Document rolling captain teams

docs/modernization/director-workflow.md

@@ -15,6 +15,8 @@ a task is complex. The default is still one agent executing one task from
 - Use stronger models only where they change the outcome.
 - Keep each implementation slice measurable, validated, committed, and pushed.
 - Avoid merge conflicts by giving every agent a disjoint task and file scope.
+- Keep teams rolling: when one team finishes, integrate or park its result and
+  start the next disjoint team without waiting for every other team to finish.
 
 ## Roles
 
@@ -55,13 +57,16 @@ example:
 - dependency cleanup
 - test/hardening work
 
-The captain owns implementation for its assigned task group. The captain turns
+The captain owns implementation for its assigned task group. A team should be a
-one task-group objective into smaller disjoint subtasks, spawns or requests
+captain plus multiple workers when the work can be split into disjoint files.
-workers when useful, reviews their changes, runs focused validation when cheap,
+The captain turns one task-group objective, or a small coherent run of adjacent
-and returns an integration-ready result. If nested subagents are available, the
+task rows, into smaller disjoint subtasks, spawns or requests workers when
-captain may spawn workers. If nested subagents are not available in the current
+useful, reviews their changes, runs focused validation when cheap, and returns
-surface, the captain returns a worker plan and the director performs the
+an integration-ready result. If nested subagents are available, the captain may
-second-level spawns without taking over implementation.
+spawn workers and continue through the next compatible subtask after each worker
+returns. If nested subagents are not available in the current surface, the
+captain returns a worker plan and the director performs the second-level spawns
+without taking over implementation.
 
 The captain must not edit broad shared files unless assigned. The captain must
 not rewrite the task tracker or roadmap except for a requested status note.
@@ -111,38 +116,47 @@ has requested `gpt-5.4` captains, so use that override for captains.
 - Prefer the smallest number of teams that keeps disjoint work moving. Multiple
   captains are appropriate when task rows have non-overlapping write scopes and
   can validate independently. Avoid many agents in one file family.
+- Do not synchronize all teams at a barrier unless validation or merge risk
+  requires it. Use rolling integration: wait for whichever team finishes first,
+  process that result, then immediately start another disjoint team if ready
+  work remains.
 
 ## Delegation Flow
 
-1. Director picks one or more `Ready` tasks from
+1. Director picks two or more `Ready` tasks from
    `docs/modernization/tasks.md` with disjoint write scopes.
 2. Director assigns each independent task group to a `gpt-5.4` captain.
 3. Captains implement directly or coordinate workers/explorers for disjoint
-   subtasks.
+   subtasks, and may continue through a coherent sequence of adjacent tasks
+   within the assigned scope.
 4. Captains run focused validation when cheap and return changed files,
    validation, blockers, and integration notes.
-5. Director reviews for scope conflicts and integrates returned changes.
+5. Director waits for whichever team finishes first, reviews for scope
-6. Director runs the listed validation command or the quiet checkpoint wrapper.
+   conflicts, integrates returned changes, and starts the next disjoint team
+   while other teams keep running.
+6. Director runs the listed validation command or the quiet checkpoint wrapper
+   for each integrated slice.
 7. Director updates `tasks.md`, `debt.md`, and `roadmap.md` if tasks moved.
-8. Director commits and pushes the verified slice.
+8. Director commits and pushes verified slices incrementally.
 
 ## Director Prompt Template For A Captain
 
 ```text
 You are the gpt-5.4 team captain for the <group> task group in PanoPainter.
 
-Task source: docs/modernization/tasks.md task <TASK-ID>.
+Task source: docs/modernization/tasks.md task(s) <TASK-ID-LIST>.
 Debt ids: <DEBT-LIST>.
 Assigned scope: <FILES/DIRS>.
 Validation: <COMMANDS>.
 
 Goal: <ONE PARAGRAPH>.
 
-Own this task group through implementation. Split into disjoint worker tasks
+Own this task group through implementation. Build a small team of workers for
-only when that is faster or safer than doing the bounded edits yourself. Use
+disjoint subtasks when possible, review their outputs, and keep looping through
-gpt-5.4 only for risky C++ behavior changes. Keep tasks small enough to
+the assigned coherent task sequence until the scope is done, blocked, or no
-validate. Do not edit outside the assigned scope. Other agents may be working
+longer safe to continue. Use gpt-5.4 only for risky C++ behavior changes. Keep
-in parallel; do not revert unrelated changes.
+tasks small enough to validate. Do not edit outside the assigned scope. Other
+agents may be working in parallel; do not revert unrelated changes.
 
 Return:
 - recommended worker tasks with model choice and file scope