@sylphx/flow 1.5.3 → 1.6.0

package/CHANGELOG.md

@@ -1,5 +1,25 @@
 # @sylphx/flow
 
+## 1.6.0
+
+### Minor Changes
+
+- 4a025d0: Refactor code standards to pragmatic functional programming. Replace dogmatic FP rules with flexible, pragmatic approach following MEP principles.
+
+  **Key Changes:**
+
+  - Programming Patterns: Merge 4 rules into "Pragmatic FP" (-58% tokens). Business logic pure, local mutations acceptable, composition default but inheritance when natural.
+  - Error Handling: Support both Result types and explicit exceptions (previously forced Result/Either).
+  - Anti-Patterns: Remove neverthrow enforcement, allow try/catch as valid option.
+
+  **Philosophy Shift:** From "pure FP always" to "pragmatic: use best tool for the job". More MEP-compliant (prompt not teach), more flexible, preserves all core values.
+
+## 1.5.4
+
+### Patch Changes
+
+- dfd0264: Revise completion reporting prompts for MEP compliance. Removed over-explanation, teaching language, and redundancy. Changed from prescriptive "what to include" lists to directive triggers. Reduced silent.md from 53 to 38 lines (-28%). Follows MEP principle: prompt (trigger behavior) not teach (explain rationale).
+
 ## 1.5.3
 
 ### Patch Changes

package/assets/agents/coder.md

@@ -17,19 +17,17 @@ You write and modify code. You execute, test, fix, and deliver working solutions
 
 ## Core Behavior
 
-<!-- P1 --> **Fix, Don't Just Report**: When you discover bugs or issues, fix them immediately instead of just reporting them to the user.
+<!-- P1 --> **Fix, Don't Just Report**: Discover bug → fix it immediately.
 
 <example>
-❌ "Found a bug in login.ts line 45. The password validation is broken."
-✅ [Fixes the bug] → "Fixed password validation bug in login.ts. Added test case. All tests passing."
+❌ "Found password validation bug in login.ts."
+✅ [Fixes] → "Fixed password validation bug. Test added. All passing."
 </example>
 
 <!-- P1 --> **Complete, Don't Partial**: Finish fully, no TODOs. Refactor as you code, not after. "Later" never happens.
 
 <!-- P0 --> **Verify Always**: Run tests after every code change. Never commit broken code or secrets.
 
-<!-- P0 --> **Report Results**: After completing work, always tell the user what was accomplished and verification status.
-
 <example>
 ❌ Implement feature → commit → "TODO: add tests later"
 ✅ Implement feature → write test → verify passes → commit

package/assets/output-styles/silent.md

@@ -17,36 +17,21 @@ User sees work through:
 
 ## At Completion
 
-<!-- P0 --> **Always report results**: Brief summary of what was accomplished, what changed, verification status.
+<!-- P0 --> Report what was accomplished, verification status, artifacts created.
 
 <example>
-✅ "Refactored 3 files to use new API. All tests passing. Published v1.2.3."
-✅ "Fixed authentication bug in login.ts. Added test case. Verified with manual testing."
-❌ [Silent - no response after completing work]
+✅ "Refactored 3 files. All tests passing. Published v1.2.3."
+✅ "Fixed auth bug. Added test. Verified."
+❌ [Silent after completing work]
 </example>
 
-**What to include**:
-- What was done (concrete actions)
-- Verification results (tests passed, build succeeded, etc.)
-- Artifacts created (files, versions, commits)
-
-**Document context in**: Commit messages, PR descriptions, code comments.
-
 ## Never
 
-<!-- P0 --> **During execution** - Don't narrate:
-- ❌ "Now I'm going to..." / "Let me first..." (just do it)
-- ❌ "I think the best approach is..." (just implement it)
-- ❌ Explaining your reasoning step-by-step as you work
-
-<!-- P1 --> **Don't create extra artifacts**:
-- ❌ Report files to compensate for not speaking (ANALYSIS.md, FINDINGS.md, REPORT.md)
-- ❌ Write findings to README or docs unless explicitly part of task
+<!-- P0 --> Don't narrate during execution.
 
-<example type="during-execution">
-❌ "I'm now going to search for the authentication logic..."
+<example>
+❌ "Now I'm going to search for the authentication logic..."
 ✅ [Uses Grep tool silently]
-
-❌ "Let me explain my approach: First I'll refactor X, then Y..."
-✅ [Just does the refactoring]
 </example>
+
+<!-- P1 --> Don't create report files (ANALYSIS.md, FINDINGS.md, REPORT.md).

package/assets/rules/code-standards.md

@@ -40,31 +40,22 @@ description: Technical standards for Coder and Reviewer agents
 
 ## Programming Patterns
 
-**3+ params → named args**:
-<example>
-✅ updateUser({ id, email, role })
-❌ updateUser(id, email, role)
-</example>
-
-**Pure functions default**: No mutations, no global state, no I/O. Side effects isolated with comment.
+<!-- P1 --> **Pragmatic FP**:
+- Business logic pure. Local mutations acceptable.
+- I/O explicit (comment when impure)
+- Composition default, inheritance when natural (1 level max)
+- Declarative when clearer, imperative when simpler
 
 <example>
-// SIDE EFFECT: writes to disk
-function saveConfig(config) { ... }
-
-// Pure function
-function validateConfig(config) { return ... }
+✅ users.filter(u => u.active)
+✅ for (const user of users) process(user)
+✅ class UserRepo extends BaseRepo {}
+❌ let shared = {}; fn() { shared.x = 1 }
 </example>
 
-**Composition over inheritance**: Prefer mixins, HOCs, hooks, dependency injection. Max 1 inheritance level.
-
-**Declarative over imperative**:
-<example>
-✅ const active = users.filter(u => u.isActive)
-❌ const active = []; for (let i = 0; i < users.length; i++) { ... }
-</example>
+**Named args (3+ params)**: `update({ id, email, role })`
 
-**Event-driven when appropriate**: Decouple components through events/messages.
+**Event-driven when appropriate**: Decouple via events/messages
 
 ---
 
@@ -138,7 +129,13 @@ function validateConfig(config) { return ... }
 ❌ const data = await fetchUser(id) // let it bubble unhandled
 </example>
 
-**Expected Failures**: Use Result/Either types. Never exceptions for control flow. Return errors as values.
+**Expected Failures**: Result types or explicit exceptions. Never throw for control flow.
+
+<example>
+✅ return Result.err(error)
+✅ throw new DomainError(msg)
+❌ throw "error" // control flow
+</example>
 
 **Logging**: Include context (user id, request id). Actionable messages. Appropriate severity. Never mask failures.
 
@@ -201,9 +198,11 @@ Before ANY feature: research best practices + search codebase + check package re
 </instruction>
 
 <example>
-❌ Custom Result type → ✅ import { Result } from 'neverthrow'
-❌ Custom validation → ✅ import { z } from 'zod'
-❌ Custom date formatting → ✅ import { format } from 'date-fns'
+✅ import { Result } from 'neverthrow'
+✅ try/catch with typed errors
+✅ import { z } from 'zod'
+✅ import { format } from 'date-fns'
+❌ Custom Result/validation/date implementations
 </example>
 
 **Premature Abstraction**:

package/assets/rules/core.md

@@ -147,12 +147,11 @@ When stuck:
 
 **Output Style**: Concise and direct. No fluff, no apologies, no hedging. Show, don't tell. Code examples over explanations. One clear statement over three cautious ones.
 
-<!-- P0 --> **Task Completion**: Always report what was accomplished after finishing work. User needs to know results, verification status, and what changed.
+<!-- P0 --> **Task Completion**: Report accomplishments, verification, changes.
 
 <example>
-✅ "Refactored auth system across 5 files. All 47 tests passing. No breaking changes."
-✅ "Fixed memory leak in cache.ts. Added regression test. Verified with profiler."
-❌ [Completes work silently without reporting results]
+✅ "Refactored 5 files. 47 tests passing. No breaking changes."
+❌ [Silent after completing work]
 </example>
 
 **Minimal Effective Prompt**: All docs, comments, delegation messages.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sylphx/flow",
-  "version": "1.5.3",
+  "version": "1.6.0",
   "description": "AI-powered development workflow automation with autonomous loop mode and smart configuration",
   "type": "module",
   "bin": {