pantheon-opencode 1.6.0-beta.1 → 1.6.0-beta.10

package/src/skills/session-goal/SKILL.md

@@ -14,10 +14,10 @@ Use this skill to pin a session objective at the start of a long or complex sess
 
 ## Usage
 
-Invoke via the `/focus` command:
+Invoke via the `/pantheon-focus` command (a conversation-only goal anchor):
 
 ```
-/focus Implement JWT authentication with refresh token rotation
+/pantheon-focus Implement JWT authentication with refresh token rotation
 ```
 
 Or state it explicitly at the start of a session:
@@ -70,9 +70,18 @@ Before each major delegation or decision, run this quick check:
 
 ---
 
-## Cross-Session Persistence
+## Cross-Session Continuity
 
-For goals that span multiple sessions, write the goal to `/memories/session/`:
+V2 does not provide durable goal tools. `/pantheon-focus` only anchors the current
+conversation and must not be described as surviving compaction or a new
+session. For multi-phase work that needs persistent checkpoints, use
+`/pantheon-deepwork`; otherwise ask before writing a goal to a project file.
+
+In V1, use the implemented goal tools when they are available and explicitly
+authorized. Do not infer that their presence in one host generation means they
+exist in V2.
+
+Historical path example (not a V2 runtime command):
 
 ```
 /memories/session/current-goal.md
@@ -84,7 +93,7 @@ Status: Phase 2 of 3 (backend done, frontend in progress)
 Next: POST /auth/refresh endpoint
 ```
 
-This ensures the goal survives context compaction and session restarts.
+This file-based approach requires explicit authorization and is not automatic.
 
 ---
 

package/src/skills/spec-driven-development/SKILL.md

@@ -12,7 +12,9 @@ description: "Define requirements via spec-first before any code — PRD, edge c
 2. **PRD** — Escreva um documento de requisitos: objetivo, personas, fluxos, regras de negócio, critérios de aceitação
 3. **Edge Cases** — Mapeie entradas inválidas, concorrência, falhas de API, estados vazios
 4. **Technical Spec** — Decisões de arquitetura: componentes, dados, API contracts, deploy
-5. **Approval** — Apresente ao usuário antes de codar. "É isso mesmo?"
+5. **Approval** — Apresente o plano completo ao usuário antes de codar. Se o
+   planejamento veio de um subagente, devolva o plano integral ao orquestrador
+   para que ele o exiba na conversa principal antes de pedir aprovação.
 
 ## Anti-patterns
 - ❌ Pular direto pra implementação

package/src/skills/tdd-with-agents/SKILL.md

@@ -8,13 +8,21 @@ alwaysApply: false
 
 # TDD with Agents
 
-Enforce RED → GREEN → REFACTOR cycle across all implementation agents. Includes advanced testing patterns for E2E, load, mutation, and contract testing.
+Use RED → GREEN → REFACTOR for behavior-changing implementation where a meaningful test can express the change. Keep verification proportional to the changed surface and risk; advanced testing patterns are reserved for changes that warrant them.
 
 ---
 
 ## Core Principle
 
-> **Write the test FIRST. Watch it fail. Write minimal code to pass. Refactor with confidence.**
+> **For testable behavior changes, write the focused test first, observe RED, implement minimally, then refactor.**
+
+## Proportional TDD
+
+- Use the complete RED → GREEN → REFACTOR cycle for new or changed behavior when a focused test is practical. Include a focused regression check for bug fixes.
+- For typo, formatting, documentation-only, or otherwise non-behavioral edits, do not invent a test; inspect the diff and run the narrowest relevant validation.
+- Run targeted tests for a small change. Run broader suites when the changed surface, integration boundaries, or risk make them useful; do not run the whole suite solely because one line changed.
+- If a relevant existing test already captures the behavior, use it instead of adding a duplicate. If no automated check can express the change, report the manual or static verification performed.
+- Auth, security, payment, data-integrity, and schema/migration changes retain focused RED/GREEN tests, required regression coverage, and Themis review. Do not weaken a project-specific required safety gate.
 
 ---
 
@@ -112,12 +120,12 @@ def test_provider_satisfies_consumer_contract():
     pass
 ```
 
-### Mutation Testing
+### Mutation Testing (high-risk/critical logic only)
 - Mutate source code (change `>` to `<`, remove conditions)
 - Run tests → should fail (mutation killed)
 - If tests pass → test is weak; improve it
 
-### Visual Regression
+### Visual Regression (visual behavior only)
 ```typescript
 test('homepage looks the same', async ({ page }) => {
   await page.goto('/')
@@ -129,8 +137,8 @@ test('homepage looks the same', async ({ page }) => {
 
 ## Coverage Rules
 
-- **Minimum: 80%** for all code
-- **Critical paths: 100%** (auth, payments, data integrity)
+- Follow a repository's explicit coverage threshold when the changed code is in its measurement scope; do not manufacture a coverage target for docs, formatting, or a tiny isolated edit.
+- **Critical paths:** preserve project-required coverage and tests for auth, payments, and data integrity.
 - **No snapshot testing** — test behavior, not output shape
 - **Test edge cases**: empty input, null, boundary values, errors
 
@@ -143,20 +151,20 @@ test('homepage looks the same', async ({ page }) => {
 | **Hermes** | Unit + integration for FastAPI endpoints, services, middleware |
 | **Aphrodite** | Component behavior tests with React Testing Library |
 | **Demeter** | Migration upgrade/downgrade, query correctness |
-| **Themis** | Verifies coverage ≥80%, edge cases tested, error conditions |
+| **Themis** | Reviews the changed surface, relevant edge/error cases, and applicable repository coverage requirements; always review sensitive/material changes |
 
 ---
 
 ## Workflow
 
 ```
-1. Zeus/Athena defines feature with testable acceptance criteria
+1. Use a plan/spec only when scope, risk, or ambiguity warrants it; a bounded fix may proceed directly
 2. Hermes writes failing test (RED)
 3. Hermes implements minimal code (GREEN)
 4. Hermes refactors (REFACTOR)
 5. Aphrodite writes frontend tests in parallel
-6. Themis reviews: coverage, edge cases, correctness
-7. If coverage <80% → NEEDS_REVISION
+6. Themis reviews sensitive or material changes, checking changed behavior and applicable quality gates
+7. Escalate unmet repository or safety-critical test requirements; do not fail a micro-edit against an unrelated global coverage figure
 ```
 
 ---

package/opencode.json

@@ -1,58 +0,0 @@
-{
-  "$schema": "https://opencode.ai/config.json",
-  "provider": {
-    "opencode-go": {
-      "models": {
-        "mimo-v2.5": {
-          "attachment": true,
-          "modalities": { "input": ["text", "image"] }
-        }
-      }
-    }
-  },
-  "default_agent": "zeus",
-  "plugins": ["src/plugin-v2"],
-  "experimental": {
-    "subagent_depth": 2
-  },
-  "permission": {
-    "skill": {
-      "*": "allow"
-    },
-    "websearch": "deny",
-    "bash": {
-      "git *": "allow",
-      "npm *": "allow",
-      "npx *": "allow",
-      "pytest *": "allow",
-      "ruff *": "allow",
-      "pip *": "allow",
-      "python3 *": "allow"
-    }
-  },
-  "mcp": {
-    "bifrost": {
-      "type": "remote",
-      "url": "https://llm.ofertachina.cloud/mcp",
-      "enabled": true
-    }
-  },
-  "agent": {
-    "talos": {
-      "permission": {
-        "edit": {
-          "*": "allow",
-          "**/migrations/**": "deny",
-          "**/alembic/**": "deny",
-          "**/models/**": "deny",
-          "**/auth/**": "deny",
-          "**/*.sql": "deny"
-        },
-        "bash": {
-          "*": "allow",
-          "alembic *": "deny"
-        }
-      }
-    }
-  }
-}