@benzotti/jedi 0.1.42 → 0.1.43

package/dist/index.js

@@ -12791,7 +12791,7 @@ var stateCommand = defineCommand({
 // package.json
 var package_default = {
   name: "@benzotti/jedi",
-  version: "0.1.42",
+  version: "0.1.43",
   description: "JDI - Context-efficient AI development framework for Claude Code",
   type: "module",
   bin: {

package/framework/commands/implement-plan.md

@@ -24,6 +24,7 @@ Execute a PLAN.md with complexity-based routing.
 9. Execute:
    - **Single agent:** Spawn with `subagent_type: {plan.primary_agent}` (NOT `general-purpose`). Pass `PLAN: {index-path}`. For split plans, the agent reads task files one at a time via `file:` field in state.yaml.
    - **Agent Teams:** For split plans, spawn ONE Task tool call per task with `subagent_type: {task.agent}` (the pin from the task file frontmatter), passing `TASK_FILE: {task-file-path}` so it loads only its assigned task. For legacy plans, pass `PLAN: {plan-path}` and use `primary_agent`.
+   - **Prompt scoping** — one task = one spawn. Never bundle multiple tasks into one prompt. Give exact file paths, cap exploration ("read only your TASK_FILE + its named targets"), and request short reports (<400 words). Agents can be truncated mid-task; scoped prompts survive the budget ceiling.
 10. Collect and execute deferred ops (files, commits)
 11. Run verification (tests, lint, typecheck)
 12. **Update state via CLI** — do NOT manually edit state.yaml. Run `npx jdi state executing` before execution and `npx jdi state complete` after. Use `npx jdi state advance-task {task-id}` after each task completes.

package/framework/components/meta/AgentBase.md

@@ -11,6 +11,19 @@ Standards inherited by all JDI agents via `<JDI:AgentBase />`. Default loads Cor
 - Batch file reads: issue all Read calls in a single turn rather than sequentially.
 - Batch git operations: combine related commands into a single Bash call where possible.
 
+## Budget Discipline
+
+You have a finite per-invocation budget (tokens, tool calls, wall time). Long runs can be terminated mid-task before you produce your final report. To survive:
+
+1. **Batch reads in parallel** — one turn with all Read calls, not sequential.
+2. **Cap exploration** — read only the files your spawn prompt names. If more are needed, report what you need and stop rather than wandering.
+3. **Write fixes before verifying** — Edit calls persist even if you are later truncated. Save the report for last.
+4. **Short reports (<400 words)** — terse file list + one sentence per change. Long formal reports are where truncation bites.
+5. **One concern per invocation** — address what was asked, do not expand scope.
+6. **Don't re-read files you just edited** — the harness tracks state.
+
+If your work exceeds one invocation, complete what you can, return a progress report naming exactly what remains, and let the orchestrator re-spawn you.
+
 ## Component Resolution
 
 When a spec contains `<JDI:*>` tags:

package/framework/components/meta/AgentTeamsOrchestration.md

@@ -11,7 +11,7 @@ description: Agent Teams orchestration quick-reference
 1. **Pre-flight** — Read command spec, `<JDI:CodebaseContext />`, read state.yaml, set status to "executing". Read each task file's `agent:` frontmatter field so you know which specialist to spawn per task (see `.jdi/framework/components/meta/AgentRouter.md`).
 2. **Create Team** — `TeamCreate(team_name: "{team-name}")`
 3. **Create Tasks** — TaskCreate per work unit, set `addBlockedBy` dependencies
-4. **Spawn Teammates** — Task tool with `subagent_type: "{task.agent}"` (the pin from the task file frontmatter — e.g. `unity-ui-specialist`, `gameplay-programmer`). Never hardcode `general-purpose` when a pin exists. Verify the pinned agent is installed before spawning; if not, downgrade to `general-purpose` and record `agent_downgrade:` in the summary. Include in prompt: agent spec path, team context, task assignments.
+4. **Spawn Teammates** — Task tool with `subagent_type: "{task.agent}"` (the pin from the task file frontmatter — e.g. `unity-ui-specialist`, `gameplay-programmer`). Never hardcode `general-purpose` when a pin exists. Verify the pinned agent is installed before spawning; if not, downgrade to `general-purpose` and record `agent_downgrade:` in the summary. Include in prompt: agent spec path, team context, task assignments. **Scope tightly** — one task per spawn, exact file targets, capped exploration, short reports (<400 words). See `AgentBase.md` § Budget Discipline.
 5. **Coordinate** — Automatic message delivery for results, TaskList to monitor, SendMessage to guide/unblock
 6. **Cleanup** — shutdown_request to all → TeamDelete → set status "complete" → report (include which specialist ran which task and any downgrade events)
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@benzotti/jedi",
-  "version": "0.1.42",
+  "version": "0.1.43",
   "description": "JDI - Context-efficient AI development framework for Claude Code",
   "type": "module",
   "bin": {