prizmkit 1.1.162 → 1.1.165
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 +4 -4
- package/bundled/VERSION.json +3 -3
- package/bundled/adapters/cursor/assets/prizmkit-hook.cjs +65 -0
- package/bundled/adapters/cursor/hooks-adapter.js +139 -0
- package/bundled/adapters/cursor/paths.js +11 -0
- package/bundled/adapters/cursor/rules-adapter.js +49 -0
- package/bundled/adapters/cursor/skill-adapter.js +27 -0
- package/bundled/dev-pipeline/README.md +18 -5
- package/bundled/dev-pipeline/prizmkit_runtime/checkpoint_state.py +3 -25
- package/bundled/dev-pipeline/prizmkit_runtime/config.py +71 -14
- package/bundled/dev-pipeline/prizmkit_runtime/gitops.py +28 -4
- package/bundled/dev-pipeline/prizmkit_runtime/heartbeat.py +5 -2
- package/bundled/dev-pipeline/prizmkit_runtime/platform_detection.py +21 -3
- package/bundled/dev-pipeline/prizmkit_runtime/runners.py +19 -5
- package/bundled/dev-pipeline/prizmkit_runtime/sessions.py +123 -28
- package/bundled/dev-pipeline/prizmkit_runtime/status.py +2 -0
- package/bundled/dev-pipeline/prizmkit_runtime/test_result.py +1 -42
- package/bundled/dev-pipeline/scripts/init-bugfix-pipeline.py +43 -6
- package/bundled/dev-pipeline/scripts/init-pipeline.py +46 -8
- package/bundled/dev-pipeline/scripts/init-refactor-pipeline.py +41 -6
- package/bundled/dev-pipeline/scripts/parse-stream-progress.py +143 -27
- package/bundled/dev-pipeline/scripts/update-feature-status.py +2 -2
- package/bundled/dev-pipeline/scripts/utils.py +3 -12
- package/bundled/dev-pipeline/templates/bug-fix-list-schema.json +4 -2
- package/bundled/dev-pipeline/templates/feature-list-schema.json +4 -2
- package/bundled/dev-pipeline/templates/refactor-list-schema.json +4 -2
- package/bundled/dev-pipeline/tests/live_ai_cli_log_smoke.py +2 -1
- package/bundled/dev-pipeline/tests/test_checkpoint_state.py +5 -23
- package/bundled/dev-pipeline/tests/test_generate_bootstrap_prompt.py +2 -2
- package/bundled/dev-pipeline/tests/test_python_runner_parity.py +231 -0
- package/bundled/dev-pipeline/tests/test_unified_cli.py +406 -30
- package/bundled/dev-pipeline/tests/test_utils.py +23 -0
- package/bundled/rules/USAGE.md +3 -0
- package/bundled/skills/_metadata.json +1 -1
- package/bundled/skills/app-planner/SKILL.md +18 -9
- package/bundled/skills/app-planner/references/app-design-guide.md +7 -5
- package/bundled/skills/app-planner/references/brainstorm-guide.md +13 -21
- package/bundled/skills/app-planner/references/generated-plan-review.md +6 -2
- package/bundled/skills/bug-planner/SKILL.md +13 -5
- package/bundled/skills/bug-planner/assets/bug-confirmation-template.md +11 -7
- package/bundled/skills/bug-planner/references/generated-plan-review.md +7 -3
- package/bundled/skills/bug-planner/references/verification.md +0 -2
- package/bundled/skills/bug-planner/scripts/validate-bug-list.py +37 -7
- package/bundled/skills/feature-planner/SKILL.md +17 -11
- package/bundled/skills/feature-planner/assets/planning-guide.md +13 -13
- package/bundled/skills/feature-planner/references/completeness-review.md +8 -4
- package/bundled/skills/feature-planner/references/generated-plan-review.md +6 -2
- package/bundled/skills/feature-planner/scripts/validate-and-generate.py +43 -19
- package/bundled/skills/prizmkit-init/SKILL.md +1 -1
- package/bundled/skills/prizmkit-init/references/config-schema.md +2 -2
- package/bundled/skills/prizmkit-plan/SKILL.md +15 -4
- package/bundled/skills/prizmkit-plan/assets/plan-template.md +18 -3
- package/bundled/skills/prizmkit-plan/assets/spec-template.md +17 -5
- package/bundled/skills/prizmkit-plan/references/clarify-guide.md +26 -24
- package/bundled/skills/prizmkit-plan/references/review-plan-spec-loop.md +7 -5
- package/bundled/skills/prizmkit-plan/references/verification-checklist.md +15 -6
- package/bundled/skills/prizmkit-prizm-docs/assets/prizm-docs-format.md +1 -1
- package/bundled/skills/prizmkit-prizm-docs/references/op-init.md +1 -1
- package/bundled/skills/refactor-planner/SKILL.md +18 -11
- package/bundled/skills/refactor-planner/references/generated-plan-review.md +6 -2
- package/bundled/skills/refactor-planner/references/planning-phases.md +14 -9
- package/bundled/skills/refactor-planner/references/refactor-scoping-guide.md +8 -2
- package/bundled/skills/refactor-planner/scripts/validate-and-generate-refactor.py +38 -9
- package/package.json +4 -2
- package/src/ai-cli-launch.js +9 -2
- package/src/clean.js +42 -6
- package/src/config.js +51 -10
- package/src/detect-platform.js +30 -8
- package/src/external-skills.js +33 -99
- package/src/index.js +5 -0
- package/src/manifest.js +30 -4
- package/src/platforms.js +11 -4
- package/src/prompts.js +12 -4
- package/src/scaffold.js +75 -4
- package/src/upgrade.js +15 -14
|
@@ -90,11 +90,13 @@ Use these tables to guide tech stack selection based on project requirements.
|
|
|
90
90
|
|
|
91
91
|
### Selection Heuristics
|
|
92
92
|
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
-
|
|
96
|
-
-
|
|
97
|
-
-
|
|
93
|
+
Treat the matrices as comparison aids, not a universal stack prescription:
|
|
94
|
+
|
|
95
|
+
- Preserve an existing supported stack unless confirmed goals or evidence justify migration.
|
|
96
|
+
- When the user has no strong preference, compare only options that fit the product outcome, team capability, delivery horizon, deployment environment, operational ownership, and verified project conventions. Recommend one with explicit rationale; do not apply a universal default stack.
|
|
97
|
+
- Consider FastAPI for an ML/AI backend, Go for evidenced high-concurrency/resource constraints, or SQLite for a bounded prototype only when those conditions are confirmed and the trade-offs fit the intent.
|
|
98
|
+
- Ask about deployment when it materially constrains framework, data, cost, compliance, or operations. Otherwise record deployment as explicitly deferred rather than forcing a premature decision.
|
|
99
|
+
- Keep recommendations distinct from confirmed user decisions and state what evidence change would cause the recommendation to be reconsidered.
|
|
98
100
|
|
|
99
101
|
|
|
100
102
|
|
|
@@ -15,8 +15,7 @@ Evaluate the user's initial goal statement:
|
|
|
15
15
|
- **Vague** — Direction exists but needs narrowing (e.g., "improve security")
|
|
16
16
|
- **Exploring** — No firm goal yet, just a direction (e.g., "something with auth")
|
|
17
17
|
|
|
18
|
-
If **vague** or **exploring**, ask
|
|
19
|
-
Do NOT proceed until there is a concrete, testable problem statement (one sentence).
|
|
18
|
+
If **vague** or **exploring**, ask about ambiguity that changes the problem, beneficiary, success outcome, or scope. Resolve evidence-backed facts from available context and disclose low-risk assumptions. Do not proceed until there is a concrete, testable problem statement, but do not interrogate implementation details that are not needed to define the problem.
|
|
20
19
|
|
|
21
20
|
### Phase B: Understand the Idea
|
|
22
21
|
|
|
@@ -27,20 +26,13 @@ Answer these questions (use codebase exploration as needed):
|
|
|
27
26
|
3. **What exists today?** — Current state, prior art in the codebase, adjacent systems.
|
|
28
27
|
4. **What constraints matter?** — Performance, compatibility, security, timeline.
|
|
29
28
|
|
|
30
|
-
|
|
31
|
-
- Performance expectations
|
|
32
|
-
- Scale (users, data, traffic)
|
|
33
|
-
- Security or privacy constraints
|
|
34
|
-
- Reliability / availability needs
|
|
35
|
-
- Maintenance and ownership expectations
|
|
29
|
+
Consider non-functional dimensions only when they materially affect the app decision: performance, scale, security/privacy, reliability, maintenance, ownership, cost, or another domain-specific constraint. Use project evidence first. If a relevant low-risk value remains unknown, propose and clearly mark a reversible **assumption**; if different answers materially change the product or architecture, ask the user.
|
|
36
30
|
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
Summarize findings before moving on. If anything is unclear, ask.
|
|
31
|
+
Summarize confirmed facts, evidence-backed inferences, recommendations, assumptions, and consequential unknowns before moving on.
|
|
40
32
|
|
|
41
33
|
### Phase C: Explore Approaches
|
|
42
34
|
|
|
43
|
-
|
|
35
|
+
First determine whether materially different viable paths exist. If they do, generate the smallest useful comparison—usually 2-3 approaches, but never manufacture options to satisfy a count. If one evidence-supported path remains, explain why alternatives are not materially viable and proceed with that path. For each compared approach:
|
|
44
36
|
|
|
45
37
|
- **Name** — Short label (e.g., "JWT middleware", "OAuth proxy")
|
|
46
38
|
- **How it works** — 2-3 sentences
|
|
@@ -59,9 +51,9 @@ Before asking the user to choose, stress-test each approach using the red team c
|
|
|
59
51
|
4. Who disagrees?
|
|
60
52
|
|
|
61
53
|
Mark any approach that fails 2+ red team questions as **HIGH RISK**.
|
|
62
|
-
If
|
|
54
|
+
If every viable approach is high risk, reconsider the problem or generate a hybrid that addresses the evidenced weaknesses.
|
|
63
55
|
|
|
64
|
-
Present
|
|
56
|
+
Present only meaningful choices. Ask the user to select when the choice materially affects product intent, architecture, cost, compatibility, or another consequential outcome; otherwise record the evidence-supported recommendation as a disclosed, reversible assumption.
|
|
65
57
|
|
|
66
58
|
### Phase D: Capture Design
|
|
67
59
|
|
|
@@ -72,7 +64,7 @@ Produce a structured summary:
|
|
|
72
64
|
[One sentence, testable]
|
|
73
65
|
|
|
74
66
|
## Approaches Considered
|
|
75
|
-
[
|
|
67
|
+
[Material alternatives with pros/cons/effort, or why only one viable path remained]
|
|
76
68
|
|
|
77
69
|
## Selected Approach
|
|
78
70
|
[Complete selected approach and rationale, written as standalone design context without answer tokens or dialogue provenance]
|
|
@@ -93,9 +85,9 @@ This summary becomes the input for the next phase (specification or planning).
|
|
|
93
85
|
|
|
94
86
|
## Rules
|
|
95
87
|
|
|
96
|
-
-
|
|
97
|
-
-
|
|
98
|
-
- Prefer
|
|
99
|
-
-
|
|
100
|
-
- YAGNI ruthlessly
|
|
101
|
-
- Do NOT implement, code, or modify behavior during brainstorming
|
|
88
|
+
- Clarify consequential uncertainty; do not ask merely to remove every unknown.
|
|
89
|
+
- Group related questions when one answer does not depend on another; sequence only dependent decisions.
|
|
90
|
+
- Prefer selectable options for material choices when possible.
|
|
91
|
+
- Keep confirmed facts, inferences, recommendations, assumptions, and unknowns distinct.
|
|
92
|
+
- Apply YAGNI ruthlessly: every selected design element must map to the intent baseline, a confirmed constraint, an existing contract, or an evidenced risk.
|
|
93
|
+
- Do NOT implement, code, or modify behavior during brainstorming.
|
|
@@ -40,6 +40,9 @@ Do not rely on `git status`, `git diff`, or `git diff --cached` to decide whethe
|
|
|
40
40
|
|
|
41
41
|
For every reviewed app-planning artifact or section, check:
|
|
42
42
|
|
|
43
|
+
- Intent fidelity and constraint precedence: the selected product outcome, success meaning, scope, non-goals, and project constraints preserve confirmed user intent rather than AI preferences or generic best practices
|
|
44
|
+
- Evidence status honesty: confirmed facts, evidence-backed inferences, recommendations, assumptions, deferrals, and unknowns remain distinct; no consequential project decision is silently defaulted
|
|
45
|
+
- Design necessity and traceability: every app-level decision maps to a confirmed goal, constraint, existing contract, or evidenced risk, and unsupported future complexity is absent
|
|
43
46
|
- Project brief completeness: goal, users, differentiators, constraints, tech stack assumptions, and at least three actionable ideas when producing a final brief
|
|
44
47
|
- Consistency among conventions, infrastructure, architecture decisions, and project brief content
|
|
45
48
|
- Infrastructure completeness or explicit deferral for database, deployment, and cloud services topics when those flows ran
|
|
@@ -57,14 +60,15 @@ For every reviewed app-planning artifact or section, check:
|
|
|
57
60
|
|
|
58
61
|
Repeat the pre-generation simulation for every reviewed new or changed app-planning line or section as if the reviewer has never seen the planning conversation. First scan all AI-visible fields and sections; machine metadata is exempt, but every generated natural-language value must be session-independent. From the artifact alone, answer:
|
|
59
62
|
|
|
60
|
-
1. What exact product outcome or technical decision does this content record?
|
|
61
|
-
2. What exists today and what desired state or constraint applies?
|
|
63
|
+
1. What exact confirmed product outcome or technical decision does this content record, and how does it preserve the intent baseline?
|
|
64
|
+
2. What exists today, which statements are facts versus assumptions/recommendations, and what desired state or constraint applies?
|
|
62
65
|
3. Which approach was selected, expressed by meaning rather than an option label?
|
|
63
66
|
4. What constraints and non-goals must downstream work preserve?
|
|
64
67
|
5. Why is each reference material relevant?
|
|
65
68
|
6. How will downstream planning or implementation know the decision was honored?
|
|
66
69
|
7. Does any phrase require an unseen earlier question, recommendation, or option list?
|
|
67
70
|
8. Do quoted source materials agree with the final task decision?
|
|
71
|
+
9. Is every included decision necessary for a confirmed goal, constraint, existing contract, or evidenced risk, with no speculative future design?
|
|
68
72
|
|
|
69
73
|
Return `NEEDS_FIXES` if any answer is missing, ambiguous, or dependent on shorthand such as `方案B`, `按推荐走`, `use option A`, `same as above`, or `go with your recommendation`. Parenthetical notes are part of the artifact and must pass the same fresh-session test. Do not emit transcript annotations such as `(original response: "...")`; raw shorthand is not independently intelligible and materially useful. Ask the user for clarification when there is not one provable antecedent. Treat `所有问题都按你的推荐处理`, `全部按照推荐`, `use all recommendations`, and equivalent blanket recommendation approval as conversational authorization: write the concrete accepted decisions, omit the raw approval, and never repeat it once per accepted recommendation. Do not retain non-code planning-source paths such as `.agents/brainstorm/<note>.md`; copy or normalize the task-relevant content into the durable artifact, which must not depend on that source file still existing.
|
|
70
74
|
|
|
@@ -7,6 +7,15 @@ description: "Interactive bug planning that produces, validates, appends, and su
|
|
|
7
7
|
|
|
8
8
|
Interactive planning skill that creates, updates, validates, and summarizes the standardized `.prizmkit/plans/bug-fix-list.json` for later autonomous bug-fix execution. It never fixes source code.
|
|
9
9
|
|
|
10
|
+
## Intent-Aligned Planning Policy
|
|
11
|
+
|
|
12
|
+
Before proposing or finalizing bug contracts:
|
|
13
|
+
1. Establish the **intent baseline**: confirmed actual behavior, expected outcome, scope/non-goals, and explicit constraints. User requirements and confirmed decisions outrank AI preferences or general best practices; never silently violate safety, legal/privacy/data-integrity obligations, or verified existing contracts. Surface material conflicts instead.
|
|
14
|
+
2. Maintain **evidence status**: distinguish confirmed facts, evidence-backed inferences, recommendations, assumptions, and unknowns. Never present a suspected root cause, code location, or fix approach as confirmed user intent.
|
|
15
|
+
3. **Clarify by decision impact**. Ask before choices that materially change expected behavior, scope, compatibility, safety, severity, verification, cost, or irreversible state. Resolve from project evidence first; for low-risk, local, and reversible details, record a disclosed assumption instead of interrupting.
|
|
16
|
+
4. Explore alternatives only when **materially different viable paths** affect the behavioral contract. Compare meaningful trade-offs without manufacturing an option count or prescribing an unverified fix.
|
|
17
|
+
5. Produce a **minimum-sufficient** bug contract: every requirement maps to confirmed behavior, a constraint, existing contract, or evidenced risk, and every expected outcome maps to observable completion evidence. Defer speculative cleanup and unsupported future work.
|
|
18
|
+
|
|
10
19
|
## Invocation Commitment (Hard Rule)
|
|
11
20
|
|
|
12
21
|
When the user invokes `/bug-planner`, you MUST execute the bug-planner workflow. You must NEVER:
|
|
@@ -47,7 +56,7 @@ Every new or changed bug is an executable contract for a fresh AI session that h
|
|
|
47
56
|
1. **Self-contained contract**: The bug's `description` and `acceptance_criteria`, read together, MUST define the objective, current state and actual behavior, desired state and expected behavior, selected scope and decisions, severity rationale, constraints, non-goals, relevant integrations, edge cases, reproduction conditions, verification decisions, and completion evidence. Because no separate rationale field is added, include the durable severity rationale in `description`. Preserve user requirements at matching detail.
|
|
48
57
|
2. **Supplementary evidence only**: `user_context` is supplementary evidence only. Logs, stack traces, screenshots, and source excerpts may support diagnosis, but they MUST NOT expand, replace, or contradict the contract. If `user_context` were removed, a fresh bug-fix session must still know what fails, where and when it fails, what correct behavior means, which scope was selected, and how to verify the fix.
|
|
49
58
|
3. **Severity and verification are durable decisions**: Write the complete severity rationale, selected scope, environment, reproduction path, verification type, and verification decisions by meaning. Never store only an option label or conversational answer.
|
|
50
|
-
4. **Clarify, do not guess**:
|
|
59
|
+
4. **Clarify by impact, do not guess**: Expected behavior, selected behavioral scope, material applicability, and relative references require clarification when multiple meanings would materially change the contract. Root cause, code location, and fix approach may remain explicitly labeled as evidence-backed hypotheses or unknowns when the confirmed behavior and bounded investigation path are sufficient for execution.
|
|
51
60
|
5. **Bug isolation**: Each bug contract and its supplementary evidence contain only material relevant to that bug. Repeat shared environment or constraints only when explicitly global.
|
|
52
61
|
|
|
53
62
|
### Artifact-Wide AI Readability
|
|
@@ -191,7 +200,7 @@ Gather project metadata from the project's own configuration and documentation
|
|
|
191
200
|
- Auto-detect from project files (`package.json`, `requirements.txt`, `go.mod`, etc.)
|
|
192
201
|
- If none found, ask the user
|
|
193
202
|
3. **Identify testing framework**: Read from `.prizmkit/config.json` `tech_stack.testing`, or auto-detect from package.json/requirements.txt/etc., or ask user
|
|
194
|
-
4. **Clarify context** —
|
|
203
|
+
4. **Clarify context by impact** — inspect project evidence first. Ask when ambiguity in the environment, affected systems, expected behavior, or scope would materially alter the bug contract; label recommendations as recommendations and group related questions unless one answer changes the next. Record low-risk reversible assumptions explicitly instead of questioning until subjective full understanding.
|
|
195
204
|
5. **Collect reference materials** — **Upfront Material Detection (Hard Rule)**: If the user has already provided materials (file paths, URLs, rules, specifications, code snippets) in the same message that invoked this skill: (a) Acknowledge what was received: "I received the following materials: [list]"; (b) Read/fetch all provided materials immediately; (c) You MUST still ask: "Are there any additional materials you'd like to provide?"; (d) NEVER skip this collection step just because the user already provided some materials.
|
|
196
205
|
|
|
197
206
|
If the user has NOT provided any materials upfront, explicitly ask whether they have any supplementary materials for you to review before proceeding to bug collection:
|
|
@@ -229,7 +238,7 @@ When parsing user input, auto-detect the format and read `${SKILL_DIR}/reference
|
|
|
229
238
|
- Acceptance criteria (auto-suggest based on description, user can edit)
|
|
230
239
|
- Model override (optional; if specified, overrides $MODEL env var for this bug fix)
|
|
231
240
|
|
|
232
|
-
**Per-bug clarification** —
|
|
241
|
+
**Per-bug clarification** — require confirmed current/actual behavior, desired/expected behavior, consequential scope, severity rationale, and verification decisions. Inspect evidence before asking, group related consequential questions, and label any root cause, code location, integration impact, or fix direction as confirmed, evidence-backed hypothesis, or unknown. A fresh execution session may investigate an unknown root cause; do not force certainty or invent a fix merely to finish planning. Do not finalize shorthand that requires an unseen question, recommendation, or option list.
|
|
233
242
|
|
|
234
243
|
**Per-bug confirmation (mandatory)** — after extracting and clarifying each bug, present a structured summary using the template in `${SKILL_DIR}/assets/bug-confirmation-template.md`, then ask the three confirmation questions defined there.
|
|
235
244
|
|
|
@@ -288,7 +297,7 @@ Return `NEEDS_FIXES` whenever any answer is missing, ambiguous, or available onl
|
|
|
288
297
|
- Description clearly states **expected** vs **actual** behavior (not just "X doesn't work")
|
|
289
298
|
- Reproduction path is specific enough for the pipeline AI to locate the relevant code
|
|
290
299
|
- If the bug involves user interaction, the trigger action is described (not just the symptom)
|
|
291
|
-
- **Code location
|
|
300
|
+
- **Code location guidance**: Provide evidence-backed file/module/function hints when known; otherwise state the bounded discovery target and mark the exact location unknown rather than inventing one
|
|
292
301
|
- **Verification method**: How should the AI verify the fix? (run specific test, check specific behavior)
|
|
293
302
|
- Bad: "Login is broken" — too vague, AI will search the entire codebase
|
|
294
303
|
- Good: "Login form at /login returns 500 when password field is empty. Expected: validation error 400. Root cause likely in src/api/auth.ts POST /api/auth/login handler — missing null check on password field."
|
|
@@ -444,7 +453,6 @@ Key points:
|
|
|
444
453
|
- Critical/high severity bugs require clear automated, manual, or hybrid verification evidence.
|
|
445
454
|
- Medium/low severity bugs use the smallest verification that proves the fix and guards against regression.
|
|
446
455
|
- `browser_interaction` is supported for UI-reproducible bugs; `verification_type` still declares whether verification is automated, manual, or hybrid.
|
|
447
|
-
- Do not generate `critic` or `critic_count`; those fields are fully removed and validators reject them.
|
|
448
456
|
|
|
449
457
|
---
|
|
450
458
|
|
|
@@ -10,22 +10,26 @@ Present this after extracting and clarifying each bug:
|
|
|
10
10
|
│ Description: <expected vs actual behavior>
|
|
11
11
|
│ Severity: <auto-classified> | Verification: <type>
|
|
12
12
|
│
|
|
13
|
-
│ Reproduction: <steps
|
|
14
|
-
│ Affected: <module/feature or "unknown">
|
|
13
|
+
│ Reproduction: <confirmed steps/evidence, or "unknown — bounded discovery required">
|
|
14
|
+
│ Affected: <evidence-backed module/feature, or "unknown">
|
|
15
|
+
│ Root Cause: <confirmed / evidence-backed hypothesis / unknown> — <basis or investigation boundary>
|
|
15
16
|
│
|
|
16
17
|
│ Acceptance Criteria (fix verified when):
|
|
17
18
|
│ 1. <criterion — specific enough for automated pipeline to verify>
|
|
18
19
|
│ 2. <criterion>
|
|
19
20
|
│
|
|
20
|
-
│
|
|
21
|
-
│ - <
|
|
21
|
+
│ Evidence Status:
|
|
22
|
+
│ - Confirmed facts: <actual/expected behavior and evidence>
|
|
23
|
+
│ - Hypotheses/assumptions: <clearly labeled, or "None">
|
|
24
|
+
│ Open Consequential Questions:
|
|
25
|
+
│ - <decisions that materially change behavior/scope/verification, or "None">
|
|
22
26
|
└────────────────────────────────────────────────────────
|
|
23
27
|
```
|
|
24
28
|
|
|
25
29
|
Then ask three confirmation questions:
|
|
26
|
-
1. "
|
|
27
|
-
2. "
|
|
28
|
-
3. "Are the acceptance criteria specific enough that the pipeline can autonomously verify the fix?"
|
|
30
|
+
1. "Are the confirmed actual behavior, expected behavior, and selected scope accurate?"
|
|
31
|
+
2. "Are the evidence, hypotheses, unknowns, and severity rationale labeled correctly?"
|
|
32
|
+
3. "Are the acceptance criteria specific enough that the pipeline can autonomously verify the outcome without assuming a particular unproven fix?"
|
|
29
33
|
|
|
30
34
|
Only finalize the bug entry after user confirms all three points.
|
|
31
35
|
|
|
@@ -29,6 +29,9 @@ Do not rely on `git status`, `git diff`, or `git diff --cached` to decide whethe
|
|
|
29
29
|
|
|
30
30
|
For every reviewed bug entry, check:
|
|
31
31
|
|
|
32
|
+
- Intent fidelity: confirmed actual behavior, expected outcome, behavioral scope, non-goals, and verification preserve the user's meaning rather than an AI-selected fix
|
|
33
|
+
- Evidence status honesty: facts, evidence-backed inferences, recommendations, assumptions, and unknowns remain distinct; suspected root causes, code locations, and fix approaches are never presented as confirmed without evidence
|
|
34
|
+
- Minimum-sufficient scope: every requested change maps to confirmed behavior, an existing contract, constraint, or evidenced risk; speculative cleanup and unsupported future work are absent
|
|
32
35
|
- Schema compatibility with `dev-pipeline-bug-fix-list-v1` and `.prizmkit/dev-pipeline/templates/bug-fix-list-schema.json`
|
|
33
36
|
- Dependency/DAG consistency, duplicate handling, and root-cause overlap
|
|
34
37
|
- Description completeness: objective, current/actual behavior, desired/expected behavior, selected scope, reproduction path, code-location hints, affected environment, relevant integrations, constraints, non-goals, edge cases, verification decisions, completion evidence, and headless execution readiness
|
|
@@ -45,14 +48,15 @@ For every reviewed bug entry, check:
|
|
|
45
48
|
|
|
46
49
|
Repeat the pre-generation simulation for every reviewed new or changed bug as if the reviewer has never seen the planning conversation. First scan all AI-visible fields and sections; machine metadata is exempt, but every generated natural-language value must be session-independent. From the artifact alone, answer:
|
|
47
50
|
|
|
48
|
-
1. What exact problem or outcome is this task responsible for?
|
|
49
|
-
2. What exists today
|
|
50
|
-
3. Which fix scope and verification approach were selected, expressed by meaning rather than an option label?
|
|
51
|
+
1. What exact confirmed problem or outcome is this task responsible for?
|
|
52
|
+
2. What exists today, what must change from actual to expected behavior, and which statements are confirmed versus hypothesized?
|
|
53
|
+
3. Which behavioral fix scope and verification approach were selected, expressed by meaning rather than an option label, without prescribing an unproven implementation?
|
|
51
54
|
4. What constraints and non-goals must be preserved?
|
|
52
55
|
5. Why is each reference material relevant?
|
|
53
56
|
6. How can completion be verified?
|
|
54
57
|
7. Does any phrase require an unseen earlier question, recommendation, or option list?
|
|
55
58
|
8. Do quoted source materials agree with the final task decision?
|
|
59
|
+
9. Is every requested change necessary for confirmed behavior, a constraint, existing contract, or evidenced risk, with no speculative cleanup?
|
|
56
60
|
|
|
57
61
|
Return `NEEDS_FIXES` if any answer is missing, ambiguous, available only in `user_context`, or dependent on shorthand such as `方案B`, `按推荐走`, `use option A`, `same as above`, or `go with your recommendation`. Parenthetical notes are part of the artifact and must pass the same fresh-session test. Do not emit transcript annotations such as `(original response: "...")`; raw shorthand is not independently intelligible and materially useful. Preserve substantive rationale in the durable bug contract. Treat `所有问题都按你的推荐处理`, `全部按照推荐`, `use all recommendations`, and equivalent blanket recommendation approval as conversational authorization: write the concrete accepted decisions, omit the raw approval, and never repeat it once per accepted recommendation. Do not retain non-code planning-source paths such as `.agents/brainstorm/<note>.md`; copy or normalize the task-relevant content and evidence excerpt into the contract, which must not depend on that source file still existing. Ask the user for clarification when there is not one provable antecedent.
|
|
58
62
|
|
|
@@ -25,5 +25,3 @@ Use `browser_interaction` for UI-reproducible bugs.
|
|
|
25
25
|
- `tool: playwright-cli` is best for local dev-server verification in an isolated browser.
|
|
26
26
|
- `tool: opencli` is best when an existing Chrome login/session or third-party integration cookies are needed.
|
|
27
27
|
- `verify_steps` should describe what to prove, not low-level click scripts.
|
|
28
|
-
|
|
29
|
-
Do not emit `critic` or `critic_count`; those fields are retired and validators reject them.
|
|
@@ -30,6 +30,21 @@ VALID_SEVERITIES = {"critical", "high", "medium", "low"}
|
|
|
30
30
|
VALID_SOURCE_TYPES = {"stack_trace", "user_report", "failed_test", "log_pattern", "monitoring_alert"}
|
|
31
31
|
VALID_VERIFICATION_TYPES = {"automated", "manual", "hybrid"}
|
|
32
32
|
VALID_STATUSES = {"pending", "in_progress", "completed", "failed", "skipped", "needs_info", "auto_skipped"}
|
|
33
|
+
ALLOWED_LIST_FIELDS = {
|
|
34
|
+
"$schema", "project_name", "project_description", "created_at",
|
|
35
|
+
"created_by", "bugs", "global_context",
|
|
36
|
+
}
|
|
37
|
+
ALLOWED_GLOBAL_CONTEXT_FIELDS = {
|
|
38
|
+
"tech_stack", "language", "runtime", "frontend_framework",
|
|
39
|
+
"frontend_styling", "backend_framework", "database", "orm",
|
|
40
|
+
"testing_strategy", "bundler", "project_type", "ci_pipeline",
|
|
41
|
+
}
|
|
42
|
+
ALLOWED_BUG_FIELDS = {
|
|
43
|
+
"id", "title", "description", "severity", "priority", "error_source",
|
|
44
|
+
"environment", "affected_modules", "verification_type", "dependencies",
|
|
45
|
+
"acceptance_criteria", "status", "user_context", "browser_interaction",
|
|
46
|
+
"model",
|
|
47
|
+
}
|
|
33
48
|
BUG_ID_PATTERN = re.compile(r"^B-\d{3}$")
|
|
34
49
|
SCHEMA_VERSION = "dev-pipeline-bug-fix-list-v1"
|
|
35
50
|
|
|
@@ -114,6 +129,12 @@ def validate(data, feature_ids=None):
|
|
|
114
129
|
warnings = []
|
|
115
130
|
|
|
116
131
|
# Top-level required fields
|
|
132
|
+
unknown_root = set(data) - ALLOWED_LIST_FIELDS
|
|
133
|
+
if unknown_root:
|
|
134
|
+
errors.append("bug list has unknown fields: {}".format(
|
|
135
|
+
", ".join(sorted(unknown_root))
|
|
136
|
+
))
|
|
137
|
+
|
|
117
138
|
if "$schema" not in data:
|
|
118
139
|
errors.append("Missing required field: $schema")
|
|
119
140
|
elif data["$schema"] != SCHEMA_VERSION:
|
|
@@ -122,6 +143,17 @@ def validate(data, feature_ids=None):
|
|
|
122
143
|
if not data.get("project_name"):
|
|
123
144
|
errors.append("Missing or empty required field: project_name")
|
|
124
145
|
|
|
146
|
+
global_context = data.get("global_context")
|
|
147
|
+
if global_context is not None:
|
|
148
|
+
if not isinstance(global_context, dict):
|
|
149
|
+
errors.append("global_context must be an object")
|
|
150
|
+
else:
|
|
151
|
+
unknown_context = set(global_context) - ALLOWED_GLOBAL_CONTEXT_FIELDS
|
|
152
|
+
if unknown_context:
|
|
153
|
+
errors.append("global_context has unknown fields: {}".format(
|
|
154
|
+
", ".join(sorted(unknown_context))
|
|
155
|
+
))
|
|
156
|
+
|
|
125
157
|
bugs = data.get("bugs", [])
|
|
126
158
|
if not bugs or not isinstance(bugs, list):
|
|
127
159
|
errors.append("Missing or empty required field: bugs")
|
|
@@ -139,13 +171,11 @@ def validate(data, feature_ids=None):
|
|
|
139
171
|
for i, bug in enumerate(bugs):
|
|
140
172
|
prefix = "bugs[{}]".format(i)
|
|
141
173
|
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
)
|
|
148
|
-
)
|
|
174
|
+
unknown = set(bug.keys()) - ALLOWED_BUG_FIELDS
|
|
175
|
+
if unknown:
|
|
176
|
+
errors.append("{} has unknown fields: {}".format(
|
|
177
|
+
prefix, ", ".join(sorted(unknown))
|
|
178
|
+
))
|
|
149
179
|
|
|
150
180
|
# Required fields
|
|
151
181
|
bug_id = bug.get("id", "")
|
|
@@ -13,6 +13,15 @@ Always produce a validated `.prizmkit/plans/feature-list.json` that conforms to
|
|
|
13
13
|
|
|
14
14
|
For planning a **new application from scratch** (vision, tech stack, decomposition), use `app-planner` instead.
|
|
15
15
|
|
|
16
|
+
## Intent-Aligned Planning Policy
|
|
17
|
+
|
|
18
|
+
Before proposing or finalizing feature contracts:
|
|
19
|
+
1. Establish the **intent baseline**: confirmed product goal, success outcome, scope/non-goals, and explicit constraints. User requirements and confirmed decisions outrank AI preferences or general best practices; never silently violate safety, legal/privacy/data-integrity obligations, or verified existing contracts. Surface material conflicts instead.
|
|
20
|
+
2. Maintain **evidence status**: distinguish confirmed facts, evidence-backed inferences, recommendations, assumptions, and unknowns. Never promote an inference or preferred implementation into user intent.
|
|
21
|
+
3. **Clarify by decision impact**. Ask before choices that materially change product behavior, scope, compatibility, safety, cost, or irreversible state. Resolve from project evidence first; for low-risk, local, and reversible details, record a disclosed assumption instead of interrupting.
|
|
22
|
+
4. Explore alternatives only when **materially different viable paths** exist. Compare meaningful trade-offs without manufacturing an option count or applying a universal default.
|
|
23
|
+
5. Produce a **minimum-sufficient** feature contract: every requirement maps to a confirmed goal, constraint, existing contract, or evidenced risk, and every goal maps to observable completion evidence. Defer speculative features and unsupported future infrastructure.
|
|
24
|
+
|
|
16
25
|
## Invocation Commitment (Hard Rule)
|
|
17
26
|
|
|
18
27
|
**When the user invokes `/feature-planner`, you MUST execute the feature-planner workflow.** You must NEVER:
|
|
@@ -54,7 +63,7 @@ Every new or changed feature is an executable contract for a fresh AI session th
|
|
|
54
63
|
|
|
55
64
|
1. **Self-contained contract**: The feature's `description` and `acceptance_criteria`, read together, MUST define the objective, current state, desired state, selected decisions, constraints, non-goals, relevant integrations, edge cases, and completion evidence. Preserve detailed user requirements at matching detail; normalization must not simplify substantive rules.
|
|
56
65
|
2. **Supplementary evidence only**: `user_context` is supplementary evidence only. It may preserve scoped source excerpts and purpose-tagged references, but it MUST NOT expand, replace, or contradict the contract in `description` and `acceptance_criteria`. If `user_context` were removed, a fresh execution session must still know exactly what to implement and how to prove completion.
|
|
57
|
-
3. **Clarify, do not guess**: Ask
|
|
66
|
+
3. **Clarify by impact, do not guess**: Ask when conflicting requirements or multiple plausible antecedents would materially change product behavior, scope, compatibility, safety, cost, or completion evidence. Resolve evidence-backed facts from project context and retain safe low-risk reversible choices as explicit assumptions rather than silently inventing user intent.
|
|
58
67
|
4. **Feature isolation**: In multi-feature planning, each contract and its supplementary evidence contain only material relevant to that feature. Repeat shared context only when it explicitly applies to every affected feature. Ask the user to map material whose applicability is unclear.
|
|
59
68
|
|
|
60
69
|
### Artifact-Wide AI Readability
|
|
@@ -130,8 +139,7 @@ Trigger conditions are covered by the frontmatter `description`. Do NOT use this
|
|
|
130
139
|
8. **Browser interaction**: If present, may include `tool` and `verify_steps`; planner should add concrete `verify_steps` when known, but the schema permits an empty object for AI runtime exploration.
|
|
131
140
|
9. **Complexity enum**: If present, is one of: low, medium, high, critical
|
|
132
141
|
10. **Model field**: If present, is a non-empty string
|
|
133
|
-
11. **
|
|
134
|
-
12. **Root schema**: Has $schema='dev-pipeline-feature-list-v1', project_name, and non-empty features array
|
|
142
|
+
11. **Root schema**: Has $schema='dev-pipeline-feature-list-v1', project_name, and non-empty features array
|
|
135
143
|
|
|
136
144
|
5. **Use script output as source of truth** — if validation fails, fix and re-run until pass
|
|
137
145
|
|
|
@@ -142,7 +150,7 @@ Before questions, check optional context files (never block if absent):
|
|
|
142
150
|
- `.prizmkit/config.json` (existing stack preferences and detected tech stack)
|
|
143
151
|
- `.prizmkit/plans/project-brief.md` (project context from app-planner, if available)
|
|
144
152
|
- existing `.prizmkit/plans/feature-list.json` (required for incremental mode)
|
|
145
|
-
- Platform instruction file: use the `platform` field in `.prizmkit/manifest.json` as source of truth when present (`codex` → `AGENTS.md`, `claude` → `CLAUDE.md`, `codebuddy` → `CODEBUDDY.md`, `all` → read every matching file). Legacy manifests may contain `both`; treat it as read-only compatibility and read `CLAUDE.md` plus `CODEBUDDY.md` only when encountered.
|
|
153
|
+
- Platform instruction file: use the `platform` field in `.prizmkit/manifest.json` as source of truth when present (`codex` → `AGENTS.md`, `cursor` → existing user-owned `AGENTS.md` when present, `claude` → `CLAUDE.md`, `codebuddy` → `CODEBUDDY.md`, `all` → read every matching file). Legacy manifests may contain `both`; treat it as read-only compatibility and read `CLAUDE.md` plus `CODEBUDDY.md` only when encountered.
|
|
146
154
|
- If `.prizmkit/prizm-docs/root.prizm` is absent and the project has existing source code, scan the directory structure to understand the codebase layout:
|
|
147
155
|
```bash
|
|
148
156
|
find . -maxdepth 2 -type d \
|
|
@@ -151,7 +159,7 @@ Before questions, check optional context files (never block if absent):
|
|
|
151
159
|
-not -path '*/__pycache__/*' -not -path '*/vendor/*' \
|
|
152
160
|
-not -path '*/.agents/*' -not -path '*/.codex/*' \
|
|
153
161
|
-not -path '*/.claude/*' -not -path '*/.codebuddy/*' \
|
|
154
|
-
-not -path '*/.prizmkit/*' \
|
|
162
|
+
-not -path '*/.cursor/*' -not -path '*/.prizmkit/*' \
|
|
155
163
|
| sed -e 's;[^/]*/;|____;g;s;____|; |;g'
|
|
156
164
|
```
|
|
157
165
|
|
|
@@ -273,7 +281,7 @@ Execute the planning workflow in conversation mode with mandatory checkpoints:
|
|
|
273
281
|
|
|
274
282
|
### Interactive Phases
|
|
275
283
|
1. Clarify scope and goals
|
|
276
|
-
1.1 **Requirement clarification** —
|
|
284
|
+
1.1 **Requirement clarification** — establish the intent baseline, inspect project evidence, and classify uncertainty by decision impact. Ask about consequential ambiguity in goals, external behavior, scope, non-goals, compatibility, safety, cost, or irreversible choices; label recommendations and group related questions unless answers are dependent. Proceed when consequential ambiguity is resolved and any low-risk reversible assumptions are explicit—not when every unknown has been eliminated.
|
|
277
285
|
1.2 **Collect reference materials** — **Upfront Material Detection (Hard Rule)**: If the user has already provided materials (file paths, URLs, rules, specifications, code snippets) in the same message that invoked this skill: (a) Acknowledge what was received: "I received the following materials: [list]"; (b) Read/fetch all provided materials immediately; (c) You MUST still ask: "Are there any additional materials you'd like to provide?"; (d) NEVER skip this collection step just because the user already provided some materials.
|
|
278
286
|
|
|
279
287
|
If the user has NOT provided any materials upfront, explicitly ask whether they have any supplementary materials for you to review. Present this as a single prompt covering all material types:
|
|
@@ -290,7 +298,7 @@ Execute the planning workflow in conversation mode with mandatory checkpoints:
|
|
|
290
298
|
2. Confirm constraints and existing architecture
|
|
291
299
|
3. Propose feature set with dependencies
|
|
292
300
|
4. Refine descriptions and acceptance criteria
|
|
293
|
-
4.1 **Per-feature clarification** — for each feature,
|
|
301
|
+
4.1 **Per-feature clarification** — for each feature, ask when multiple interpretations of behavior, acceptance criteria, scope, non-goals, material integrations, or completion evidence would materially change the contract. Resolve evidence-backed details from project context, label low-risk reversible assumptions, and reject conversational shorthand that requires an unseen question, recommendation, or option list. Do not force user confirmation for unconstrained implementation details that a fresh session can safely decide and verify.
|
|
294
302
|
4.2 **Browser interaction** (mandatory for fullstack/frontend projects) — see §Browser Interaction Planning below. Qualifying features get `browser_interaction` by default. Only confirm with the user as a batch summary; do NOT ask per-feature.
|
|
295
303
|
5. Verify DAG/order/priorities and show the mandatory priority/complexity calibration table with short rationales for every item
|
|
296
304
|
6. Run the pre-generation Headless Context Completeness Gate (see §Pre-Generation Completeness Review below)
|
|
@@ -310,7 +318,7 @@ Checkpoints catch cascading errors early — skipping one means the next phase b
|
|
|
310
318
|
| **CP-FP-2** | Feature Proposals | Feature set with titles+deps identified (pre-validation) | 3-5 |
|
|
311
319
|
| **CP-FP-3** | DAG Validity | No cycles, dependencies resolved (validation dry-run) | 5 |
|
|
312
320
|
| **CP-FP-3.1** | Browser Interaction Applied | Qualifying features have `browser_interaction` field; user confirmed or opted out | 4 |
|
|
313
|
-
| **CP-FP-3.2** | Testing Defaults Applied | All features have appropriate testing expectations
|
|
321
|
+
| **CP-FP-3.2** | Testing Defaults Applied | All features have appropriate testing expectations | 7 |
|
|
314
322
|
| **CP-FP-3.3** | Completeness Review Passed | Every new or changed feature passes fresh-session simulation from `description` and `acceptance_criteria` without conversation history or `user_context` | 6 |
|
|
315
323
|
| **CP-FP-4** | `.prizmkit/plans/feature-list.json` Generated | Schema validates, all required keys present | 7-8 |
|
|
316
324
|
| **CP-FP-5** | Final Validation Pass | Python script returns `"valid": true` with zero errors | 9 |
|
|
@@ -422,7 +430,7 @@ Read `${SKILL_DIR}/references/generated-plan-review.md` and follow it as the sin
|
|
|
422
430
|
|
|
423
431
|
## Testing Defaults (Phase 8)
|
|
424
432
|
|
|
425
|
-
Set default testing-related fields for each feature. The user can opt out of generated testing expectations
|
|
433
|
+
Set default testing-related fields for each feature. The user can opt out of generated testing expectations.
|
|
426
434
|
|
|
427
435
|
| Priority | Testing expectation | Rationale |
|
|
428
436
|
|----------|---------------------|-----------|
|
|
@@ -430,8 +438,6 @@ Set default testing-related fields for each feature. The user can opt out of gen
|
|
|
430
438
|
| medium | Require focused tests for changed public behavior | Normal changes need meaningful boundary coverage. |
|
|
431
439
|
| low | Require the smallest relevant verification | Low-risk changes should stay lightweight. |
|
|
432
440
|
|
|
433
|
-
Never emit `critic` or `critic_count`; those fields are fully removed and the validator rejects them.
|
|
434
|
-
|
|
435
441
|
For frontend features with `browser_interaction`, browser verification is enabled by default. The `tool` field uses the user's choice from the mandatory browser tool question in Phase 4.2 (see §Browser Interaction Planning → Default Behavior).
|
|
436
442
|
|
|
437
443
|
Present a consolidated testing summary table at Phase 8, then ask for confirmation.
|
|
@@ -8,7 +8,7 @@ For app-level design references (vision templates, tech stack matrix), see `app-
|
|
|
8
8
|
|
|
9
9
|
## Feature Description Writing Guide
|
|
10
10
|
|
|
11
|
-
Feature descriptions are the **primary input** for autonomous pipeline sessions. A thin description forces the AI to guess
|
|
11
|
+
Feature descriptions are the **primary input** for autonomous pipeline sessions. A thin description forces the AI to guess, while an overprescribed description can turn assumptions into requirements. Write the minimum-sufficient contract: preserve every confirmed behavior and constraint at matching detail, and omit unsupported implementation choices or unrelated future design.
|
|
12
12
|
|
|
13
13
|
### Minimum Word Counts
|
|
14
14
|
|
|
@@ -21,17 +21,17 @@ Feature descriptions are the **primary input** for autonomous pipeline sessions.
|
|
|
21
21
|
|
|
22
22
|
Below 15 words is a validation error. Below the recommended minimum triggers a warning.
|
|
23
23
|
|
|
24
|
-
|
|
24
|
+
There is no schema-level upper limit, but length is not a quality target. Add detail only when it establishes confirmed intent, current/desired behavior, constraints, integrations, relevant edge cases, or completion evidence. Do not add speculative infrastructure, API shape, data fields, or future capability merely to reach a recommended word count.
|
|
25
25
|
|
|
26
26
|
### What to Include
|
|
27
27
|
|
|
28
|
-
|
|
28
|
+
Cover only the aspects that are material to this feature; omit non-applicable dimensions rather than inventing content:
|
|
29
29
|
|
|
30
|
-
1. **
|
|
31
|
-
2. **Key behaviors** — business rules, validation, state transitions, workflows
|
|
32
|
-
3. **Integration points** —
|
|
33
|
-
4. **Data model** — entities, relationships,
|
|
34
|
-
5. **
|
|
30
|
+
1. **Outcome and deliverables** — confirmed user-visible or system-observable result; name endpoints, pages, commands, or models only when the contract or existing system establishes them
|
|
31
|
+
2. **Key behaviors** — business rules, validation, state transitions, and workflows required by the intent
|
|
32
|
+
3. **Integration points** — verified existing modules, services, APIs, or predecessor outputs and why they matter
|
|
33
|
+
4. **Data model** — entities, relationships, and constraints when persistence is genuinely required
|
|
34
|
+
5. **Relevant error/edge cases** — failures, empty states, limits, permissions, concurrency, or idempotency only where they affect completion
|
|
35
35
|
|
|
36
36
|
### Good vs Bad Examples
|
|
37
37
|
|
|
@@ -61,7 +61,7 @@ Feature entries are consumed by **autonomous AI sessions running in headless mod
|
|
|
61
61
|
|
|
62
62
|
**Must include for headless readiness:**
|
|
63
63
|
1. **Objective and current state** — the exact outcome and what exists today
|
|
64
|
-
2. **Desired state and selected decisions** — the complete chosen behavior
|
|
64
|
+
2. **Desired state and selected decisions** — the complete chosen product/contract behavior, never only an option label; include implementation approach only when the user, an existing contract, or verified project constraints actually select it
|
|
65
65
|
3. **Constraints and non-goals** — boundaries the implementation must preserve
|
|
66
66
|
4. **Relevant integrations** — existing APIs, models, modules, services, and dependency outputs
|
|
67
67
|
5. **Edge cases** — validation, permissions, empty/error states, limits, concurrency, or idempotency when relevant
|
|
@@ -123,7 +123,7 @@ Then [expected outcome]
|
|
|
123
123
|
|
|
124
124
|
1. **One behavior per criterion.** Each criterion tests exactly one thing.
|
|
125
125
|
2. **No implementation details.** Criteria describe what, not how. Say "user is redirected" not "React Router navigates to /dashboard."
|
|
126
|
-
3. **Include edge cases.** Cover invalid input, unauthorized access, empty states, and error conditions.
|
|
126
|
+
3. **Include relevant edge cases.** Cover invalid input, unauthorized access, empty states, and error conditions only when they can affect the confirmed outcome.
|
|
127
127
|
4. **Be measurable.** Where performance matters, include specific thresholds (e.g., "within 2 seconds").
|
|
128
128
|
5. **Keep the count manageable.** A feature with more than 8 acceptance criteria may need to be split into sub-features.
|
|
129
129
|
|
|
@@ -186,17 +186,17 @@ Anti-pattern: a generated plan where every item is `Priority: high` and `Complex
|
|
|
186
186
|
|
|
187
187
|
These rules ensure the feature dependency graph is valid and buildable.
|
|
188
188
|
|
|
189
|
-
1. **F-001 has zero dependencies.**
|
|
189
|
+
1. **F-001 has zero feature-list dependencies.** It is the first independently executable deliverable for the current project state; make it infrastructure or setup only when confirmed prerequisites require that work. Do not recreate setup that already exists.
|
|
190
190
|
|
|
191
191
|
2. **No circular dependencies.** Dependencies MUST form a directed acyclic graph (DAG). If A depends on B and B depends on A, restructure the features.
|
|
192
192
|
|
|
193
193
|
3. **Minimal dependency sets.** Each feature should depend only on the features it directly needs. Do not add transitive dependencies explicitly. If F-003 depends on F-002 and F-002 depends on F-001, then F-003 does NOT need to list F-001 as a dependency.
|
|
194
194
|
|
|
195
|
-
4. **
|
|
195
|
+
4. **Place authentication before its consumers when required.** Do not add or prioritize authentication merely because it is common; use the confirmed product scope and existing auth state.
|
|
196
196
|
|
|
197
197
|
5. **Data model before display.** Features that create or define data entities must precede features that display, search, or manipulate that data.
|
|
198
198
|
|
|
199
|
-
6. **
|
|
199
|
+
6. **Place missing prerequisites before their consumers.** Database, scaffolding, CI/CD, or environment work belongs early only when it is absent, in scope, and required by a confirmed feature. Existing-project planning must not manufacture infrastructure tasks.
|
|
200
200
|
|
|
201
201
|
7. **Independent features can be parallel.** If two features share no dependencies on each other, they can be built in parallel. The dependency graph should reflect this by not artificially linking them.
|
|
202
202
|
|
|
@@ -12,8 +12,8 @@ Scan all AI-visible fields and sections, not only the main contract. Every gener
|
|
|
12
12
|
|
|
13
13
|
For each new or changed feature, answer all of these from `description` and `acceptance_criteria` alone:
|
|
14
14
|
|
|
15
|
-
1. What exact problem or outcome is this feature responsible for?
|
|
16
|
-
2. What exists today and what must change?
|
|
15
|
+
1. What exact confirmed problem or outcome is this feature responsible for, and how does it preserve the intent baseline?
|
|
16
|
+
2. What exists today, which statements are facts versus inferences/assumptions, and what must change?
|
|
17
17
|
3. Which approach was selected, expressed by meaning rather than an option label?
|
|
18
18
|
4. What constraints and non-goals must be preserved?
|
|
19
19
|
5. Which existing modules, APIs, data, dependencies, or other relevant integrations are involved?
|
|
@@ -22,8 +22,10 @@ For each new or changed feature, answer all of these from `description` and `acc
|
|
|
22
22
|
8. Does any phrase require an unseen earlier question, recommendation, or option list?
|
|
23
23
|
9. Why is each reference material relevant, and what should the execution AI inspect?
|
|
24
24
|
10. Do quoted source materials agree with the final task decision?
|
|
25
|
+
11. Does every prescribed behavior or design choice map to a confirmed goal, constraint, existing contract, or evidenced risk?
|
|
26
|
+
12. Are any unresolved consequential decisions hidden behind an AI recommendation or silent default?
|
|
25
27
|
|
|
26
|
-
If any answer is unavailable, ambiguous, or present only in `user_context`, the verdict is `NEEDS_FIXES`.
|
|
28
|
+
If any consequential answer is unavailable, ambiguous, or present only in `user_context`, the verdict is `NEEDS_FIXES`. A low-risk, local, reversible implementation assumption may remain when it is labeled and paired with a verification point; never infer a missing product decision from conversation memory.
|
|
27
29
|
|
|
28
30
|
## Step 2: Contract and Material Checks
|
|
29
31
|
|
|
@@ -57,7 +59,9 @@ Look at the feature set as a whole:
|
|
|
57
59
|
- **Implied functionality gaps**: Does one feature assume a capability that no feature provides?
|
|
58
60
|
- **Missing integration seams**: If two features share data or interact at runtime, is the interface specified by meaning?
|
|
59
61
|
- **Dependency context**: Does each dependent feature state exactly which predecessor output it consumes?
|
|
60
|
-
- **Scope leaks**: Does a description activate rejected or out-of-scope functionality?
|
|
62
|
+
- **Scope leaks**: Does a description activate rejected or out-of-scope functionality, speculative future capability, or unsupported infrastructure?
|
|
63
|
+
- **Design necessity**: Does every prescribed component, interface, or dependency map to confirmed intent, an existing contract, or an evidenced risk?
|
|
64
|
+
- **Evidence status**: Are recommendations and inferred implementation details clearly separated from confirmed product decisions?
|
|
61
65
|
- **Source conflict**: Does an excerpt describe an earlier alternative that conflicts with the selected final decision?
|
|
62
66
|
|
|
63
67
|
## Step 4: Present Review and Repair
|
|
@@ -29,6 +29,9 @@ Do not rely on `git status`, `git diff`, or `git diff --cached` to decide whethe
|
|
|
29
29
|
|
|
30
30
|
For every reviewed feature entry, check:
|
|
31
31
|
|
|
32
|
+
- Intent fidelity: confirmed product outcome, success meaning, scope, non-goals, and constraints preserve user intent rather than AI preferences or generic best practices
|
|
33
|
+
- Evidence status honesty: confirmed facts, evidence-backed inferences, recommendations, assumptions, and unknowns remain distinct; no consequential product or contract decision is silently defaulted
|
|
34
|
+
- Minimum-sufficient design: every prescribed behavior, component, interface, or dependency maps to a confirmed goal, constraint, existing contract, or evidenced risk; speculative features and unsupported infrastructure are absent
|
|
32
35
|
- Schema compatibility with `dev-pipeline-feature-list-v1` and `.prizmkit/dev-pipeline/templates/feature-list-schema.json`
|
|
33
36
|
- Dependency/DAG soundness: dependencies exist, no cycles, no poorly ordered prerequisite chains
|
|
34
37
|
- Description completeness and headless execution readiness: `description` plus `acceptance_criteria` defines objective, current state, desired state, selected decisions, constraints, non-goals, relevant integrations, edge cases, and completion evidence without conversation history
|
|
@@ -45,14 +48,15 @@ For every reviewed feature entry, check:
|
|
|
45
48
|
|
|
46
49
|
Repeat the pre-generation simulation for every reviewed new or changed feature as if the reviewer has never seen the planning conversation. First scan all AI-visible fields and sections; machine metadata is exempt, but every generated natural-language value must be session-independent. From the artifact alone, answer:
|
|
47
50
|
|
|
48
|
-
1. What exact problem or outcome is this task responsible for?
|
|
49
|
-
2. What exists today and what must change?
|
|
51
|
+
1. What exact confirmed problem or outcome is this task responsible for, and how does it preserve the intent baseline?
|
|
52
|
+
2. What exists today, which statements are facts versus inferences/assumptions, and what must change?
|
|
50
53
|
3. Which approach was selected, expressed by meaning rather than an option label?
|
|
51
54
|
4. What constraints and non-goals must be preserved?
|
|
52
55
|
5. Why is each reference material relevant?
|
|
53
56
|
6. How can completion be verified?
|
|
54
57
|
7. Does any phrase require an unseen earlier question, recommendation, or option list?
|
|
55
58
|
8. Do quoted source materials agree with the final task decision?
|
|
59
|
+
9. Does every prescribed behavior or design choice have a confirmed requirement, constraint, existing contract, or evidenced risk, with no speculative future scope?
|
|
56
60
|
|
|
57
61
|
Return `NEEDS_FIXES` if any answer is missing, ambiguous, available only in `user_context`, or dependent on shorthand such as `方案B`, `按推荐走`, `use option A`, `same as above`, or `go with your recommendation`. Parenthetical notes are part of the artifact and must pass the same fresh-session test. Do not emit transcript annotations such as `(original response: "...")`; raw shorthand is not independently intelligible and materially useful. Preserve substantive rationale in the durable task contract. Treat `所有问题都按你的推荐处理`, `全部按照推荐`, `use all recommendations`, and equivalent blanket recommendation approval as conversational authorization: write the concrete accepted decisions, omit the raw approval, and never repeat it once per accepted recommendation. Do not retain non-code planning-source paths such as `.agents/brainstorm/<note>.md`; copy or normalize the task-relevant content into the contract, which must not depend on that source file still existing. Ask the user for clarification when there is not one provable antecedent.
|
|
58
62
|
|