deepflow 0.1.33 → 0.1.35

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "deepflow",
-  "version": "0.1.33",
+  "version": "0.1.35",
   "description": "Stay in flow state - lightweight spec-driven task orchestration for Claude Code",
   "keywords": [
     "claude",

package/src/commands/df/execute.md

@@ -4,9 +4,9 @@
 
 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 commands (except status)
+**NEVER:** Read source files, edit code, run tests, run git commands (except status), use TaskOutput
 
-**ONLY:** Read PLAN.md, read specs/doing-*.md, spawn background agents, use TaskOutput to get results, update PLAN.md
+**ONLY:** Read PLAN.md, read specs/doing-*.md, spawn background agents, wait with Bash monitor, read `.deepflow/results/*.yaml` for outcomes, update PLAN.md
 
 ---
 
@@ -43,17 +43,53 @@ Statusline writes to `.deepflow/context.json`: `{"percentage": 45}`
 
 ## Agent Protocol
 
-Each task = one background agent. **TaskOutput blocks until agent completes and returns result directly.** Never poll, loop, or repeatedly check for results.
+Each task = one background agent. **NEVER use TaskOutput** — it returns full transcripts (100KB+) that explode context.
 
-```python
-# 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 Strategy: Bash Monitor**
+- One Bash call that monitors result files
+- Shows progress via streaming (user sees in real-time)
+- Minimal context (just the final output)
+- User can react/cancel if needed
 
-# Wait for all results (single message, multiple TaskOutput calls)
-# TaskOutput BLOCKS — no polling needed, result returned when agent finishes
-TaskOutput(task_id=task_id_1)
-TaskOutput(task_id=task_id_2)
+```python
+# 1. Spawn agents in parallel (single message, multiple Task calls)
+Task(subagent_type="general-purpose", run_in_background=True, prompt="T1: ...")
+Task(subagent_type="general-purpose", run_in_background=True, prompt="T2: ...")
+Task(subagent_type="general-purpose", run_in_background=True, prompt="T3: ...")
+
+# 2. Wait with Bash monitor (ONE call, streams progress to user)
+Bash("""
+RESULTS_DIR="{worktree}/.deepflow/results"
+EXPECTED=3
+TIMEOUT=300
+
+timeout $TIMEOUT bash -c '
+  seen=""
+  while [ $(ls "$0"/*.yaml 2>/dev/null | wc -l) -lt '$EXPECTED' ]; do
+    for f in "$0"/*.yaml 2>/dev/null; do
+      if [ -f "$f" ] && [[ ! "$seen" =~ "$f" ]]; then
+        echo "✓ $(basename "$f" .yaml)"
+        seen="$seen $f"
+      fi
+    done
+    sleep 5
+  done
+  echo "ALL COMPLETE"
+' "$RESULTS_DIR" || echo "TIMEOUT: some tasks did not complete"
+""")
+
+# 3. Read actual results (minimal context)
+Read("{worktree}/.deepflow/results/T1.yaml")
+Read("{worktree}/.deepflow/results/T2.yaml")
+Read("{worktree}/.deepflow/results/T3.yaml")
+```
+
+**User sees streaming:**
+```
+✓ T1
+✓ T3
+✓ T2
+ALL COMPLETE
 ```
 
 Result file `.deepflow/results/{task_id}.yaml`:
@@ -382,14 +418,18 @@ When all tasks done for a `doing-*` spec:
 
 ### 10. ITERATE
 
-After spawning agents, call TaskOutput for ALL running agents in a SINGLE message. **TaskOutput blocks—do NOT loop, poll, or check repeatedly.** One call per agent, results returned when complete.
+After spawning agents, use Bash monitor to wait. **NEVER use TaskOutput** — it explodes context.
 
 ```python
-# After spawning T1, T2, T3 in parallel, wait for all in parallel:
-TaskOutput(task_id=t1_id)  # BLOCKS until T1 done
-TaskOutput(task_id=t2_id)  # BLOCKS until T2 done
-TaskOutput(task_id=t3_id)  # BLOCKS until T3 done
-# All three in ONE message = parallel wait, zero polling
+# After spawning T1, T2, T3 in parallel:
+
+# 1. Wait with Bash monitor (streams progress to user)
+Bash("timeout 300 bash -c '...' ")  # See Agent Protocol for full script
+
+# 2. Read results
+Read("{worktree}/.deepflow/results/T1.yaml")
+Read("{worktree}/.deepflow/results/T2.yaml")
+Read("{worktree}/.deepflow/results/T3.yaml")
 ```
 
 Then check which tasks completed, update PLAN.md, identify newly unblocked tasks, spawn next wave.