deepflow 0.1.32 → 0.1.33

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "deepflow",
3
- "version": "0.1.32",
3
+ "version": "0.1.33",
4
4
  "description": "Stay in flow state - lightweight spec-driven task orchestration for Claude Code",
5
5
  "keywords": [
6
6
  "claude",
@@ -43,7 +43,7 @@ Statusline writes to `.deepflow/context.json`: `{"percentage": 45}`
43
43
 
44
44
  ## Agent Protocol
45
45
 
46
- Each task = one background agent. Use TaskOutput to wait for results. Never poll files in a loop.
46
+ Each task = one background agent. **TaskOutput blocks until agent completes and returns result directly.** Never poll, loop, or repeatedly check for results.
47
47
 
48
48
  ```python
49
49
  # Spawn agents in parallel (single message, multiple Task calls)
@@ -51,6 +51,7 @@ task_id_1 = Task(subagent_type="general-purpose", run_in_background=True, prompt
51
51
  task_id_2 = Task(subagent_type="general-purpose", run_in_background=True, prompt="T2: ...")
52
52
 
53
53
  # Wait for all results (single message, multiple TaskOutput calls)
54
+ # TaskOutput BLOCKS — no polling needed, result returned when agent finishes
54
55
  TaskOutput(task_id=task_id_1)
55
56
  TaskOutput(task_id=task_id_2)
56
57
  ```
@@ -381,13 +382,14 @@ When all tasks done for a `doing-*` spec:
381
382
 
382
383
  ### 10. ITERATE
383
384
 
384
- After spawning agents, wait for results using TaskOutput. Call TaskOutput for ALL running agents in a SINGLE message (parallel wait).
385
+ 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.
385
386
 
386
387
  ```python
387
388
  # After spawning T1, T2, T3 in parallel, wait for all in parallel:
388
- TaskOutput(task_id=t1_id) # These three calls go in ONE message
389
- TaskOutput(task_id=t2_id)
390
- TaskOutput(task_id=t3_id)
389
+ TaskOutput(task_id=t1_id) # BLOCKS until T1 done
390
+ TaskOutput(task_id=t2_id) # BLOCKS until T2 done
391
+ TaskOutput(task_id=t3_id) # BLOCKS until T3 done
392
+ # All three in ONE message = parallel wait, zero polling
391
393
  ```
392
394
 
393
395
  Then check which tasks completed, update PLAN.md, identify newly unblocked tasks, spawn next wave.