pantheon-opencode 2.0.0-rc.1 → 2.0.0
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/AGENTS.global.md +2 -2
- package/AGENTS.md +8 -8
- package/CHANGELOG.md +54 -0
- package/README.md +2 -0
- package/README.pt-BR.md +2 -0
- package/bin/pantheon-init.mjs +13 -0
- package/commands/pantheon-audit.md +1 -1
- package/commands/pantheon-deepwork.md +1 -1
- package/commands/pantheon-optimize.md +41 -63
- package/package.json +4 -3
- package/plugin.json +1 -1
- package/prompts/optimize-database.prompt.md +5 -5
- package/prompts/plan-architecture.prompt.md +6 -6
- package/pyproject.toml +1 -1
- package/scripts/build-agents-md.mjs +10 -10
- package/scripts/build-plugin.mjs +26 -0
- package/scripts/install/opencode-version.mjs +17 -5
- package/scripts/install/opencode.mjs +8 -1
- package/scripts/optimize.mjs +322 -0
- package/scripts/prune.mjs +105 -14
- package/scripts/update.mjs +20 -15
- package/skills-lock.json +11 -11
- package/src/agents/aphrodite.md +15 -14
- package/src/agents/apollo.md +2 -1
- package/src/agents/athena.md +5 -5
- package/src/agents/demeter.md +2 -0
- package/src/agents/hephaestus.md +1 -0
- package/src/agents/hermes.md +19 -95
- package/src/agents/iris.md +3 -0
- package/src/agents/nyx.md +1 -0
- package/src/agents/prometheus.md +2 -0
- package/src/agents/talos.md +3 -0
- package/src/agents/themis.md +91 -87
- package/src/agents/zeus.md +41 -266
- package/src/instructions/agent-return-format.instructions.md +1 -1
- package/src/instructions/memory-protocol.instructions.md +1 -1
- package/src/instructions/zeus-anti-stall.instructions.md +3 -3
- package/src/instructions/zeus-communication-rules.instructions.md +1 -1
- package/src/instructions/zeus-council-synthesis.instructions.md +2 -2
- package/src/instructions/zeus-timeout-retry.instructions.md +10 -10
- package/src/pantheon/model-command.ts +12 -12
- package/src/pantheon/tools.ts +4 -0
- package/src/pantheon/tui-version-check.ts +1 -1
- package/src/pantheon/update-notifier.ts +13 -8
- package/src/pantheon/vision.ts +20 -20
- package/src/plugin/index.js +14594 -0
- package/src/plugins/tui/dist/tui.d.ts +3 -3
- package/src/plugins/tui/dist/tui.d.ts.map +1 -1
- package/src/plugins/tui/dist/tui.js +923 -340
- package/src/plugins/tui/dist/tui.js.map +1 -1
- package/src/plugins/tui/package-lock.json +2 -2
- package/src/plugins/tui/package.json +1 -1
- package/src/plugins/tui/src/autonomy-state.ts +27 -15
- package/src/plugins/tui/src/index.tsx +44 -23
- package/src/plugins/tui/src/pantheon-settings.tsx +461 -105
- package/src/plugins/tui/src/tui-prefs.ts +106 -4
- package/src/plugins/tui/src/update-notice.ts +9 -6
- package/src/plugins/tui/src/whats-new-open.ts +4 -4
- package/src/plugins/tui/src/whats-new.tsx +119 -17
- package/src/skills/agent-coordination/SKILL.md +6 -6
- package/src/skills/artifact-management/SKILL.md +43 -39
- package/src/skills/artifact-management/references/artifact-templates.md +103 -48
- package/src/skills/auto-continue/references/auto-continue-details.md +13 -13
- package/src/skills/code-review-checklist/SKILL.md +6 -6
- package/src/skills/incremental-implementation/SKILL.md +13 -13
- package/src/skills/memory-bank/references/anti-patterns.md +3 -3
- package/src/skills/spec-driven-development/SKILL.md +12 -14
- package/src/skills/tdd-with-agents/SKILL.md +6 -5
- package/src/skills/visual-review-pipeline/SKILL.md +1 -1
- package/src/skills/visual-review-pipeline/references/workflow-steps.md +1 -1
|
@@ -1,71 +1,126 @@
|
|
|
1
|
-
# Artifact Management — Templates
|
|
1
|
+
# Artifact Management — High-Density Templates
|
|
2
2
|
|
|
3
|
-
|
|
4
|
-
you need the `.tmp/` layout or a PLAN/IMPL/REVIEW template. Artifact types,
|
|
5
|
-
who-generates-what, proportional-use rules, pause points, and cleanup stay in
|
|
6
|
-
`SKILL.md`.
|
|
3
|
+
Companion reference for `SKILL.md`. Contains templates for architectural plans, executive reports, and ADRs.
|
|
7
4
|
|
|
8
5
|
---
|
|
9
6
|
|
|
10
|
-
##
|
|
7
|
+
## 1. Architectural Plan (`.pantheon/deepwork/<slug>/PLAN.md`)
|
|
11
8
|
|
|
12
|
-
|
|
9
|
+
Produced by `@athena`. Opens with an immediate Mermaid diagram and follows with dense, actionable phases:
|
|
13
10
|
|
|
14
|
-
```
|
|
15
|
-
|
|
16
|
-
├── .tmp/ ← GITIGNORED — ephemeral artifacts
|
|
17
|
-
│ ├── PLAN-<feature>.md
|
|
18
|
-
│ ├── IMPL-phase1-hermes.md
|
|
19
|
-
│ ├── IMPL-phase1-aphrodite.md
|
|
20
|
-
│ └── REVIEW-<feature>.md
|
|
21
|
-
├── _notes/ ← permanent ADRs; Git tracking follows repository policy
|
|
22
|
-
│ └── ADR-<topic>.md
|
|
23
|
-
├── 01-active-context.md
|
|
24
|
-
└── 02-progress-log.md
|
|
25
|
-
```
|
|
11
|
+
```markdown
|
|
12
|
+
# Architectural Plan: [Feature / Refactor Title]
|
|
26
13
|
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
or other files being tracked; `_tasks/` may be Git-ignored.
|
|
14
|
+
> [!NOTE]
|
|
15
|
+
> High-level context, background problem, and target outcome.
|
|
30
16
|
|
|
31
|
-
|
|
17
|
+
> [!IMPORTANT]
|
|
18
|
+
> Non-negotiable safety constraints, auth boundaries, or database schema requirements.
|
|
32
19
|
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
20
|
+
## 1. Visual Execution Flow
|
|
21
|
+
|
|
22
|
+
\`\`\`mermaid
|
|
23
|
+
flowchart TD
|
|
24
|
+
A["Requirement"] --> B["Phase 1: Backend (@hermes)"]
|
|
25
|
+
B --> C{"Lint & Slice Test Gate"}
|
|
26
|
+
C -- PASS --> D["Phase 2: Frontend (@aphrodite)"]
|
|
27
|
+
D --> E["Phase 3: Security & Code Audit (@themis)"]
|
|
28
|
+
\`\`\`
|
|
29
|
+
|
|
30
|
+
## 2. Quantitative Baseline & Impact
|
|
37
31
|
|
|
38
|
-
|
|
39
|
-
|
|
32
|
+
| Dimension | Before | Target | Verification Method |
|
|
33
|
+
|---|---|---|---|
|
|
34
|
+
| Latency | ~150s | < 2s | Sliced test runner |
|
|
35
|
+
| Token Overhead | ~20k | < 8k | Context telemetry |
|
|
36
|
+
| Affected Files | — | 3 files | Git diff check |
|
|
40
37
|
|
|
41
|
-
## Phases
|
|
42
|
-
1. Phase 1 — @hermes
|
|
43
|
-
2. Phase 2 — @aphrodite
|
|
38
|
+
## 3. Implementation Phases
|
|
44
39
|
|
|
45
|
-
|
|
46
|
-
-
|
|
40
|
+
### Phase 1: Core Implementation (@hermes)
|
|
41
|
+
- **Target Files:** `src/server/auth.ts`, `tests/auth.test.ts`
|
|
42
|
+
- **Actions:** RED -> GREEN -> REFACTOR implementation of the auth handler.
|
|
43
|
+
- **Validation Gate:** `node --test tests/auth.test.ts`
|
|
44
|
+
- **Exit Criteria:** All tests green; no Biome/Ruff lint warnings.
|
|
45
|
+
|
|
46
|
+
### Phase 2: Interface & Client (@aphrodite)
|
|
47
|
+
- **Target Files:** `src/ui/login.tsx`
|
|
48
|
+
- **Actions:** Connect UI state to new auth endpoint; ensure WCAG AA keyboard access.
|
|
49
|
+
- **Validation Gate:** `npx biome check src/ui/login.tsx`
|
|
50
|
+
|
|
51
|
+
## 4. Risks & Contingency
|
|
52
|
+
|
|
53
|
+
| Identified Risk | Impact | Contingency / Mitigation |
|
|
54
|
+
|---|---|---|
|
|
55
|
+
| Breaking change to legacy clients | High | Preserve backwards-compatible endpoint alias for 1 release |
|
|
56
|
+
| Token spike in subagent cascade | Medium | Use direct specialist dispatch without intermediate hops |
|
|
47
57
|
```
|
|
48
58
|
|
|
49
|
-
|
|
59
|
+
---
|
|
60
|
+
|
|
61
|
+
## 2. Executive Report & Analysis (`.pantheon/reports/<YYYY-MM-DD>-<topic>.md`)
|
|
62
|
+
|
|
63
|
+
Produced by `@apollo` (deep discovery) or `@themis` (quality/security audits):
|
|
64
|
+
|
|
50
65
|
```markdown
|
|
51
|
-
#
|
|
52
|
-
**Date:** YYYY-MM-DD **Status:** Awaiting Themis Review
|
|
66
|
+
# Executive Report: [Analysis Topic]
|
|
53
67
|
|
|
54
|
-
|
|
55
|
-
|
|
68
|
+
> [!NOTE]
|
|
69
|
+
> Summary of findings and systemic conclusions.
|
|
56
70
|
|
|
57
|
-
|
|
58
|
-
|
|
71
|
+
> [!TIP]
|
|
72
|
+
> Key optimization opportunities and quick wins.
|
|
73
|
+
|
|
74
|
+
## 1. Architecture / System Topology
|
|
75
|
+
|
|
76
|
+
\`\`\`mermaid
|
|
77
|
+
graph LR
|
|
78
|
+
Client["Client Host"] --> Gateway["Decision Router"]
|
|
79
|
+
Gateway --> Specialist["Domain Specialist"]
|
|
80
|
+
\`\`\`
|
|
81
|
+
|
|
82
|
+
## 2. Metrics & Comparison
|
|
83
|
+
|
|
84
|
+
| Metric | Current State | Target / Proposed | Delta (%) |
|
|
85
|
+
|---|---|---|---|
|
|
86
|
+
| Test Latency | 150.000ms | 50ms | -99.9% |
|
|
87
|
+
| Initial Context | 19.877 tokens | 7.500 tokens | -62.2% |
|
|
88
|
+
|
|
89
|
+
## 3. Findings & Evidence
|
|
90
|
+
- Detailed finding 1 with exact file citations.
|
|
91
|
+
- Detailed finding 2 with reproducible evidence.
|
|
92
|
+
|
|
93
|
+
## 4. Prioritized Recommendations
|
|
94
|
+
1. Actionable item 1 (low effort, high impact)
|
|
95
|
+
2. Actionable item 2 (medium effort)
|
|
59
96
|
```
|
|
60
97
|
|
|
61
|
-
|
|
98
|
+
---
|
|
99
|
+
|
|
100
|
+
## 3. Architectural Decision Record (`docs/adr/<NNN>-<slug>.md`)
|
|
101
|
+
|
|
102
|
+
Produced by `@mnemosyne`:
|
|
103
|
+
|
|
62
104
|
```markdown
|
|
63
|
-
#
|
|
64
|
-
|
|
105
|
+
# ADR-[NNN]: [Decision Title]
|
|
106
|
+
|
|
107
|
+
**Date:** YYYY-MM-DD
|
|
108
|
+
**Status:** [Proposed | Accepted | Superseded]
|
|
109
|
+
|
|
110
|
+
> [!IMPORTANT]
|
|
111
|
+
> Decision impacts: [Core systems / architecture / protocols].
|
|
112
|
+
|
|
113
|
+
## Context
|
|
114
|
+
What problem was being solved? What forces or constraints applied?
|
|
115
|
+
|
|
116
|
+
## Decision
|
|
117
|
+
What was decided? Which approach was chosen over the alternatives?
|
|
65
118
|
|
|
66
|
-
##
|
|
67
|
-
|
|
119
|
+
## Alternatives Considered
|
|
120
|
+
- **Alternative A:** [Reason rejected]
|
|
121
|
+
- **Alternative B:** [Reason rejected]
|
|
68
122
|
|
|
69
|
-
##
|
|
70
|
-
-
|
|
123
|
+
## Consequences
|
|
124
|
+
- **Positive:** [Benefits gained]
|
|
125
|
+
- **Negative / Trade-offs:** [Costs or constraints accepted]
|
|
71
126
|
```
|
|
@@ -51,12 +51,12 @@ whether partial results are acceptable. It is force-fed into every session via `
|
|
|
51
51
|
skill is opt-in. Do not restate those values here — a copy in this skill is precisely what drifted
|
|
52
52
|
out of sync with them. If a dispatch times out, read the role's row from the instruction file.
|
|
53
53
|
|
|
54
|
-
###
|
|
54
|
+
### Partial Results on Timeout
|
|
55
55
|
|
|
56
56
|
Whether an agent may return partial results is the **Partial Results OK?** column in that table.
|
|
57
|
-
Only agents marked
|
|
57
|
+
Only agents marked YES there may return partial — never implementers, never reviewers.
|
|
58
58
|
|
|
59
|
-
**How to signal timeout
|
|
59
|
+
**How to signal partial timeout:**
|
|
60
60
|
When dispatching, set the expectation explicitly:
|
|
61
61
|
```
|
|
62
62
|
@apollo Search for all auth-related files. If you hit timeout, return whatever you have found so far — partial results are acceptable.
|
|
@@ -68,8 +68,8 @@ Maintain an in-context (not persistent/native) checklist of delegations when nee
|
|
|
68
68
|
|
|
69
69
|
| Agent | Started | Timeout | Status | Partial OK? |
|
|
70
70
|
|-------|---------|---------|--------|-------------|
|
|
71
|
-
| apollo | T+0s | T+60s |
|
|
72
|
-
| hermes | T+0s | T+180s |
|
|
71
|
+
| apollo | T+0s | T+60s | complete | YES |
|
|
72
|
+
| hermes | T+0s | T+180s | in progress | NO |
|
|
73
73
|
|
|
74
74
|
---
|
|
75
75
|
|
|
@@ -77,23 +77,23 @@ Maintain an in-context (not persistent/native) checklist of delegations when nee
|
|
|
77
77
|
|
|
78
78
|
**Good (auto-continues):**
|
|
79
79
|
```
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
80
|
+
Wrote migration file.
|
|
81
|
+
-> Running migration tests...
|
|
82
|
+
Tests pass (3/3).
|
|
83
|
+
-> Next: write UserRepository query methods.
|
|
84
84
|
```
|
|
85
85
|
|
|
86
86
|
**Good (stops at Gate 2):**
|
|
87
87
|
```
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
- Coverage: 87%
|
|
88
|
+
Phase 1 complete: migration + repository layer.
|
|
89
|
+
GATE 2 — Themis review summary:
|
|
90
|
+
- Coverage: 87% | No OWASP issues
|
|
91
91
|
Ready for Phase 2? Waiting for go-ahead.
|
|
92
92
|
```
|
|
93
93
|
|
|
94
94
|
**Bad (stops unnecessarily):**
|
|
95
95
|
```
|
|
96
|
-
|
|
96
|
+
Wrote the migration file.
|
|
97
97
|
Should I now run the migration tests? [waiting]
|
|
98
98
|
```
|
|
99
99
|
|
|
@@ -52,7 +52,7 @@ Run the itemized pass (Correctness, Code Quality, Testing, Security/OWASP, Docum
|
|
|
52
52
|
- [HIGH] component.tsx:15 — Missing input validation
|
|
53
53
|
- [MEDIUM] test_utils.py:8 — Edge case not covered
|
|
54
54
|
|
|
55
|
-
###
|
|
55
|
+
### Human Review Focus
|
|
56
56
|
1. [Item AI cannot fully validate — e.g., business logic correctness]
|
|
57
57
|
2. [Item 2 — e.g., UX flow matches requirements]
|
|
58
58
|
```
|
|
@@ -86,11 +86,11 @@ For comprehensive reviews, run 5 checks simultaneously:
|
|
|
86
86
|
|
|
87
87
|
## Anti-Patterns
|
|
88
88
|
|
|
89
|
-
-
|
|
90
|
-
-
|
|
91
|
-
-
|
|
92
|
-
-
|
|
93
|
-
-
|
|
89
|
+
- Reviewing entire file instead of diff
|
|
90
|
+
- Approving without running tests
|
|
91
|
+
- Ignoring security implications
|
|
92
|
+
- Vague feedback ("looks good", "needs work")
|
|
93
|
+
- Nitpicking style over substance
|
|
94
94
|
|
|
95
95
|
---
|
|
96
96
|
|
|
@@ -5,23 +5,23 @@ description: "Implement in thin vertical slices — one commit per task, testabl
|
|
|
5
5
|
|
|
6
6
|
# Incremental Implementation
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
Build in thin, testable vertical slices. One commit per task.
|
|
9
9
|
|
|
10
10
|
## Rules
|
|
11
|
-
1.
|
|
12
|
-
2.
|
|
13
|
-
3.
|
|
14
|
-
4.
|
|
11
|
+
1. Each slice delivers independently testable value.
|
|
12
|
+
2. One commit per slice with tests passing.
|
|
13
|
+
3. If a slice exceeds 50 changed lines, split it into smaller tasks.
|
|
14
|
+
4. Rolling back a slice must not break previous slices.
|
|
15
15
|
|
|
16
16
|
## Slice Pattern
|
|
17
17
|
```
|
|
18
|
-
Slice 1 — Schema
|
|
19
|
-
Slice 2 — API endpoint (
|
|
20
|
-
Slice 3 — Frontend component (mock API
|
|
21
|
-
Slice N —
|
|
18
|
+
Slice 1 — Schema and data model (migration up/down tested)
|
|
19
|
+
Slice 2 — API endpoint (test -> implementation -> refactor)
|
|
20
|
+
Slice 3 — Frontend component (mock API -> UI -> integration)
|
|
21
|
+
Slice N — E2E integration (happy path + edge cases)
|
|
22
22
|
```
|
|
23
23
|
|
|
24
|
-
## Anti-
|
|
25
|
-
-
|
|
26
|
-
-
|
|
27
|
-
-
|
|
24
|
+
## Anti-Patterns
|
|
25
|
+
- Horizontal slicing (building the entire backend before touching frontend).
|
|
26
|
+
- Mega-commits of 500+ lines.
|
|
27
|
+
- Implementing changes without prior test verification (RED -> GREEN).
|
|
@@ -6,7 +6,7 @@ pattern violates the memory-bank rules. The golden rules themselves stay in
|
|
|
6
6
|
|
|
7
7
|
---
|
|
8
8
|
|
|
9
|
-
###
|
|
9
|
+
### Anti-Pattern: Session output as files
|
|
10
10
|
```
|
|
11
11
|
# Wrong
|
|
12
12
|
Create IMPLEMENTATION_SUMMARY.md
|
|
@@ -16,7 +16,7 @@ Create STATUS.md
|
|
|
16
16
|
@mnemosyne Append to 02-progress-log.md: [summary]
|
|
17
17
|
```
|
|
18
18
|
|
|
19
|
-
###
|
|
19
|
+
### Anti-Pattern: Mandatory handoff after every phase
|
|
20
20
|
```
|
|
21
21
|
# Wrong: After every phase → handoff to @mnemosyne
|
|
22
22
|
|
|
@@ -24,7 +24,7 @@ Create STATUS.md
|
|
|
24
24
|
At sprint close → explicit @mnemosyne invocation
|
|
25
25
|
```
|
|
26
26
|
|
|
27
|
-
###
|
|
27
|
+
### Anti-Pattern: Duplicating information
|
|
28
28
|
```
|
|
29
29
|
# Wrong: duplicate the same fact in both durable Memory and a project document
|
|
30
30
|
|
|
@@ -1,25 +1,23 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: spec-driven-development
|
|
3
|
-
description: "Define requirements via spec-first before
|
|
3
|
+
description: "Define requirements via spec-first before code — PRD, edge cases, acceptance criteria"
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# Spec-Driven Development
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
Do not write code before understanding the problem.
|
|
9
9
|
|
|
10
10
|
## Workflow
|
|
11
|
-
1.
|
|
12
|
-
2.
|
|
13
|
-
3.
|
|
14
|
-
4.
|
|
15
|
-
5.
|
|
16
|
-
planejamento veio de um subagente, devolva o plano integral ao orquestrador
|
|
17
|
-
para que ele o exiba na conversa principal antes de pedir aprovação.
|
|
11
|
+
1. Interview: Extract requirements with iterative questions to resolve ambiguity.
|
|
12
|
+
2. PRD: Document core requirements: objective, personas, user flows, business rules, and acceptance criteria.
|
|
13
|
+
3. Edge Cases: Map invalid inputs, concurrency, API failures, and empty states.
|
|
14
|
+
4. Technical Spec: Document architectural decisions: components, data models, API contracts, and deployment.
|
|
15
|
+
5. Approval: Present the complete plan to the user before writing code. When planning was executed in a subagent, return the full plan to the orchestrator so it displays in the main conversation before requesting approval.
|
|
18
16
|
|
|
19
|
-
## Anti-
|
|
20
|
-
-
|
|
21
|
-
-
|
|
22
|
-
-
|
|
17
|
+
## Anti-Patterns
|
|
18
|
+
- Jumping straight into implementation without requirements.
|
|
19
|
+
- Assuming requirements without confirmation.
|
|
20
|
+
- Overly verbose specifications (5+ pages) — keep specs concise and actionable.
|
|
23
21
|
|
|
24
22
|
## Output
|
|
25
|
-
`spec.md`
|
|
23
|
+
`spec.md` at project root or `.pantheon/deepwork/<feature>/PLAN.md` — used as input for planning.
|
|
@@ -79,11 +79,12 @@ Use RED → GREEN → REFACTOR for behavior-changing implementation where a mean
|
|
|
79
79
|
|
|
80
80
|
## Anti-Patterns
|
|
81
81
|
|
|
82
|
-
-
|
|
83
|
-
- Anti-pattern:
|
|
84
|
-
- Anti-pattern:
|
|
85
|
-
- Anti-pattern:
|
|
86
|
-
- Anti-pattern:
|
|
82
|
+
- Proportionality: TDD (RED -> GREEN -> REFACTOR) is mandatory for testable behavior, business logic, and security; glue code, configuration, documentation, and UI/CSS adjustments do not require test-first creation.
|
|
83
|
+
- Anti-pattern: Creating test ceremonies for trivial configuration or formatting tasks.
|
|
84
|
+
- Anti-pattern: Testing private implementation details or creating tight coupling.
|
|
85
|
+
- Anti-pattern: Excessive I/O mocking instead of direct integration tests.
|
|
86
|
+
- Anti-pattern: Ignoring test failures without diagnosing the diff.
|
|
87
|
+
- Anti-pattern: Running the entire test suite for bounded local changes.
|
|
87
88
|
|
|
88
89
|
---
|
|
89
90
|
|
|
@@ -73,7 +73,7 @@ Zeus must be invoked when:
|
|
|
73
73
|
- Use `browser/snapshot` for accessibility tree context
|
|
74
74
|
- Fallback: If Playwright MCP is unavailable, skip with warning:
|
|
75
75
|
```
|
|
76
|
-
|
|
76
|
+
[WARN] Playwright MCP unavailable — visual review skipped.
|
|
77
77
|
Install Playwright MCP server to enable visual review pipeline.
|
|
78
78
|
```
|
|
79
79
|
For UI implementation review, Aphrodite self-reviews.
|
|
@@ -70,7 +70,7 @@ Iteration N:
|
|
|
70
70
|
- Use `browser/snapshot` for accessibility tree context
|
|
71
71
|
- Fallback: If Playwright MCP is unavailable, skip with warning:
|
|
72
72
|
```
|
|
73
|
-
|
|
73
|
+
[WARN] Playwright MCP unavailable — visual review skipped.
|
|
74
74
|
Install Playwright MCP server to enable visual review pipeline.
|
|
75
75
|
```
|
|
76
76
|
For UI implementation review, Aphrodite self-reviews.
|