Roles, capability profiles and help on the new loop (M2.6)

- roles.driver (unset: the planner's model) and roles.classifier (unset:
  the expert's); the mapping is pinned when an item opens, and the driver
  and the go-ahead reader run on the item's own (L9).
- profiles: in configuration (tools, strengths, weaknesses), used in
  briefings: the driver's instructions say what its helper and expert are
  good at, the helper's brief who reads its handback; never a model name.
- delegate(task) and ask_expert(question) for the driver. A helper works
  on a branch off the milestone's; on a handback its work comes back as
  uncommitted changes, otherwise it is discarded, so harness branches
  never hold commits only the clone has. ask_expert keeps its budget.
- Triggers: failure_limit failed commands in a row (Driver's new "stuck"
  outcome) or the turn cap, mid-milestone, call a helper in once per
  milestone; if it fails too, the item waits on the operator. A
  delegation cut off by a crash is discarded at boot.
- Evaluation capture: delegations and ask_expert as before, and the
  reader's verdicts as classifier pairs.

Tests: help tests (merge-back, discard, needs a milestone, the stuck
trigger and its once-per-milestone limit, the expert and its budget,
pinning, briefings by profile, boot discarding a cut-off delegation),
config tests for roles and profiles, and the walk delegating with a
scripted helper that sometimes fails, with a delegations_settle property.
The walk found helper commits stranded on a merged PR's branch, fixed by
returning a helper's work uncommitted.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE

nisse-dev/src/nisse_dev/delegation.py

@@ -54,8 +54,8 @@ Stay inside the sub-task you were given. It comes from a plan a human already
 approved; widening it is not yours to do. If the sub-task turns out to be
 wrong or impossible, say so in the handback rather than substituting your own.
 
-When you are done, call hand_back exactly once. Write it for a materially
-weaker model that cannot see your reasoning and will act on your note alone:
+When you are done, call hand_back exactly once. Write it for {reader},
+which cannot see your reasoning and will act on your note alone:
 
 - what changed
 - what is now true that was not before
@@ -172,10 +172,14 @@ class Delegation:
         caps: Caps | None = None,
         now: Callable[[], float] = time.monotonic,
         cancel: Cancel | None = None,
+        reader: str = "",
     ) -> None:
         self._client = client
         self._store = store
         self._workspace = workspace
+        # Who acts on the handback, from its capability profile (L9): never
+        # a model's name.
+        self._reader = reader or "a materially weaker model"
         self._git = git_repo
         self._model = model
         self._backing_model = backing_model
@@ -323,7 +327,8 @@ class Delegation:
         self, transcript: Transcript, brief: str, branch: str, started_at: float
     ) -> DelegationResult:
         system = (
-            f"{SYSTEM_PROMPT}\n\n{self._workspace.describe()}"
+            f"{SYSTEM_PROMPT.format(reader=self._reader)}\n\n"
+            f"{self._workspace.describe()}"
             f"\n\nYour sub-task:\n{brief}"
         )
         touched: set[str] = set()