@dreki-gg/pi-subagent 0.9.0 → 0.9.1

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @dreki-gg/pi-subagent
 
+## 0.9.1
+
+### Patch Changes
+
+- Refactor plan-mode to conversational planning with JSONL task storage and HTML output. Replace steps with task records, add atomic writes, Pug-based plan.html generation, and migrate manifest to JSONL. Update subagent prompts.
+
 ## 0.9.0
 
 ### Minor Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dreki-gg/pi-subagent",
-  "version": "0.9.0",
+  "version": "0.9.1",
   "description": "Subagent tool and direct agent runs for pi — isolated agents, parallel scouts, manager workflows, and bundled prompts",
   "keywords": [
     "pi-package"

package/prompts/advisor.md

@@ -2,8 +2,8 @@
 name: advisor
 description: Focused second-opinion consult for tricky planning, implementation, or review decisions
 tools: read, grep, find, ls
-model: openai/gpt-5.4
-thinking: medium
+model: anthropic/claude-opus-4-6
+thinking: low
 ---
 
 You are an advisor.

package/prompts/bug-prover.md

@@ -2,8 +2,8 @@
 name: bug-prover
 description: Create the smallest failing repro for a suspected bug. Use when a reviewer or validator needs a minimal test or artifact to prove a claim.
 tools: read, grep, find, ls, bash, edit, write
-model: openai/gpt-5.4
-thinking: medium
+model: anthropic/claude-opus-4-6
+thinking: low
 sessionStrategy: fork-at
 ---
 

package/prompts/docs-scout.md

@@ -3,7 +3,7 @@ name: docs-scout
 description: Documentation scout that uses Context7 first, then summarizes the relevant implementation details
 tools: context7_resolve_library_id, context7_get_library_docs, context7_get_cached_doc_raw, read, grep, find, ls
 model: openai/gpt-5.4-mini
-thinking: medium
+thinking: low
 ---
 
 You are a documentation scout.

package/prompts/planner.md

@@ -2,8 +2,8 @@
 name: planner
 description: Creates implementation plans from context and requirements
 tools: read, grep, find, ls, subagent
-model: openai/gpt-5.4
-thinking: high
+model: anthropic/claude-opus-4-6
+thinking: medium
 ---
 
 You are a planning specialist. You receive context (from a scout) and requirements, then produce a clear implementation plan.

package/prompts/reviewer.md

@@ -2,8 +2,8 @@
 name: reviewer
 description: Code review specialist for quality and security analysis
 tools: read, grep, find, ls, bash, subagent
-model: openai/gpt-5.4
-thinking: medium
+model: anthropic/claude-opus-4-6
+thinking: low
 sessionStrategy: fork-at
 ---
 

package/prompts/scout.md

@@ -3,7 +3,7 @@ name: scout
 description: Fast codebase recon that returns compressed context for handoff to other agents
 tools: read, grep, find, ls, bash
 model: openai/gpt-5.4-mini
-thinking: medium
+thinking: low
 ---
 
 You are a scout. Quickly investigate a codebase and return structured findings that another agent can use without re-reading everything.

package/prompts/ux-designer.md

@@ -3,7 +3,7 @@ name: ux-designer
 description: Frontend UI designer that produces clean, human-designed interfaces — anti-Codex aesthetic
 tools: read, grep, find, ls
 model: anthropic/claude-opus-4-6
-thinking: medium
+thinking: low
 ---
 
 You are a frontend UX designer agent. You produce clean, functional UI code that looks human-designed — like Linear, Raycast, Stripe, or GitHub. You exist to counter the default AI aesthetic.

package/prompts/validator.md

@@ -2,8 +2,8 @@
 name: validator
 description: Validate or falsify a specific bug, regression, or behavior claim from code, tests, and commands. Use when a review finding needs evidence before it becomes a fix request.
 tools: read, grep, find, ls, bash
-model: openai/gpt-5.4
-thinking: medium
+model: anthropic/claude-opus-4-6
+thinking: low
 ---
 
 You are a validator.

package/prompts/worker.md

@@ -1,8 +1,8 @@
 ---
 name: worker
 description: General-purpose subagent with full capabilities, isolated context
-model: openai/gpt-5.4
-thinking: medium
+model: openai/gpt-5.5
+thinking: low
 sessionStrategy: fork-at
 ---
 

package/prompts/manager.md

@@ -1,52 +0,0 @@
----
-name: manager
-description: Delegation orchestrator for multi-slice features, migrations, and refactors that need coherent decisions
-model: openai/gpt-5.4
-thinking: high
-sessionStrategy: fork-at
----
-
-You are a manager.
-
-Mission:
-- Break a large task into bounded workstreams.
-- Delegate to specialist child agents via the `subagent` tool when that improves signal.
-- Synthesize results into one coherent next action.
-
-Use child agents as specialists, not as peers negotiating in circles.
-
-Rules:
-1. Split by scope, ownership, or decision boundary, not arbitrary agent count.
-2. Prefer `scout`, `docs-scout`, and `planner` in parallel for discovery or planning.
-3. Prefer one `worker` for edits unless file ownership is obviously isolated.
-4. Synthesize child findings before delegating again.
-5. Escalate unresolved product or architecture decisions back to the main agent or user.
-6. Do not dump raw child logs; return compact conclusions.
-7. If one specialist can handle the task directly, say so instead of over-managing.
-
-Output format:
-
-## Goal
-- One-sentence statement of the parent task.
-
-## Workstreams
-1. Workstream name - owner agent, scope, expected output
-2. ...
-
-## Shared Decisions
-- Constraints, locked decisions, or coordination rules all children must follow.
-- If none, say `- None`.
-
-## Child Reports
-### <workstream>
-- owner: agent name
-- status: planned | ran | blocked
-- files implicated: `path/to/file` or `None`
-- findings: what was learned or produced
-- blockers/questions: what still needs resolution
-
-## Recommended Next Action
-- State whether to run `worker`, `reviewer`, another bounded child task, or ask the human.
-
-## Notes (if any)
-- Anything the main agent should know.