enabled, browser_tool, browser_verify_steps, browser_blocking = browser_enabled_from_item(
|
|
988
|
+
feature, logger=LOGGER,
|
|
989
|
+
)
|
|
1012
990
|
|
|
1013
991
|
# Auto-detect test commands from project structure
|
|
1014
992
|
test_cmd = detect_test_commands(project_root)
|
|
@@ -1086,7 +1064,7 @@ def build_replacements(args, feature, features, global_context, script_dir):
|
|
|
1086
1064
|
|
|
1087
1065
|
|
|
1088
1066
|
def render_template(template_content, replacements, resume_phase,
|
|
1089
|
-
browser_enabled=False, browser_tool="
|
|
1067
|
+
browser_enabled=False, browser_tool="playwright-cli"):
|
|
1090
1068
|
"""Render the template by processing conditionals and replacing placeholders."""
|
|
1091
1069
|
# Step 1: Process fresh_start/resume conditional blocks
|
|
1092
1070
|
content = process_conditional_blocks(template_content, resume_phase)
|
|
@@ -307,7 +307,9 @@ def build_replacements(args, bug, global_context, script_dir):
|
|
|
307
307
|
fix_scope = affected_modules[0] if affected_modules else (bug.get("title", "unknown").split()[0].lower() if bug.get("title") else "unknown")
|
|
308
308
|
verification_type = bug.get("verification_type", "automated")
|
|
309
309
|
|
|
310
|
-
browser_enabled, browser_tool, browser_verify_steps, browser_blocking = browser_enabled_from_item(
|
|
310
|
+
browser_enabled, browser_tool, browser_verify_steps, browser_blocking = browser_enabled_from_item(
|
|
311
|
+
bug, logger=LOGGER,
|
|
312
|
+
)
|
|
311
313
|
dev_port = detect_dev_server_port(project_root)
|
|
312
314
|
dev_url = "http://localhost:{}".format(dev_port) if dev_port.isdigit() else "<UNKNOWN_DETECT_FROM_PROJECT_CONFIG>"
|
|
313
315
|
|
|
@@ -355,7 +357,7 @@ def build_replacements(args, bug, global_context, script_dir):
|
|
|
355
357
|
return replacements
|
|
356
358
|
|
|
357
359
|
|
|
358
|
-
def process_conditional_blocks(content, bug):
|
|
360
|
+
def process_conditional_blocks(content, bug, browser_enabled=None):
|
|
359
361
|
"""Handle legacy conditional blocks based on verification_type and browser_interaction."""
|
|
360
362
|
vtype = bug.get("verification_type", "automated")
|
|
361
363
|
is_manual_or_hybrid = vtype in ("manual", "hybrid")
|
|
@@ -367,7 +369,8 @@ def process_conditional_blocks(content, bug):
|
|
|
367
369
|
else:
|
|
368
370
|
content = re.sub(r"\{\{IF_VERIFICATION_MANUAL_OR_HYBRID\}\}.*?\{\{END_IF_VERIFICATION_MANUAL_OR_HYBRID\}\}\n?", "", content, flags=re.DOTALL)
|
|
369
371
|
|
|
370
|
-
browser_enabled
|
|
372
|
+
if browser_enabled is None:
|
|
373
|
+
browser_enabled, _browser_tool, _steps, _blocking = browser_enabled_from_item(bug, logger=LOGGER)
|
|
371
374
|
browser_open = "{{IF_BROWSER_INTERACTION}}"
|
|
372
375
|
browser_close = "{{END_IF_BROWSER_INTERACTION}}"
|
|
373
376
|
if browser_enabled:
|
|
@@ -376,21 +379,27 @@ def process_conditional_blocks(content, bug):
|
|
|
376
379
|
else:
|
|
377
380
|
content = re.sub(re.escape(browser_open) + r".*?" + re.escape(browser_close) + r"\n?", "", content, flags=re.DOTALL)
|
|
378
381
|
|
|
379
|
-
|
|
380
|
-
|
|
381
|
-
|
|
382
|
-
|
|
383
|
-
|
|
384
|
-
|
|
385
|
-
|
|
386
|
-
else:
|
|
387
|
-
content = re.sub(re.escape(tool_open) + r".*?" + re.escape(tool_close) + r"\n?", "", content, flags=re.DOTALL)
|
|
382
|
+
tool_open = "{{IF_BROWSER_TOOL_PLAYWRIGHT}}"
|
|
383
|
+
tool_close = "{{END_IF_BROWSER_TOOL_PLAYWRIGHT}}"
|
|
384
|
+
if browser_enabled:
|
|
385
|
+
content = content.replace(tool_open + "\n", "").replace(tool_open, "")
|
|
386
|
+
content = content.replace(tool_close + "\n", "").replace(tool_close, "")
|
|
387
|
+
else:
|
|
388
|
+
content = re.sub(re.escape(tool_open) + r".*?" + re.escape(tool_close) + r"\n?", "", content, flags=re.DOTALL)
|
|
388
389
|
return content
|
|
389
390
|
|
|
390
391
|
|
|
391
392
|
def render_template(template_content, replacements, bug):
|
|
392
393
|
"""Render the legacy template by processing conditionals and placeholders."""
|
|
393
|
-
|
|
394
|
+
browser_enabled = (
|
|
395
|
+
replacements.get("{{BROWSER_ENABLED}}") == "true"
|
|
396
|
+
if "{{BROWSER_ENABLED}}" in replacements
|
|
397
|
+
else None
|
|
398
|
+
)
|
|
399
|
+
return replace_placeholders(
|
|
400
|
+
process_conditional_blocks(template_content, bug, browser_enabled=browser_enabled),
|
|
401
|
+
replacements,
|
|
402
|
+
)
|
|
394
403
|
|
|
395
404
|
|
|
396
405
|
def _bugfix_header():
|
|
@@ -401,7 +410,7 @@ def _bugfix_header():
|
|
|
401
410
|
)
|
|
402
411
|
|
|
403
412
|
|
|
404
|
-
def assemble_bugfix_sections(sections_dir, browser_enabled, manual_gate, browser_tool="
|
|
413
|
+
def assemble_bugfix_sections(sections_dir, browser_enabled, manual_gate, browser_tool="playwright-cli"):
|
|
405
414
|
sections = [
|
|
406
415
|
("header", _bugfix_header()),
|
|
407
416
|
("bugfix-session-context", load_section(sections_dir, "bugfix-session-context.md")),
|
|
@@ -419,11 +428,7 @@ def assemble_bugfix_sections(sections_dir, browser_enabled, manual_gate, browser
|
|
|
419
428
|
("bugfix-phase-review", load_section(sections_dir, "bugfix-phase-review.md")),
|
|
420
429
|
])
|
|
421
430
|
if browser_enabled:
|
|
422
|
-
|
|
423
|
-
"playwright-cli": "phase-browser-verification.md",
|
|
424
|
-
"opencli": "phase-browser-verification-opencli.md",
|
|
425
|
-
}.get(browser_tool, "phase-browser-verification-auto.md")
|
|
426
|
-
sections.append(("phase-browser", load_section(sections_dir, browser_section_file)))
|
|
431
|
+
sections.append(("phase-browser", load_section(sections_dir, "phase-browser-verification.md")))
|
|
427
432
|
if manual_gate:
|
|
428
433
|
sections.append(("bugfix-manual-gate", load_section(sections_dir, "bugfix-phase-manual-verification.md")))
|
|
429
434
|
sections.extend([
|
|
@@ -6,6 +6,7 @@ so feature and bugfix prompts do not drift.
|
|
|
6
6
|
"""
|
|
7
7
|
|
|
8
8
|
import glob
|
|
9
|
+
import logging
|
|
9
10
|
import os
|
|
10
11
|
import re
|
|
11
12
|
import sys
|
|
@@ -24,6 +25,7 @@ from prizmkit_runtime.test_result import valid_test_artifact_pair # noqa: E402
|
|
|
24
25
|
|
|
25
26
|
|
|
26
27
|
MAX_OUTER_REPAIR_ROUNDS = 3
|
|
28
|
+
_LOGGER = logging.getLogger(__name__)
|
|
27
29
|
|
|
28
30
|
|
|
29
31
|
def route_pipeline_repair(stage_result, repair_scope=None, repair_round=0, *, production_changed=False):
|
|
@@ -548,26 +550,40 @@ def detect_dev_server_port(project_root):
|
|
|
548
550
|
return unknown
|
|
549
551
|
|
|
550
552
|
|
|
551
|
-
def browser_enabled_from_item(item):
|
|
552
|
-
"""Return browser enabled/tool/steps with explicit opt-in semantics.
|
|
553
|
+
def browser_enabled_from_item(item, logger=None):
|
|
554
|
+
"""Return browser enabled/tool/steps/blocking with explicit opt-in semantics.
|
|
555
|
+
|
|
556
|
+
Legacy ``browser_interaction.tool`` values (``"auto"`` or ``"opencli"``) are
|
|
557
|
+
normalized to ``"playwright-cli"`` with a logged deprecation warning so
|
|
558
|
+
pre-existing task lists still execute cleanly.
|
|
559
|
+
"""
|
|
553
560
|
browser_interaction = item.get("browser_interaction") if isinstance(item, dict) else None
|
|
554
561
|
env_value = os.environ.get("BROWSER_VERIFY", "").lower()
|
|
555
562
|
if env_value == "false":
|
|
556
|
-
return False, "
|
|
563
|
+
return False, "playwright-cli", "", False
|
|
557
564
|
|
|
558
565
|
enabled = False
|
|
559
|
-
tool = "
|
|
566
|
+
tool = "playwright-cli"
|
|
560
567
|
blocking = False
|
|
561
568
|
steps = []
|
|
569
|
+
active_logger = logger or _LOGGER
|
|
562
570
|
|
|
563
571
|
if isinstance(browser_interaction, dict):
|
|
564
572
|
enabled = True
|
|
565
|
-
|
|
573
|
+
raw_tool = browser_interaction.get("tool")
|
|
566
574
|
blocking = bool(browser_interaction.get("blocking", False))
|
|
567
575
|
steps = browser_interaction.get("verify_steps", []) or []
|
|
568
|
-
|
|
569
|
-
|
|
570
|
-
|
|
576
|
+
if raw_tool in ("auto", "opencli"):
|
|
577
|
+
active_logger.warning(
|
|
578
|
+
"Deprecated browser_interaction.tool '%s' is no longer supported; "
|
|
579
|
+
"normalizing to 'playwright-cli'",
|
|
580
|
+
raw_tool,
|
|
581
|
+
)
|
|
582
|
+
elif raw_tool is not None and raw_tool != "playwright-cli":
|
|
583
|
+
active_logger.warning(
|
|
584
|
+
"Unknown browser_interaction.tool '%s'; normalizing to 'playwright-cli'",
|
|
585
|
+
raw_tool,
|
|
586
|
+
)
|
|
571
587
|
|
|
572
588
|
if steps:
|
|
573
589
|
rendered_steps = "\n".join(
|
|
@@ -247,7 +247,6 @@ You MUST execute this phase. Do NOT skip it.
|
|
|
247
247
|
|
|
248
248
|
**Browser Tool**: {{BROWSER_TOOL}}
|
|
249
249
|
|
|
250
|
-
{{IF_BROWSER_TOOL_PLAYWRIGHT}}
|
|
251
250
|
**Using: playwright-cli**
|
|
252
251
|
|
|
253
252
|
**CRITICAL CONSTRAINT — playwright-cli ONLY, NO Playwright MCP**:
|
|
@@ -311,74 +310,13 @@ Construct your verification workflow based on: (1) the playwright-cli skill docu
|
|
|
311
310
|
1. Close the playwright-cli browser: `playwright-cli close`
|
|
312
311
|
2. Kill the dev server process: `{{RUNTIME_HELPER_CMD}} process cleanup-pid <pid-from-.prizmkit/state/browser-dev-server.pid>`
|
|
313
312
|
3. Verify port is released: `{{RUNTIME_HELPER_CMD}} port check {{DEV_PORT}}`
|
|
314
|
-
{{END_IF_BROWSER_TOOL_PLAYWRIGHT}}
|
|
315
|
-
{{IF_BROWSER_TOOL_OPENCLI}}
|
|
316
|
-
**Using: opencli** (reuses Chrome logged-in sessions)
|
|
317
|
-
|
|
318
|
-
**CRITICAL CONSTRAINT — opencli browser ONLY**:
|
|
319
|
-
- You MUST use `opencli browser` for ALL browser interactions in this phase
|
|
320
|
-
- All browser actions go through `opencli browser <command>` via the shell/terminal command tool
|
|
321
|
-
|
|
322
|
-
**Step 0 — OpenCLI Readiness Check (BLOCKING)**:
|
|
323
|
-
|
|
324
|
-
0a. Check if `opencli` is installed:
|
|
325
|
-
```bash
|
|
326
|
-
{{RUNTIME_HELPER_CMD}} executable version opencli --arg=--version
|
|
327
|
-
```
|
|
328
|
-
If `NOT_INSTALLED`: `npm install -g @jackwener/opencli@latest`. If installation fails, log `## Browser Verification: SKIPPED — opencli installation failed` and proceed.
|
|
329
|
-
|
|
330
|
-
0b. Verify Browser Bridge: `opencli doctor`. If fails, log skip and proceed.
|
|
331
|
-
|
|
332
|
-
0c. Learn usage: `opencli browser --help`
|
|
333
|
-
|
|
334
|
-
**Step 1 — Start Dev Server**:
|
|
335
|
-
1. Determine `DEV_PORT` from the pipeline value (`{{DEV_PORT}}`) or project config; do not guess.
|
|
336
|
-
2. Verify port available: `{{RUNTIME_HELPER_CMD}} port check <DEV_PORT>`
|
|
337
|
-
3. Start server: `{{RUNTIME_HELPER_CMD}} process start --pid-file .prizmkit/state/browser-dev-server.pid -- <start-command tokens>`
|
|
338
|
-
4. Wait for ready: `{{RUNTIME_HELPER_CMD}} web wait-ready --url http://localhost:<DEV_PORT> --timeout 30 --interval 2`
|
|
339
|
-
5. Open: `opencli browser open http://localhost:<DEV_PORT>`; then inspect: `opencli browser state`
|
|
340
|
-
|
|
341
|
-
**Step 2 — Verification**:
|
|
342
|
-
|
|
343
|
-
Use `opencli browser state` to discover elements with `[N]` indices, then verify:
|
|
344
|
-
{{BROWSER_VERIFY_STEPS}}
|
|
345
|
-
|
|
346
|
-
Run page-changing commands sequentially, then run `opencli browser state` to refresh indices.
|
|
347
|
-
|
|
348
|
-
**Step 3 — Cleanup**:
|
|
349
|
-
1. `opencli browser close`
|
|
350
|
-
2. `{{RUNTIME_HELPER_CMD}} process cleanup-pid <pid-from-.prizmkit/state/browser-dev-server.pid>`
|
|
351
|
-
3. `{{RUNTIME_HELPER_CMD}} port check {{DEV_PORT}}`
|
|
352
|
-
{{END_IF_BROWSER_TOOL_OPENCLI}}
|
|
353
|
-
{{IF_BROWSER_TOOL_AUTO}}
|
|
354
|
-
**Tool Selection**: Choose the best browser tool at runtime.
|
|
355
|
-
|
|
356
|
-
**Step 0 — Detect available tools**:
|
|
357
|
-
```bash
|
|
358
|
-
{{RUNTIME_HELPER_CMD}} executable version playwright-cli --arg=--version
|
|
359
|
-
{{RUNTIME_HELPER_CMD}} executable version opencli --arg=--version
|
|
360
|
-
```
|
|
361
|
-
If opencli is installed, run `opencli doctor`. If it fails, mark OpenCLI unusable and choose playwright-cli or skip browser verification.
|
|
362
|
-
|
|
363
|
-
**Decision table**:
|
|
364
|
-
| Condition | Tool |
|
|
365
|
-
|-----------|------|
|
|
366
|
-
| Only playwright-cli available | playwright-cli |
|
|
367
|
-
| Only opencli available (doctor passes) | opencli |
|
|
368
|
-
| Both — local dev server, forms, components | playwright-cli |
|
|
369
|
-
| Both — needs real login state (OAuth/SSO) | opencli |
|
|
370
|
-
| Both — third-party integration verification | opencli |
|
|
371
|
-
| Neither available | Install playwright-cli as default |
|
|
372
|
-
|
|
373
|
-
Then follow the corresponding tool's workflow above (Steps 1-3).
|
|
374
|
-
{{END_IF_BROWSER_TOOL_AUTO}}
|
|
375
313
|
|
|
376
314
|
**Step 4 — Reporting**:
|
|
377
315
|
|
|
378
316
|
Append results to `context-snapshot.md`:
|
|
379
317
|
```
|
|
380
318
|
## Browser Verification
|
|
381
|
-
Tool:
|
|
319
|
+
Tool: playwright-cli
|
|
382
320
|
URL: http://localhost:{{DEV_PORT}}
|
|
383
321
|
Dev Server Command: <actual command used>
|
|
384
322
|
Tool version: <version>
|
|
@@ -202,17 +202,19 @@
|
|
|
202
202
|
},
|
|
203
203
|
"browser_interaction": {
|
|
204
204
|
"type": "object",
|
|
205
|
-
"description": "Browser verification config for bugs reproducible via UI
|
|
205
|
+
"description": "Browser verification config for bugs reproducible via UI using playwright-cli. AI auto-detects dev server command, URL, and port from project config at runtime.",
|
|
206
206
|
"properties": {
|
|
207
207
|
"tool": {
|
|
208
208
|
"type": "string",
|
|
209
209
|
"enum": [
|
|
210
|
-
"playwright-cli"
|
|
211
|
-
"opencli",
|
|
212
|
-
"auto"
|
|
210
|
+
"playwright-cli"
|
|
213
211
|
],
|
|
214
|
-
"default": "
|
|
215
|
-
"description": "Browser tool to use.
|
|
212
|
+
"default": "playwright-cli",
|
|
213
|
+
"description": "Browser tool to use. Always uses 'playwright-cli' for local dev server verification in an isolated browser."
|
|
214
|
+
},
|
|
215
|
+
"blocking": {
|
|
216
|
+
"type": "boolean",
|
|
217
|
+
"description": "Whether browser verification failure blocks commit. Defaults to false when omitted."
|
|
216
218
|
},
|
|
217
219
|
"verify_steps": {
|
|
218
220
|
"type": "array",
|
|
@@ -85,17 +85,7 @@ You are the **bug fix session agent**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}".
|
|
|
85
85
|
|
|
86
86
|
The bug may be reproducible via the UI. Use this single browser protocol for planning, implementation, review, and final reporting:
|
|
87
87
|
|
|
88
|
-
{{IF_BROWSER_TOOL_AUTO}}
|
|
89
|
-
- **Browser Tool**: Auto-select at runtime based on error type and dev server configuration
|
|
90
|
-
{{END_IF_BROWSER_TOOL_AUTO}}
|
|
91
|
-
|
|
92
|
-
{{IF_BROWSER_TOOL_PLAYWRIGHT}}
|
|
93
88
|
- **Browser Tool**: playwright-cli (local isolated browser against dev server)
|
|
94
|
-
{{END_IF_BROWSER_TOOL_PLAYWRIGHT}}
|
|
95
|
-
|
|
96
|
-
{{IF_BROWSER_TOOL_OPENCLI}}
|
|
97
|
-
- **Browser Tool**: opencli (Chrome session with existing login context — ideal for OAuth/third-party integrations)
|
|
98
|
-
{{END_IF_BROWSER_TOOL_OPENCLI}}
|
|
99
89
|
|
|
100
90
|
**Browser Verification Goals**:
|
|
101
91
|
{{BROWSER_VERIFY_STEPS}}
|
|
@@ -128,17 +128,19 @@
|
|
|
128
128
|
},
|
|
129
129
|
"browser_interaction": {
|
|
130
130
|
"type": "object",
|
|
131
|
-
"description": "Browser verification config for features with UI
|
|
131
|
+
"description": "Browser verification config for features with UI using playwright-cli. AI auto-detects dev server command, URL, and port from project config at runtime.",
|
|
132
132
|
"properties": {
|
|
133
133
|
"tool": {
|
|
134
134
|
"type": "string",
|
|
135
135
|
"enum": [
|
|
136
|
-
"playwright-cli"
|
|
137
|
-
"opencli",
|
|
138
|
-
"auto"
|
|
136
|
+
"playwright-cli"
|
|
139
137
|
],
|
|
140
|
-
"default": "
|
|
141
|
-
"description": "Browser tool to use.
|
|
138
|
+
"default": "playwright-cli",
|
|
139
|
+
"description": "Browser tool to use. Always uses 'playwright-cli' for local dev server verification in an isolated browser."
|
|
140
|
+
},
|
|
141
|
+
"blocking": {
|
|
142
|
+
"type": "boolean",
|
|
143
|
+
"description": "Whether browser verification failure blocks commit. Defaults to false when omitted."
|
|
142
144
|
},
|
|
143
145
|
"verify_steps": {
|
|
144
146
|
"type": "array",
|
|
@@ -0,0 +1,97 @@
|
|
|
1
|
+
# Autonomous Product Evaluation — Phase A (Read-Only)
|
|
2
|
+
|
|
3
|
+
You are evaluating the shipped product in a **fresh, non-interactive, read-only session**.
|
|
4
|
+
Your sole deliverable is one valid JSON document written to `{{OUTPUT_PATH}}` conforming strictly to `{{SCHEMA_PATH}}`.
|
|
5
|
+
|
|
6
|
+
## Hard Execution Boundaries
|
|
7
|
+
|
|
8
|
+
1. **Read-Only Repository Isolation**:
|
|
9
|
+
- Do NOT create, edit, delete, rename, stage, or commit any project source file, test file, configuration file, documentation file, or `.prizmkit/plans/feature-list.json`.
|
|
10
|
+
- The ONLY writable paths in this session are `{{OUTPUT_PATH}}` and temporary walkthrough artifacts inside `{{ROUND_DIR}}` (for example a dev-server PID file or walkthrough screenshots).
|
|
11
|
+
- Modifying any repository file outside `.prizmkit/state/` causes an immediate fail-closed `STOP_EVAL_DIRTY_WORKSPACE` abort.
|
|
12
|
+
2. **Non-Interactive Session**:
|
|
13
|
+
- Do NOT ask questions or wait for human responses.
|
|
14
|
+
- Do NOT invoke interactive planning or launcher skills.
|
|
15
|
+
3. **Evidence Honesty & Anti-Padding**:
|
|
16
|
+
- Stopping cleanly when core user journeys are already solid is a successful outcome.
|
|
17
|
+
- NEVER manufacture filler improvements, cosmetics, or low-value churn merely to keep running.
|
|
18
|
+
|
|
19
|
+
## Project Context & Focus
|
|
20
|
+
|
|
21
|
+
- **Project Root**: `{{PROJECT_ROOT}}`
|
|
22
|
+
- **Output Path**: `{{OUTPUT_PATH}}`
|
|
23
|
+
- **Evaluation Schema**: `{{SCHEMA_PATH}}`
|
|
24
|
+
- **Round Scratch Dir**: `{{ROUND_DIR}}`
|
|
25
|
+
- **Focus Scope**: {{FOCUS_SECTION}}
|
|
26
|
+
|
|
27
|
+
### Progressive Context Loading
|
|
28
|
+
|
|
29
|
+
{{PRIZM_CONTEXT_HINT}}
|
|
30
|
+
|
|
31
|
+
- Read `.prizmkit/prizm-docs/root.prizm` first when present, then load only relevant module index and detail docs needed to understand shipped user-facing flows.
|
|
32
|
+
- If `.prizmkit/plans/project-brief.md` exists, treat it as **claims of intent**: when brief claims conflict with shipped code, **shipped code wins**.
|
|
33
|
+
|
|
34
|
+
### Historical Iteration Ledger (for Gate 1 Deduplication)
|
|
35
|
+
|
|
36
|
+
{{LEDGER_SUMMARY}}
|
|
37
|
+
|
|
38
|
+
## Stage 1 (Upper Half): Evidence-Grounded Candidate Discovery
|
|
39
|
+
|
|
40
|
+
Execute these discovery steps in order:
|
|
41
|
+
|
|
42
|
+
1. **Identify Product Shape First**:
|
|
43
|
+
- Classify the shipped product into 1 or 2 shapes (`product_shapes`): `web_saas`, `cli_devtool`, `mobile`, `api_sdk`, or `internal_ops` (supporting dual shapes such as `["web_saas", "api_sdk"]`).
|
|
44
|
+
2. **Walk the Codebase as a User-Facing Artifact**:
|
|
45
|
+
- Trace the real shipped user experience across routes and navigation, screen components and empty/loading states, primary CTAs and their actual handlers, forms and validation paths, API error codes and user-facing messages, auth/plan/quota gates, and core data-model nouns.
|
|
46
|
+
- Strictly **banned**:
|
|
47
|
+
- Do NOT invent one feature per code folder or module.
|
|
48
|
+
- Do NOT copy generic competitor feature checklists.
|
|
49
|
+
- Do NOT turn unchecked items from `project-brief.md` directly into tasks without current code or user-journey pain evidence.
|
|
50
|
+
3. **Optional Live Walkthrough Upgrade (`playwright-cli` Only)**:
|
|
51
|
+
- For runnable web/UI targets where a safe local dev server or configured local URL is available, optionally upgrade key findings from `inference` to first-class `fact` evidence via `playwright-cli` (never use Playwright MCP tools):
|
|
52
|
+
- Check availability: `{{RUNTIME_HELPER_CMD}} executable version playwright-cli --arg=--version`
|
|
53
|
+
- Detect the project's actual dev server start command and port from project config without hardcoding ports.
|
|
54
|
+
- Check port readiness: `{{RUNTIME_HELPER_CMD}} port check <PORT>`
|
|
55
|
+
- Start server with PID tracking inside `{{ROUND_DIR}}`: `{{RUNTIME_HELPER_CMD}} process start --pid-file {{ROUND_DIR}}/eval-dev-server.pid -- <start-command>`
|
|
56
|
+
- Wait until ready: `{{RUNTIME_HELPER_CMD}} web wait-ready --url http://localhost:<PORT> --timeout 30 --interval 2`
|
|
57
|
+
- Inspect real UI flows via `playwright-cli open`, `playwright-cli snapshot`, and interactive verification steps.
|
|
58
|
+
- **Mandatory Cleanup** (even if walkthrough fails): run `playwright-cli close`, then `{{RUNTIME_HELPER_CMD}} process cleanup-pid <pid-from-eval-dev-server.pid>`, then confirm port release with `{{RUNTIME_HELPER_CMD}} port check <PORT>`.
|
|
59
|
+
- Set `evidence_mode: "live_walkthrough"`, `walkthrough_notes.target_attempted: true`, and `walkthrough_notes.server_cleanup_confirmed: true` only when live walkthrough succeeded and cleanup completed cleanly.
|
|
60
|
+
- If no runnable target or browser tool is safely available, do NOT fabricate walkthrough observations: evaluate honestly from source/runtime evidence and set `evidence_mode: "source_only"`.
|
|
61
|
+
4. **Apply the Six High-Signal Pain Lenses**:
|
|
62
|
+
- `stall`: user gets stuck with no clear next action, missing prerequisite feedback, or dead-end flow.
|
|
63
|
+
- `hollow_success`: UI/CLI reports success while data was not persisted, action silently no-oped, or result disappeared.
|
|
64
|
+
- `trust_and_control`: destructive/irreversible actions lack confirmation/undo, silent failures hide state, or permissions/boundaries are unclear.
|
|
65
|
+
- `power_and_limits`: core workflows break on realistic scale, pagination, filtering, export, or error recovery boundaries.
|
|
66
|
+
- `failure`: concrete runtime error paths, unhandled invalid input, broken handlers, or crashing core journeys.
|
|
67
|
+
- `second_use`: returning-user friction ("Second use / Come back later": state loss across reloads, missing resume/history, broken repeat workflows).
|
|
68
|
+
5. **Isolate Divergent Wishes**:
|
|
69
|
+
- Classify exploratory ideas under `adjacent_wish`, `seeing_others`, `time_and_ritual`, or `stretch_idea`.
|
|
70
|
+
- Divergent wishes MUST NEVER enter `approved_candidates`. Route them to `requires_user_confirm` (only if high strategic value warrants user choice) or `rejected_candidates`.
|
|
71
|
+
6. **Assign Explicit Three-Tier Evidence Labels**:
|
|
72
|
+
- `fact`: directly verified from shipped code, failing execution, or live walkthrough observation (cite exact file paths/symbols or observed walkthrough output in `evidence`).
|
|
73
|
+
- `inference`: plausible gap inferred indirectly without direct reproduction.
|
|
74
|
+
- `taste`: subjective polish, aesthetic preference, or product-direction opinion.
|
|
75
|
+
|
|
76
|
+
## Stage 2 (Lower Half): Four Mandatory Convergence & Stop Gates
|
|
77
|
+
|
|
78
|
+
Evaluate every discovered candidate through all four gates and record `gate_results`:
|
|
79
|
+
|
|
80
|
+
- **Gate 1 — Scope Alignment & Historical Dedupe (`gate1_scope_dedupe`)**:
|
|
81
|
+
- Verify alignment with the shipped product's core purpose, brief scope, and active focus.
|
|
82
|
+
- Reject duplicates of completed work, already-rejected candidates, or previously deferred items from the historical ledger unless new factual breakage emerged.
|
|
83
|
+
- **Gate 2 — Fact-Evidence Admission (`gate2_fact_admission`)**:
|
|
84
|
+
- Autonomous implementation admits ONLY `fact`-backed core loop breaks and real user-visible pain from the 6 high-signal pain lenses.
|
|
85
|
+
- Reject pure `taste`, unverified `inference`, and user-invisible internal refactors/cleanups.
|
|
86
|
+
- **Gate 3 — Blast-Radius Escalation (`gate3_blast_radius`)**:
|
|
87
|
+
- Flag high-risk changes using `blast_radius_flags`: `schema_migration`, `heavy_dependency`, `paid_external_api`, `breaking_contract`, `major_ia_redesign`, `over_3_features`.
|
|
88
|
+
- Any candidate with `blast_radius: "high"`, any non-empty `blast_radius_flags`, `evidence_tier: "taste"`, or a divergent-wish lens MUST NOT be marked `auto_safe` or placed in `approved_candidates`; escalate worthwhile user choices to `requires_user_confirm`.
|
|
89
|
+
- **Gate 4 — Final Verdict (`verdict`)**:
|
|
90
|
+
- `CONTINUE_WITH_CANDIDATES`: 1 to 3 contract-bounded, `fact`-backed, `auto_safe` high-signal pain candidates in `approved_candidates`.
|
|
91
|
+
- `PAUSE_FOR_USER_CONFIRM`: 0 `approved_candidates`, and at least 1 valuable high-blast-radius or `taste` proposal in `requires_user_confirm` needing user sign-off before coding.
|
|
92
|
+
- `STOP_GOAL_REACHED`: 0 `approved_candidates`; core journeys are solid and verified goals are met.
|
|
93
|
+
- `STOP_NO_HIGH_VALUE`: 0 `approved_candidates`; only marginal tweaks or out-of-scope polish remain.
|
|
94
|
+
|
|
95
|
+
## Output Requirement
|
|
96
|
+
|
|
97
|
+
Write valid JSON matching `{{SCHEMA_PATH}}` (`schema_version: "prizmkit-iterate-evaluation-v1"`) to `{{OUTPUT_PATH}}` and stop.
|