feat(orchestrator): S5 Tasks with choices, Gantt, estimates and burn charts

Requirement 001 phase 6, S5:

- Tasks tab: every pending ask, rule request, operator row and choice
  card shows under "waits on Operator"; a choice request goes out on a
  fixed channel button, post and call with an agent multi-select, and a
  click on an option sends a passkey-signed answer the agent checks with
  operator_message. The unsigned /api/decisions/<id>/choose route is
  gone, and a decision, choice answer or choice recipient whose name
  holds "*" is refused, so a signed answer never reaches every agent.
- Gantt view: one bar per task from start to end (running to now), one
  arrow per explicit, branch-base and queue-order edge, hatched forecast
  bars (always, points only, real only) from the median duration or
  points times median hours per point.
- rasci.py set --after/--drop-after stores task dependencies and refuses
  unknown tasks and cycles.
- Estimation toggle (No estimate default, Story points) is stored in the
  hub settings; burndown and burnup per whole register, list filter or
  one agent or line, counting tasks or summing complexity with the
  unestimated tasks as their own line.
- New skill kvb-org-queue-estimate: "Request estimates" (story points
  mode, passkey-signed board action) or the skill sends exactly one
  newsletter listing every unestimated task with its RASCI parties; a
  party name that is no plain name shows as "unnamed party".
- Business value per task or in bulk is stored only with a verified
  passkey assertion over the exact ids and values; WSJF uses it instead
  of the median. The task list sorts by every decision-50 mode both ways.
- e2e: the walk's pending ask lives an hour instead of 60 s, and the
  CDP and BiDi drivers retry removing the browser profile while the
  browser exits (ENOTEMPTY).

Evidence: make test 709 OK, ruff and markdownlint clean
(/tmp/s5-make-test-fix-2.log); e2e 26 OK in Chromium and Firefox
(/tmp/s5-e2e-fix-2.log); MEDUSA 50 files, an independent skeptic
rejected four holes (unsigned choose route, unsigned estimates request,
free-text party names, "*" recipients incl. normalizer bypasses), all
fixed and re-verified, the 8 remaining pattern hits accepted, rescan 0
open.

🎯 Fix: 92 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 88
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

orchestrator/kvb_orchestrator/mcp.py

@@ -5,6 +5,7 @@ from http import HTTPStatus
 
 from . import NAME
 from .asking import OPTION_LIMIT
+from .choosing import CHOICE_REQUEST
 from .errors import RpcError, ToolError
 from .fields import WAIT_CAP
 from .requesting import AGENT_CAP
@@ -64,19 +65,22 @@ class Mcp:
             tool("review_list", "List the pending reviews.", {}),
             tool(
                 "decision_request",
-                "Ask the operator to pick one of several options in the Agent Orchestrator; each option becomes a button. "
-                "Returns the decision id and the hub URL.",
+                "Ask the operator to pick one of several options in the Agent Orchestrator; the question shows as a choice card "
+                "under Waits on Operator in the Tasks tab and each option becomes a button. When an operator message asks "
+                f'"{CHOICE_REQUEST}", send each open decision of kvb-think-choice through this tool. Returns the decision id and the hub URL.',
                 {
                     "question": text_property("The question, plain text."),
                     "options": {"type": "array", "minItems": 1, "maxItems": OPTION_LIMIT, "items": option, "description": "The choices, at least one."},
-                    "agent": text_property("Your agent name, shown with the question."),
+                    "agent": text_property("Your agent name, shown with the question; the operator's signed answer is a post to it."),
                     "recommended": text_property("The label of the option you recommend, or an empty string."),
                 },
             ),
             tool(
                 "decision_wait",
-                f"Wait until the operator picks an option or the timeout passes, then return the status "
-                f"(pending, decided) and the chosen label. Waits at most {WAIT_CAP} seconds.",
+                "Wait until the operator picks an option or the timeout passes, then return the status "
+                "(pending, decided), the chosen label and, for a click, message and answer: the id and text of the operator's "
+                "passkey-signed answer, a post to the asking agent; check it with operator_message(message, answer, your name) "
+                f"before acting on the choice. Waits at most {WAIT_CAP} seconds.",
                 {"id": text_property("Decision id that decision_request returned."), "timeout_seconds": wait},
             ),
             tool(