llm-party-cli 0.7.1 → 0.10.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llm-party-cli",
-  "version": "0.7.1",
+  "version": "0.10.1",
   "type": "module",
   "bin": {
     "llm-party": "dist/index.js"
@@ -45,8 +45,7 @@
     "prepublishOnly": "bun run build"
   },
   "dependencies": {
-    "@anthropic-ai/claude-agent-sdk": "^0.2.74",
-    "@anthropic-ai/claude-code": "^2.1.74",
+    "@anthropic-ai/claude-agent-sdk": "0.2.90",
     "@github/copilot-sdk": "^0.1.33-preview.2",
     "@openai/codex-sdk": "^0.115.0",
     "@opentui/core": "^0.1.89",

package/prompts/artifacts.md

@@ -1,56 +1,45 @@
 # Artifacts
 
-File and folder schemas for every artifact the system reads and writes.
-No behavioral rules here. Structure and format only.
+Canonical schemas and rules for the files agents read and write.
 
 ---
 
 ## Per-Project: `.llm-party/`
 
-Created when {{humanName}} requests initialization or the orchestrator runs an init command. 
-
-```
+```text
 .llm-party/
   TASKS.md
   memory/
     project.md
+  plans/
+    YYYY-MM-DD-title.md
   skills/
 ```
 
----
-
 ### `.llm-party/TASKS.md`
 
-Task list for this project. Written before work starts. Updated immediately on completion.
-
-**Format:**
 ```markdown
 # Tasks
 
 - [ ] AGENT:@{{agentTag}} | Task description | Date Added
-- [x] AGENT:@{{agentTag}} | Task description | Date Added | Date completed
+- [x] AGENT:@{{agentTag}} | Task description | Date Added | Date Completed
 ```
 
 Rules:
-- Add tasks BEFORE starting work
-- Mark done IMMEDIATELY on completion, not at session end
-
----
+- Add tasks before complex work starts
+- Mark completion immediately
 
 ### `.llm-party/memory/project.md`
 
-Working log for this project. Two zones: Current State (overwritable) and Log (append-only).
-
-**Template:**
 ```markdown
 # Project Memory
 
 ## Current State
 
 Last Updated: YYYY-MM-DD
-Active: [what is being worked on right now]
-Blockers: [anything blocking progress]
-Next: [immediate next action]
+Active: current work
+Blockers: current blockers
+Next: immediate next action
 
 ---
 
@@ -66,34 +55,76 @@ DATE | AGENT:@{{agentTag}} | DECISION | WHY | CONSEQUENCES
 ```
 
 Rules:
-- `Current State` block is overwritten each update. Keep it short. It is a snapshot, not a history.
-- `Log` section is append-only. Never edit or delete past entries.
-- `Decisions` section is append-only. Record decisions that emerge from discussion with {{humanName}}.
+- `Current State` is a short overwriteable snapshot
+- `Log` is append-only
+- `Decisions` is append-only
+- When logging a fix, decision, or incident, include provenance in `DETAIL` when available, such as session, ticket, PR, host, path, or command.
+
+### `.llm-party/plans/`
 
+Filename: `YYYY-MM-DD-title.md`
+
+```markdown
+---
+date: YYYY-MM-DD
+status: planning | in-progress | completed | rejected
+agents: [@agentTag]
 ---
 
-### `.llm-party/skills/`
+# Title
+
+## Context
+Why this plan exists.
+
+## Phase 1: Description
+
+### Area
+
+**Files to change:**
+
+| File | Lines | Change |
+|------|-------|--------|
+| `path/to/file.ts` | 10, 37 | What changes and why |
+
+- [ ] Task
+  - [ ] Subtask if needed
+- [ ] Task
+
+## Phase 2: Description
+
+- [ ] Task
 
-Project-local skills. Each skill is a folder containing a `SKILL.md` file:
+## Open Questions
 
+- [ ] Question
 ```
+
+Rules:
+- Frontmatter is required
+- Share the plan before execution
+- Update status and checkboxes as work progresses
+- One plan per concern
+
+### `.llm-party/skills/`
+
+```text
 skills/
   skill-name/
-    SKILL.md          # Required. YAML frontmatter (name, description) + markdown instructions.
-    scripts/           # Optional. Executable code (Python/JS) for deterministic tasks.
-    references/        # Optional. Docs loaded into context as needed.
-    assets/            # Optional. Templates, icons, fonts used in output.
+    SKILL.md
+    scripts/
+    references/
+    assets/
 ```
 
-Agents read relevant skills before executing unfamiliar workflows. Keep `SKILL.md` concise (under 5,000 words) and offload detail into `references/`.
+Rules:
+- `SKILL.md` is required
+- Keep `SKILL.md` concise and move bulk detail to `references/`
 
 ---
 
 ## Global: `~/.llm-party/`
 
-Created when {{humanName}} requests initialization or the orchestrator runs an init command. Shared across all projects.
-
-```
+```text
 ~/.llm-party/
   network/
     projects.yml
@@ -106,39 +137,28 @@ Created when {{humanName}} requests initialization or the orchestrator runs an i
       SKILL.md
 ```
 
-Additional folders/files (`config.json` etc.) may be added by the orchestrator code. Their schemas are managed in code, not in this prompt.
-
----
-
 ### `~/.llm-party/network/projects.yml`
 
-Living map of all projects. Written by agents when a project-level milestone or cross-project decision happens.
-
-**Schema:**
 ```yaml
 projects:
   - id: unique-slug
     name: Human-readable name
     root_path: /absolute/path/to/project
-    tags: [web, api, cli, creative, horror-story, chicken recipe]
-    stack: [typescript, node, postgres, salt, vineger]
+    tags: [web, api, cli]
+    stack: [typescript, node]
     history:
       - date: YYYY-MM-DD
         agent: agentTag
-        event: 25 words max describing what happened
+        event: short milestone or decision
 ```
 
 Rules:
-- `history` is append-only within each project entry
-- Write here when a decision affects multiple projects or a milestone is reached
-
----
+- `history` is append-only
+- Use it for milestones and cross-project decisions
+- Keep it breadcrumb-sized and include a short reference when useful, such as a session, ticket, PR, host, or memory file.
 
 ### `~/.llm-party/network/mind-map/`
 
-Obsidian-compatible folder. Each discovery is its own `.md` file with frontmatter and wikilinks. Users can open this folder in Obsidian to visualize the knowledge graph.
-
-**Note format:**
 ```markdown
 ---
 discovered: YYYY-MM-DD
@@ -149,38 +169,31 @@ tags: [relevant, tags]
 
 # Descriptive Title
 
-What the constraint or discovery is.
+Constraint, discovery, or lesson.
 
 ## Workaround
-How to work around it.
+How to avoid or handle it.
 
 ## Related
-- [[other-discovery-filename]]
+- [[other-discovery]]
 ```
 
-**File naming:** slugified title, e.g. `react-19-useeffect.md`, `figma-autolayout-nesting.md`.
-
 Rules:
-- Write here when a tool or resource constraint is discovered that would trap a future session
-- Include workaround. A constraint without a workaround is incomplete.
-- Use `[[wikilinks]]` to connect related discoveries
-
----
+- Each discovery gets its own file
+- Add a matching entry to `INDEX.md`
+- Include a workaround whenever the note describes a constraint
+- Include where proof lives when useful, such as a session, ticket, PR, host, path, or project memory entry.
 
 ### `~/.llm-party/agents/{{agentTag}}.md`
 
-Per-agent self memory. Not shared between agents. Each agent owns its own file.
-
-**Template:**
 ```markdown
 # {{agentName}} Self Memory
 
-DATE | RULE | EXAMPLE
+DATE | PROJECT PATH | RULE | EXAMPLE
 ```
 
 Rules:
-- Write IMMEDIATELY when a correction is received or a non-obvious approach is confirmed
-- Per-agent: one file per agent, named `{{agentTag}}.md`
+- One file per agent, named `{{agentTag}}.md`
 - Append-only
+- Write corrections and validated non-obvious approaches immediately
 
----