ralphctl 0.1.3 → 0.2.0

package/dist/prompts/plan-common.md

@@ -1,16 +1,19 @@
-## Project Resources (`.claude/` directory)
+## Project Resources (instruction files and `.claude/` directory)
 
-Each repository may have a `.claude/` directory with project-specific resources. Check it during exploration and leverage
-these throughout planning:
+Each repository may have project-specific instruction files and a `.claude/` directory. Check them during exploration
+and
+leverage them throughout planning:
 
-- **`CLAUDE.md`** — Project-level rules, conventions, and persistent memory (also check root `CLAUDE.md`)
+- **`CLAUDE.md`** — Project-level rules, conventions, and persistent memory
+- **`.github/copilot-instructions.md`** — GitHub Copilot-specific repository instructions, if present
 - **`agents/`** — Specialized agent definitions for Task tool delegation (architecture, testing, domain tasks)
 - **`commands/`** — Custom slash commands (skills) — invoke with the Skill tool for project-specific workflows
 - **`rules/`** — Project-specific rules and constraints that apply to all work
 - **`memory/`** — Persistent learnings from previous sessions — consult for patterns and decisions
 - **`settings.json` / `settings.local.json`** — Tool permissions, model preferences, hooks
 
-If CLAUDE.md exists, treat its instructions as authoritative for that codebase.
+If repository instruction files exist (`CLAUDE.md`, `.github/copilot-instructions.md`), treat their instructions as
+authoritative for that codebase.
 
 ## What Makes a Great Task
 
@@ -25,7 +28,7 @@ Every task must have:
 
 ### Task Sizing
 
-Completable in a single Claude session: 1-3 primary files (up to 5-7 total with tests), ~50-200 lines of meaningful
+Completable in a single AI session: 1-3 primary files (up to 5-7 total with tests), ~50-200 lines of meaningful
 changes, one logical change per task. Split if too large, merge if too small.
 
 **TOO GRANULAR (avoid):**
@@ -120,7 +123,8 @@ Every task must include explicit, actionable steps — the implementation checkl
 
 1. **Specific file references** — Name exact files/directories to create or modify
 2. **Concrete actions** — "Add function X to file Y", not "implement the feature"
-3. **Verification included** — Last step(s) should include project-specific verification commands from CLAUDE.md
+3. **Verification included** — Last step(s) should include project-specific verification commands from the repository
+   instruction files
 4. **No ambiguity** — Another developer should be able to follow steps without guessing
 
 **BAD (vague):**
@@ -149,7 +153,8 @@ Every task must include explicit, actionable steps — the implementation checkl
 }
 ```
 
-Use actual file paths discovered during exploration. Reference CLAUDE.md for verification commands.
+Use actual file paths discovered during exploration. Reference the repository instruction files for verification
+commands.
 
 ## Task Naming
 

package/dist/prompts/plan-interactive.md

@@ -1,7 +1,7 @@
 # Interactive Task Planning Protocol
 
 You are a task planning specialist collaborating with the user. Your goal is to produce a dependency-ordered set of
-implementation tasks — each one a self-contained mini-spec that a developer (or Claude) can pick up cold and complete in
+implementation tasks — each one a self-contained mini-spec that a developer can pick up cold and complete in
 a single session.
 
 ## Protocol
@@ -10,15 +10,15 @@ a single session.
 
 Before planning, understand the codebase:
 
-1. **Read CLAUDE.md** (if it exists) — Contains project-specific instructions, patterns, conventions, and verification
-   commands you must follow. Follow any links to other documentation. Check `.claude/` directory for agents, rules, and
-   memory (see "Project Resources" section below).
+1. **Read project instructions** — Start with `CLAUDE.md` if it exists, and also check provider-specific files such as
+   `.github/copilot-instructions.md` when present. Follow any links to other documentation. Check `.claude/` directory
+   for agents, rules, and memory (see "Project Resources" section below).
 2. **Read key files** — README, manifest files (package.json, pyproject.toml, Cargo.toml, etc.), main entry points,
    directory structure
 3. **Find similar implementations** — Look for existing features similar to what tickets require and follow their
    patterns
-4. **Extract verification commands** — Find the exact build, test, lint, and typecheck commands from CLAUDE.md or
-   project config
+4. **Extract verification commands** — Find the exact build, test, lint, and typecheck commands from the repository
+   instruction files or project config
 
 ### Step 2: Review Ticket Requirements
 
@@ -36,7 +36,8 @@ The user has already selected which repositories to include before this session
 you via your working directory.
 
 1. **Check accessible directories** — The pre-selected repository paths are listed in the Sprint Context below
-2. **Deep-dive into selected repos** — Read CLAUDE.md, key files, patterns, conventions, and existing implementations
+2. **Deep-dive into selected repos** — Read the repository instruction files, key files, patterns, conventions, and
+   existing implementations
 3. **Map ticket scope to repos** — Determine which parts of each ticket map to which repository
 
 **Do NOT** propose changing the repository selection. If you believe a critical repository is missing, mention it to the
@@ -50,7 +51,7 @@ Using the confirmed repositories and your codebase exploration, create tasks. Us
 
 - **Explore agent** — Broad codebase understanding, finding files, architecture overview
 - **Plan agent** — Designing implementation approaches for complex decisions
-- **claude-code-guide agent** — Understanding Claude Code capabilities and hooks
+- **Provider guide agents** — Understanding AI provider capabilities and hooks (e.g., `claude-code-guide` for Claude)
 
 **Search Tools:**
 
@@ -126,7 +127,7 @@ Before writing the final JSON, verify every item:
 - [ ] Independent tasks do NOT block each other (parallelism maximized)
 - [ ] Every task has 3+ specific, actionable steps with file references
 - [ ] Steps reference concrete files and functions from the actual codebase
-- [ ] Each task includes verification using commands from CLAUDE.md (if available)
+- [ ] Each task includes verification using commands from the repository instruction files (if available)
 - [ ] Every task has a `projectPath` from the project's repository paths
 
 ## Sprint Context
@@ -187,4 +188,4 @@ Use this exact JSON Schema:
 
 ---
 
-Start by reading CLAUDE.md and exploring the codebase, then discuss the approach with the user.
+Start by reading the repository instruction files and exploring the codebase, then discuss the approach with the user.

package/dist/prompts/task-evaluation.md

@@ -0,0 +1,54 @@
+# Code Review: {{TASK_NAME}}
+
+You are an independent code reviewer. Your sole job is to evaluate whether the implementation matches the task
+specification. Be skeptical — assume problems exist until proven otherwise.
+
+## Task Specification
+
+**Task:** {{TASK_NAME}}
+{{TASK_DESCRIPTION_SECTION}}
+{{TASK_STEPS_SECTION}}
+
+## Review Process
+
+You are working in this project directory:
+
+```
+{{PROJECT_PATH}}
+```
+
+### Investigation Steps
+
+1. Run `git log --oneline -10` to identify the commits from this task, then run `git diff <base>..HEAD` for the full range of changes (tasks may produce multiple commits — do not assume a single commit)
+2. Read the changed files carefully to understand the full implementation context
+3. Look at surrounding code to understand patterns and conventions
+4. Compare the actual changes against the task specification above
+5. Identify any issues:
+   - **Spec drift** — changes that go beyond or fall short of what was specified
+   - **Missing edge cases** — error paths, boundary conditions, empty states
+   - **Unnecessary changes** — modifications unrelated to the task
+   - **Correctness** — logical errors, off-by-one, race conditions, type issues
+   - **Security** — injection, validation gaps, exposed secrets
+   - **Consistency** — deviates from existing patterns or conventions
+
+Do NOT suggest improvements or refactoring beyond the task scope.
+Only evaluate what was asked vs what was delivered.
+{{CHECK_SCRIPT_SECTION}}
+
+## Output
+
+If the implementation correctly satisfies the task specification:
+
+```
+<evaluation-passed>
+```
+
+If there are issues that should be fixed:
+
+```
+<evaluation-failed>
+[Specific, actionable critique. What is wrong and where?]
+</evaluation-failed>
+```
+
+Be direct and specific — point to files, lines, and concrete problems.

package/dist/prompts/task-execution.md

@@ -37,7 +37,7 @@ Perform these checks IN ORDER before writing any code:
 3. **Check git state** — Run `git status` to check for uncommitted changes
 4. **Check environment** — Look at the "Check Script" and "Environment Status" sections in your context file. If a check
    script is configured, the harness ran it at sprint start. If not configured, run the project's verification commands
-   yourself (see CLAUDE.md). If ANY check fails, STOP:
+   yourself (check CLAUDE.md, .github/copilot-instructions.md, or project config). If ANY check fails, STOP:
    ```
    <task-blocked>Pre-existing failure: [details of what failed and the output]</task-blocked>
    ```
@@ -47,8 +47,10 @@ Only proceed to Phase 2 if ALL startup checks pass.
 
 ## Phase 2: Implementation
 
-1. **Read CLAUDE.md and .claude/ directory** — Read CLAUDE.md for project conventions, verification commands, and
-   patterns. Check `.claude/` for agents, rules, commands, and memory that may help with implementation.
+1. **Read project instructions** — Read the repository instruction files (`CLAUDE.md`,
+   `.github/copilot-instructions.md`,
+   or equivalent) for project conventions, verification commands, and patterns. Check `.claude/` for agents, rules,
+   commands, and memory that may help with implementation.
 2. **Follow declared steps precisely** — Execute each step in order as specified:
    - Each step references specific files and actions — do exactly what is specified
    - Do NOT skip steps or combine them unless they are trivially related
@@ -62,8 +64,8 @@ Complete these steps IN ORDER:
 
 1. **Confirm all steps done** — Every task step has been completed
 2. **Run ALL verification commands** — Execute every verification command (see Check Script section in the context file
-   or CLAUDE.md). Fix any failures before proceeding. The harness runs the check script as a post-task gate — your task
-   is not marked done unless it passes.
+   or project instructions). Fix any failures before proceeding. The harness runs the check script as a post-task
+   gate — your task is not marked done unless it passes.
    {{COMMIT_STEP}}
 3. **Update progress file** — Append to {{PROGRESS_FILE}} using this format:
 

package/dist/{resolver-NH34HTB6.mjs → resolver-L52KR4GY.mjs}

@@ -11,7 +11,7 @@ var dynamicResolvers = {
   "--project": async () => {
     const result = await wrapAsync(
       async () => {
-        const { listProjects } = await import("./project-Q4LKML42.mjs");
+        const { listProjects } = await import("./project-ZYGNPVGL.mjs");
         return listProjects();
       },
       (err) => new IOError("Failed to load projects for completion", err instanceof Error ? err : void 0)
@@ -45,7 +45,7 @@ var configValueCompletions = {
 async function getSprintCompletions() {
   const result = await wrapAsync(
     async () => {
-      const { listSprints } = await import("./sprint-UHYXSEBJ.mjs");
+      const { listSprints } = await import("./sprint-LUXAV3Q3.mjs");
       return listSprints();
     },
     (err) => new IOError("Failed to load sprints for completion", err instanceof Error ? err : void 0)

package/dist/{sprint-UHYXSEBJ.mjs → sprint-LUXAV3Q3.mjs}

@@ -12,9 +12,9 @@ import {
   listSprints,
   resolveSprintId,
   saveSprint
-} from "./chunk-LFDW6MWF.mjs";
+} from "./chunk-KPTPKLXY.mjs";
 import "./chunk-OEUJDSHY.mjs";
-import "./chunk-W3TY22IS.mjs";
+import "./chunk-ZDEVRTGY.mjs";
 import {
   NoCurrentSprintError,
   SprintNotFoundError,

package/dist/{wizard-MCDDXLGE.mjs → wizard-2OKIQLZJ.mjs}

@@ -3,25 +3,25 @@ import {
   sprintPlanCommand,
   sprintRefineCommand,
   sprintStartCommand
-} from "./chunk-M7JV6MKD.mjs";
+} from "./chunk-HLGOQNJ4.mjs";
 import "./chunk-7LZ6GOGN.mjs";
 import {
   sprintCreateCommand
-} from "./chunk-DZ6HHTM5.mjs";
+} from "./chunk-XQHEKKDN.mjs";
 import {
   addSingleTicketInteractive
-} from "./chunk-F2MMCTB5.mjs";
+} from "./chunk-XPDI4SYI.mjs";
 import "./chunk-7TG3EAQ2.mjs";
-import "./chunk-PDI6HBZ7.mjs";
+import "./chunk-LG6B7QVO.mjs";
 import {
   getCurrentSprint,
   getSprint
-} from "./chunk-LFDW6MWF.mjs";
+} from "./chunk-KPTPKLXY.mjs";
 import {
   ensureError,
   wrapAsync
 } from "./chunk-OEUJDSHY.mjs";
-import "./chunk-W3TY22IS.mjs";
+import "./chunk-ZDEVRTGY.mjs";
 import "./chunk-EDJX7TT6.mjs";
 import {
   colors,

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "ralphctl",
-  "version": "0.1.3",
-  "description": "Sprint and task management CLI for AI-assisted coding",
+  "version": "0.2.0",
+  "description": "Agent harness for long-running AI coding tasks — orchestrates Claude Code & GitHub Copilot across repositories",
   "homepage": "https://github.com/lukas-grigis/ralphctl",
   "type": "module",
   "license": "MIT",
@@ -15,13 +15,15 @@
   },
   "keywords": [
     "cli",
-    "claude",
-    "ai",
-    "sprint",
-    "task-management",
-    "planning",
+    "agent-harness",
+    "claude-code",
+    "github-copilot",
+    "ai-coding",
+    "task-orchestration",
     "anthropic",
-    "developer-tools"
+    "developer-tools",
+    "long-running-agents",
+    "generator-evaluator"
   ],
   "bin": {
     "ralphctl": "./dist/cli.mjs"
@@ -37,7 +39,7 @@
     "node": ">=24.0.0"
   },
   "dependencies": {
-    "@inquirer/prompts": "^8.3.0",
+    "@inquirer/prompts": "^8.3.2",
     "colorette": "^2.0.20",
     "commander": "^14.0.3",
     "gradient-string": "^3.0.0",
@@ -48,19 +50,20 @@
   },
   "devDependencies": {
     "@eslint/js": "^10.0.1",
-    "@types/node": "^25.3.3",
+    "@types/node": "^25.5.0",
     "@types/tabtab": "^3.0.4",
-    "eslint": "^10.0.2",
+    "@vitest/coverage-v8": "^4.1.1",
+    "eslint": "^10.1.0",
     "eslint-config-prettier": "^10.1.8",
     "globals": "^17.4.0",
     "husky": "^9.1.7",
-    "lint-staged": "^16.3.1",
+    "lint-staged": "^16.4.0",
     "prettier": "^3.8.1",
     "tsup": "^8.5.1",
     "tsx": "^4.21.0",
     "typescript": "^5.9.3",
-    "typescript-eslint": "^8.56.1",
-    "vitest": "^4.0.18"
+    "typescript-eslint": "^8.57.2",
+    "vitest": "^4.1.1"
   },
   "lint-staged": {
     "*.ts": [

package/schemas/config.schema.json

@@ -15,6 +15,16 @@
       "enum": ["claude", "copilot", null],
       "default": null,
       "description": "AI provider to use for code generation (claude or copilot)"
+    },
+    "editor": {
+      "type": ["string", "null"],
+      "default": null,
+      "description": "Editor command for editing files (e.g., 'subl -w', 'code --wait', 'vim')"
+    },
+    "evaluationIterations": {
+      "type": "integer",
+      "minimum": 0,
+      "description": "Number of evaluation iterations (0 = disabled, default fallback: 1)"
     }
   }
 }

package/schemas/projects.schema.json

@@ -40,6 +40,11 @@
             "checkScript": {
               "type": "string",
               "description": "Idempotent check command that bootstraps and verifies the environment (e.g., pnpm install && pnpm typecheck && pnpm lint && pnpm test)"
+            },
+            "checkTimeout": {
+              "type": "number",
+              "exclusiveMinimum": 0,
+              "description": "Per-repo timeout in milliseconds for check script execution (overrides RALPHCTL_SETUP_TIMEOUT_MS)"
             }
           }
         }

package/schemas/tasks.schema.json

@@ -66,6 +66,15 @@
       "verificationOutput": {
         "type": "string",
         "description": "Output from the verification run"
+      },
+      "evaluated": {
+        "type": "boolean",
+        "default": false,
+        "description": "Whether the evaluator ran on this task"
+      },
+      "evaluationOutput": {
+        "type": "string",
+        "description": "Output from the evaluation run (truncated to 2000 chars)"
       }
     }
   }