FN-7312: send task context to planner chat

Send bounded task state into task-detail planner chat so status and progress questions can be answered in context.

- Build reusable server-side planner chat context from task metadata, dependencies, steps, comments, activity, source, and review state.
- Pass and validate the task id on planner chat sends to keep sessions scoped to the current task.
- Update planner chat copy, docs, tests, and changeset coverage for task-aware status/progress questions.

Files changed:
 .changeset/fn-7312-task-planner-chat-context.md    |   7 +
 docs/dashboard-guide.md                            |   4 +-
 packages/dashboard/app/api/legacy.ts               |   5 +-
 .../app/components/TaskPlannerChatTab.tsx          |   5 +-
 .../__tests__/TaskPlannerChatTab.test.tsx          |  22 ++
 .../dashboard/src/__tests__/chat-manager.test.ts   |  17 +-
 .../dashboard/src/__tests__/chat-routes.test.ts    |  76 +++++
 .../__tests__/task-planner-chat-context.test.ts    | 165 +++++++++++
 packages/dashboard/src/chat.ts                     |  92 +-----
 .../dashboard/src/routes/register-chat-routes.ts   |  11 +-
 .../dashboard/src/task-planner-chat-context.ts     | 326 +++++++++++++++++++++
 11 files changed, 634 insertions(+), 96 deletions(-)

Fusion-Task-Id: FN-7312

Fusion-Task-Lineage: 90cf0fe3-3984-4a67-bb44-fce492c256eb

Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>

docs/dashboard-guide.md

@@ -1042,7 +1042,7 @@ Inspect task definition, logs, review feedback, comments, artifacts, workflow ou
 - Editable tasks with descriptions show **Summarize as title** beside the read-mode title; it asks AI to generate a concise title from the description and saves it without opening the edit form.
 - The **Summary** tab appears first for `done` tasks and is their default landing tab. It shows the recorded completion summary, changed-file/merge stats when available, completed steps, workflow results, retry counts, and a token usage & cost section broken down by model from the already-loaded task detail; unpriced models show cost as unavailable rather than `$0`. Non-`done` tasks still open on **Activity** by default.
 - The **Activity → Current** segment includes an expand/collapse control that lets the transcript and composer fill the task-detail modal, then restores the normal header, tabs, and action footer when collapsed.
-- The top-level **Chat** tab appears immediately after **Activity** and starts a task-scoped planner-model conversation. It uses the task's effective planning model, persists messages in a resumable chat session, shows starter prompts for common planning questions, can render structured planner questions, and converts only explicit operator steering intent through the scoped steering tool. Activity remains the primary operational transcript/feed/raw-log surface.
+- The top-level **Chat** tab appears immediately after **Activity** and starts a task-scoped planner-model conversation. It uses the task's effective planning model, persists messages in a resumable chat session, and sends bounded server-built task context so the planner can answer current status, progress, recent activity, dependency, and task definition questions without polluting visible chat history. It shows starter prompts for common planning questions, can render structured planner questions, and converts only explicit operator steering intent through the scoped steering tool. Activity remains the primary operational transcript/feed/raw-log surface.
 - Task-detail Activity steering comments are persisted as user comments/steering guidance and surfaced to every relevant agent lane: live executor sessions receive steering injection, while planner, reviewer (spec/plan/code), and merger agents (standard and clean-room AI merge/review) receive the latest user comments in their next prompt/pass.
 - The priority chip in task metadata is an inline picker: you can change priority directly without entering full edit mode.
 - Execution mode has a read-mode inline lightning-bolt toggle for Fast mode on/off without opening the full edit form.
@@ -1121,7 +1121,7 @@ Recommended workflow: ordinary chains stay as `Blocks N` so noise stays low, hig
 <!-- FNXC:TaskDetailPlannerChat 2026-06-30-22:30: Activity Current is the explicit operational steering-comment entry surface. Feed and Raw Logs remain read-only Activity segments, and the top-level Chat tab is intentionally separate planner-model conversation rather than steering. -->
 The **Activity** tab is the first task-detail tab and presents a segmented control for **Current**, **Feed**, and **Raw Logs**. Current contains the live, chat-styled transcript of task agent output. Consecutive entries are grouped by role and labeled as Planner, Executor, Reviewer, or Merger; legacy log rows without an agent role use the neutral Agent fallback. Agent group headers and user message headers show a small muted relative timestamp (for example, “just now”, “1m ago”, or “2h ago”) based on the transcript timestamp, while agent group metadata still includes the entry count. Consecutive text/message chunks inside a role group render as one continuous markdown bubble, while consecutive tool/tool-result/tool-error rows collapse into one expandable, compact tool-call summary that stays collapsed by default and mirrors regular Chat's dense treatment; the summary stays single-line/ellipsis-friendly on desktop and mobile, counts tool invocations, lists deduped tool names with overflow, and shows an error count when failures are present, while the expanded body pairs each call with its result or error in dense entry cards. Thinking entries render in a collapsible block that starts expanded. The transcript opens at the latest output whenever the tab loads or becomes active, then follows new live output when you are already near the bottom while preserving your scroll position when you review older messages. When older task-agent history exists, scrolling to the top or selecting **Load previous messages** prepends earlier transcript entries without moving the message you were reading. When you scroll away from the bottom of a populated transcript, a sticky **Latest** button appears inside the transcript so you can jump back to the newest message and resume live follow. For non-`done` tasks, the **Steering comment** composer sends guidance through the same steering path used by comments, including active planning/triage, `in-progress`, and `in-review` sessions, plus live CLI-agent sessions reported by the session bridge; an `in-review` Activity Current message or Comments-tab task comment re-engages an executor unless an open PR blocks moving the task back, and other messages are still saved as queued guidance when no session is currently live. Feed and Raw Logs do not show a steering composer. On a `done` task, the composer switches to **Refinement request** copy; sending starts a refinement task using the typed text as feedback and shows a success toast with the new task ID, while the current task detail modal remains on the completed task. The task-detail Activity Current segment keeps the composer pinned and visible on mobile and desktop while the transcript scrolls internally; its textarea placeholder reads “Steer the currently executing agent” for steering mode and switches to refinement copy for completed tasks, with the same inline, icon-only send affordance to the right of the input at every breakpoint. In the composer, plain **Enter** sends, **Shift+Enter** inserts a newline, and **Cmd/Ctrl+Enter** remains a supported send shortcut.
 
-The adjacent top-level **Chat** tab opens the planner-model conversation for the same task instead of posting steering comments. When no planner-chat history has loaded yet, Chat shows a guided empty state with starter prompts for recent activity, current status/blockers, next best action, and plan/definition review; selecting one sends that prompt as an ordinary chat message through the planner-chat composer/stream path. The starter prompts disappear while history is loading or after conversation history exists, so Activity Current, Feed, Raw Logs, and the steering composer remain separate.
+The adjacent top-level **Chat** tab opens the planner-model conversation for the same task instead of posting steering comments. Each send includes server-built, bounded context for the task id, status/column/progress/current step, dependencies, recent activity/comment excerpts, prompt/plan content, and available source/review state; unavailable sections are labeled so the planner states uncertainty rather than inventing execution evidence. When no planner-chat history has loaded yet, Chat shows a guided empty state with starter prompts for recent activity, current status/blockers, next best action, and plan/definition review; selecting one sends that prompt as an ordinary chat message through the task-context-aware planner-chat composer/stream path. The starter prompts disappear while history is loading or after conversation history exists, so Activity Current, Feed, Raw Logs, and the steering composer remain separate.
 
 The **Raw Logs** segment is designed for debugging long-running and tool-heavy sessions, while legacy links that requested the former top-level Logs tab land on Activity → Feed: