planflow-ai 1.3.4 → 1.3.5

package/.claude/commands/flow.md

@@ -39,7 +39,7 @@ SETTINGS:
   commit=true|false      Auto-commit after each completed phase (default: false)
   push=true|false        Auto-push after all phases + build/test pass (default: false)
   branch=<name>          Target branch for git operations (default: current branch)
-  model_routing=true|false  Auto-select model per phase based on complexity (default: true)
+  model_routing=true|false  Auto-select model per phase based on complexity (default: false)
   phase_isolation=true|false  Run each phase in isolated sub-agent with clean context (default: true)
 
 COST REPORTING:
@@ -111,7 +111,7 @@ Parse the user input to determine what action to take:
 | `commit` | `true`, `false` | `false` | Auto-commit after each phase |
 | `push` | `true`, `false` | `false` | Auto-push after completion |
 | `branch` | any string | current branch | Target branch for git ops |
-| `model_routing` | `true`, `false` | `true` | Auto-select model per phase based on complexity |
+| `model_routing` | `true`, `false` | `false` | Auto-select model per phase based on complexity |
 | `phase_isolation` | `true`, `false` | `true` | Run each phase in isolated sub-agent with clean context |
 
 ---
@@ -242,7 +242,7 @@ autopilot: false
 commit: false
 push: false
 branch: ""
-model_routing: true
+model_routing: false
 phase_isolation: true
 ```
 

package/.claude/resources/core/model-routing.md

@@ -7,7 +7,7 @@ Automatic model selection at phase boundaries during `/execute-plan`. Each phase
 
 **Scope**: `/execute-plan` only. Other skills (discovery, review, brainstorm) do not have pre-defined complexity scores and are not routed.
 
-**Config**: Controlled by `model_routing` key in `flow/.flowconfig` (default: `true`). Set `model_routing: false` to disable.
+**Config**: Controlled by `model_routing` key in `flow/.flowconfig` (default: `false`). Set `model_routing: true` to enable.
 
 ---
 
@@ -23,12 +23,16 @@ Automatic model selection at phase boundaries during `/execute-plan`. Each phase
 
 ## Platform Mappings
 
+Always use the **latest and most capable model** from each provider. Model names below are examples — always prefer the most recent version available at runtime.
+
 | Tier | Claude Code | Codex (OpenAI) | Cursor |
 |------|------------|----------------|--------|
 | Fast | `haiku` | `gpt-4.1-mini` | auto (fast) |
 | Standard | `sonnet` | `gpt-4.1` | auto (normal) |
 | Powerful | `opus` | `o3` | auto (max) |
 
+**Default model (when routing is OFF)**: Always use the most capable/recent model from the active provider — e.g., `opus` for Anthropic, `o3` for OpenAI. This is the default behavior.
+
 **Fallback rule**: If a platform doesn't support a tier, fall back to the next tier up (e.g., if no haiku equivalent, use Standard).
 
 ---
@@ -37,7 +41,7 @@ Automatic model selection at phase boundaries during `/execute-plan`. Each phase
 
 ### At Each Phase Boundary
 
-1. **Check config**: Read `model_routing` from `flow/.flowconfig`. If `false` or missing key, skip routing (use session default).
+1. **Check config**: Read `model_routing` from `flow/.flowconfig`. If `false`, missing key, or not set, skip routing (use the most capable session model — this is the default).
 2. **Read complexity**: Get the phase's complexity score from the plan file.
 3. **Look up tier**: Map score to tier using the table above.
 4. **Spawn subagent**: Use the Agent tool with `model={tier_model}` to implement the phase.

package/.claude/resources/skills/execute-plan-skill.md

@@ -189,11 +189,11 @@ Wait for user confirmation before proceeding.
 1. **Auto-switch to Plan mode** - Call `SwitchMode` tool
 2. **Present phase details** - Show scope, tasks, and approach
 3. **Wait for approval** - Get user confirmation
-4. **Select model tier** - If `model_routing` is enabled in `flow/.flowconfig` (default: `true`):
+4. **Select model tier** - If `model_routing` is enabled in `flow/.flowconfig` (default: `false` — uses the most capable session model):
    - Read the phase's complexity score
    - Look up model tier: **0-3 → Fast (haiku)**, **4-5 → Standard (sonnet)**, **6-10 → Powerful (opus)**
    - For aggregated phases, use the **highest individual phase complexity** to determine the tier
-   - If `model_routing` is `false` or key is missing, skip routing (use session model)
+   - If `model_routing` is `false` or key is missing, skip routing (use the most capable model from the active provider — e.g., opus for Anthropic, o3 for OpenAI)
    - See `.claude/resources/core/model-routing.md` for full tier table, platform mappings, and rules
 5. **Inject design context** - Before implementing, check if the discovery doc (from plan's "Based on Discovery" field) has a `## Design Context` section. If present and the phase involves UI work (see UI Phase Detection Heuristics in `.claude/resources/core/design-awareness.md`), include the Design Context in the implementation prompt. If no Design Context or phase is not UI-related, skip this step.
 6. **Implement (with phase isolation)** - Check `phase_isolation` in `flow/.flowconfig` (default: `true`):

package/.claude/rules/core/forbidden-patterns.md

@@ -256,4 +256,42 @@ const badExample = problematicCode()
 
 ## Project Anti-Patterns
 
+### 6. DON'T Execute ORM/Database Migration Commands Directly
+
+**Problem**: Running ORM tools (Prisma, Drizzle, TypeORM, Sequelize, Knex, Django ORM, Alembic, etc.) directly can cause irreversible data loss, schema corruption, or unintended migrations in production environments.
+
+```bash
+# BAD - Never run these directly
+npx prisma migrate dev
+npx prisma db push
+npx prisma db seed
+npx drizzle-kit push
+npx drizzle-kit migrate
+npx typeorm migration:run
+python manage.py migrate
+alembic upgrade head
+npx knex migrate:latest
+```
+
+**Why This is Wrong**:
+
+- Database migrations can be destructive and irreversible (dropping columns, tables, data)
+- ORM commands may connect to production databases if environment is misconfigured
+- Schema changes need human review before execution
+- Seed commands can overwrite existing data
+- The AI agent has no way to verify which database environment it's targeting
+
+**Fix**: Always present the command to the user and ask them to execute it manually.
+
+```markdown
+<!-- GOOD - Ask the user to run it -->
+"Please run the following command to apply the migration:"
+
+`npx prisma migrate dev --name add_users_table`
+
+"Review the generated migration SQL before confirming."
+```
+
+**Scope**: This applies to ALL ORM and database tools — Prisma, Drizzle, TypeORM, Sequelize, Knex, Django ORM, Alembic, SQLAlchemy, ActiveRecord, and any other database migration or seeding tool.
+
 <!-- auto-captured anti-patterns below this line -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "planflow-ai",
-  "version": "1.3.4",
+  "version": "1.3.5",
   "description": "Structured AI-assisted development workflows for discovery, planning, execution, code reviews, and testing",
   "type": "module",
   "main": "dist/cli/index.js",