deepflow 0.1.28 → 0.1.30

package/README.md

@@ -24,6 +24,7 @@
 - **Stay in flow** — Minimize context switches, maximize deep work
 - **Conversational ideation** with proactive gap discovery
 - **Specs define intent**, tasks close reality gaps
+- **Worktree isolation** — Main branch stays clean during execution
 - **Parallel execution** with context-aware checkpointing
 - **Atomic commits** for clean rollback
 
@@ -70,7 +71,7 @@ CONVERSATION
     │ Renames: feature.md → doing-feature.md
     ▼
 /df:execute
-    │ Follows existing patterns
+    │ Creates isolated worktree (main stays clean)
     │ Parallel agents, file conflicts serialize
     │ Context-aware (≥50% → checkpoint)
     │ Atomic commit per task
@@ -95,6 +96,14 @@ specs/
 
 **Ongoing:** Detects existing patterns, follows conventions, integrates with current code.
 
+## Worktree Isolation
+
+Execution happens in an isolated git worktree:
+- Main branch stays clean during execution
+- On failure, worktree preserved for debugging
+- Resume with `/df:execute --continue`
+- On success, changes merged back to main
+
 ## Context-Aware Execution
 
 Statusline shows context usage. At ≥50%:
@@ -124,7 +133,8 @@ your-project/
 └── .deepflow/
     ├── context.json      # context % for execution
     ├── checkpoint.json   # resume state
-    └── results/          # agent results
+    └── worktrees/        # isolated execution (main stays clean)
+        └── df/doing-upload/20260202-1430/
 ```
 
 ## Configuration

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "deepflow",
-  "version": "0.1.28",
+  "version": "0.1.30",
   "description": "Stay in flow state - lightweight spec-driven task orchestration for Claude Code",
   "keywords": [
     "claude",

package/src/commands/df/execute.md

@@ -2,11 +2,11 @@
 
 ## Orchestrator Role
 
-You spawn agents and poll results. You never implement.
+You are a coordinator. Spawn agents, wait for results, update PLAN.md. Never implement code yourself.
 
-**NEVER:** Read source files, edit code, run tests, run git (except status), use `TaskOutput`
+**NEVER:** Read source files, edit code, run tests, run git commands (except status)
 
-**ONLY:** Read `PLAN.md` + `specs/doing-*.md`, spawn background agents, poll `.deepflow/results/`, update PLAN.md
+**ONLY:** Read PLAN.md, read specs/doing-*.md, spawn background agents, use TaskOutput to get results, update PLAN.md
 
 ---
 
@@ -43,11 +43,16 @@ Statusline writes to `.deepflow/context.json`: `{"percentage": 45}`
 
 ## Agent Protocol
 
-Every task = one background agent. Poll result files, never `TaskOutput`.
+Each task = one background agent. Use TaskOutput to wait for results. Never poll files in a loop.
 
 ```python
-Task(subagent_type="general-purpose", run_in_background=True, prompt="T1: ...")
-# Poll: Glob(".deepflow/results/T*.yaml")
+# Spawn agents in parallel (single message, multiple Task calls)
+task_id_1 = Task(subagent_type="general-purpose", run_in_background=True, prompt="T1: ...")
+task_id_2 = Task(subagent_type="general-purpose", run_in_background=True, prompt="T2: ...")
+
+# Wait for all results (single message, multiple TaskOutput calls)
+TaskOutput(task_id=task_id_1)
+TaskOutput(task_id=task_id_2)
 ```
 
 Result file `.deepflow/results/{task_id}.yaml`:
@@ -211,15 +216,22 @@ Ready = `[ ]` + all `blocked_by` complete + experiment validated (if applicable)
 
 Context ≥50%: checkpoint and exit.
 
-**Use Task tool to spawn all ready tasks in ONE message (parallel):**
+**CRITICAL: Spawn ALL ready tasks in a SINGLE response with MULTIPLE Task tool calls.**
+
+DO NOT spawn one task, wait, then spawn another. Instead, call Task tool multiple times in the SAME message block. This enables true parallelism.
+
+Example: If T1, T2, T3 are ready, send ONE message containing THREE Task tool invocations:
+
 ```
-Task tool parameters for each task:
-- subagent_type: "general-purpose"
-- model: "sonnet"
-- run_in_background: true
-- prompt: "{task details from PLAN.md}"
+// In a SINGLE assistant message, invoke Task THREE times:
+Task(subagent_type="general-purpose", model="sonnet", run_in_background=true, prompt="T1: ...")
+Task(subagent_type="general-purpose", model="sonnet", run_in_background=true, prompt="T2: ...")
+Task(subagent_type="general-purpose", model="sonnet", run_in_background=true, prompt="T3: ...")
 ```
 
+**WRONG (sequential):** Send message with Task for T1 → wait → send message with Task for T2 → wait → ...
+**RIGHT (parallel):** Send ONE message with Task for T1, T2, T3 all together
+
 Same-file conflicts: spawn sequentially instead.
 
 **Spike Task Execution:**
@@ -375,7 +387,18 @@ When all tasks done for a `doing-*` spec:
 
 ### 10. ITERATE
 
-Repeat until: all done, all blocked, or checkpoint.
+After spawning agents, wait for results using TaskOutput. Call TaskOutput for ALL running agents in a SINGLE message (parallel wait).
+
+```python
+# After spawning T1, T2, T3 in parallel, wait for all in parallel:
+TaskOutput(task_id=t1_id)  # These three calls go in ONE message
+TaskOutput(task_id=t2_id)
+TaskOutput(task_id=t3_id)
+```
+
+Then check which tasks completed, update PLAN.md, identify newly unblocked tasks, spawn next wave.
+
+Repeat until: all done, all blocked, or context ≥50% (checkpoint).
 
 ## Rules
 
@@ -401,6 +424,8 @@ Wave 2: T3 (context: 48%)
 
 ✓ doing-upload → done-upload
 ✓ Complete: 3/3 tasks
+
+Next: Run /df:verify to verify specs and merge to main
 ```
 
 ### Spike-First Execution
@@ -426,6 +451,8 @@ Wave 2: T2, T3 parallel (context: 40%)
 
 ✓ doing-upload → done-upload
 ✓ Complete: 3/3 tasks
+
+Next: Run /df:verify to verify specs and merge to main
 ```
 
 ### Spike Failed (Agent Correctly Reported)
@@ -441,9 +468,9 @@ Verifying T1...
   → upload--streaming--failed.md
 
 ⚠ Spike T1 invalidated hypothesis
-  → Run /df:plan to generate new hypothesis spike
-
 Complete: 1/3 tasks (2 blocked by failed experiment)
+
+Next: Run /df:plan to generate new hypothesis spike
 ```
 
 ### Spike Failed (Verifier Override)
@@ -460,14 +487,16 @@ Verifying T1...
   → upload--streaming--failed.md
 
 ⚠ Spike T1 invalidated hypothesis
-  → Run /df:plan to generate new hypothesis spike
-
 Complete: 1/3 tasks (2 blocked by failed experiment)
+
+Next: Run /df:plan to generate new hypothesis spike
 ```
 
 ### With Checkpoint
 
 ```
 Wave 1 complete (context: 52%)
-Checkpoint saved. Run /df:execute --continue
+Checkpoint saved.
+
+Next: Run /df:execute --continue to resume execution
 ```

package/src/commands/df/plan.md

@@ -81,12 +81,15 @@ Include patterns in task descriptions for agents to follow.
 
 ### 4. ANALYZE CODEBASE
 
-**Use Task tool to spawn Explore agents in parallel:**
+**Spawn ALL Explore agents in ONE message, then wait for ALL with TaskOutput in ONE message:**
 ```
-Task tool parameters:
-- subagent_type: "Explore"
-- model: "haiku"
-- run_in_background: true (for parallel execution)
+// Spawn all in single message:
+t1 = Task(subagent_type="Explore", model="haiku", run_in_background=true, prompt="...")
+t2 = Task(subagent_type="Explore", model="haiku", run_in_background=true, prompt="...")
+
+// Wait all in single message:
+TaskOutput(task_id=t1)
+TaskOutput(task_id=t2)
 ```
 
 Scale agent count based on codebase size:

package/src/commands/df/spec.md

@@ -6,7 +6,7 @@ You coordinate agents and ask questions. You never search code directly.
 
 **NEVER:** Read source files, use Glob/Grep directly, run git
 
-**ONLY:** Spawn agents, poll results, ask user questions, write spec file
+**ONLY:** Spawn agents, use TaskOutput to get results, ask user questions, write spec file
 
 ---
 
@@ -31,12 +31,15 @@ Transform conversation context into a structured specification file.
 
 ### 1. GATHER CODEBASE CONTEXT
 
-**Use Task tool to spawn Explore agents in parallel:**
+**Spawn ALL Explore agents in ONE message, then wait for ALL with TaskOutput in ONE message:**
 ```
-Task tool parameters:
-- subagent_type: "Explore"
-- model: "haiku"
-- run_in_background: true
+// Spawn all in single message:
+t1 = Task(subagent_type="Explore", model="haiku", run_in_background=true, prompt="...")
+t2 = Task(subagent_type="Explore", model="haiku", run_in_background=true, prompt="...")
+
+// Wait all in single message:
+TaskOutput(task_id=t1)
+TaskOutput(task_id=t2)
 ```
 
 Find:

package/src/commands/df/verify.md

@@ -91,12 +91,15 @@ Default: L1-L3 (L4 optional, can be slow)
 
 ## Agent Usage
 
-**Use Task tool to spawn Explore agents:**
+**Spawn ALL Explore agents in ONE message, then wait for ALL with TaskOutput in ONE message:**
 ```
-Task tool parameters:
-- subagent_type: "Explore"
-- model: "haiku"
-- run_in_background: true (for parallel)
+// Spawn all in single message:
+t1 = Task(subagent_type="Explore", model="haiku", run_in_background=true, prompt="...")
+t2 = Task(subagent_type="Explore", model="haiku", run_in_background=true, prompt="...")
+
+// Wait all in single message:
+TaskOutput(task_id=t1)
+TaskOutput(task_id=t2)
 ```
 
 Scale: 1-2 agents per spec, cap 10.
@@ -157,4 +160,6 @@ rm .deepflow/checkpoint.json
 ✓ Merged df/doing-upload/20260202-1430 to main
 ✓ Cleaned up worktree and branch
 ✓ Spec complete: doing-upload → done-upload
+
+Workflow complete! Ready for next feature: /df:spec <name>
 ```