feat(kanban): surface task_runs.summary on dashboard cards + kanban show#20251
Closed
Brecht-H wants to merge 1 commit into
Closed
feat(kanban): surface task_runs.summary on dashboard cards + kanban show#20251Brecht-H wants to merge 1 commit into
Brecht-H wants to merge 1 commit into
Conversation
… show``
The kanban-worker skill (built into the gateway dispatcher's spawn
prompt) instructs every worker to hand off via
``kanban_complete(summary=..., metadata=...)``. That writes the summary
onto the closing ``task_runs`` row, NOT onto ``tasks.result`` — the
latter is left NULL unless the caller passes ``result=`` explicitly.
Result: a glance at the dashboard or ``hermes kanban show <id>`` shows
a blank "Result:" section even when the worker did real work, which
on 2026-05-05 caused a Mac false-alarm ("Hermes did nothing") on a
task that had a 10-line completion summary on its run.
This patch surfaces the latest non-null run summary as
``latest_summary`` so the worker's actual handoff lands in front of
operators.
* New helpers ``kanban_db.latest_summary(conn, task_id)`` and
``kanban_db.latest_summaries(conn, task_ids)``. The batch variant
uses a single window-function SELECT so the dashboard board endpoint
doesn't pay an N+1 cost on multi-hundred-task boards.
* CLI ``hermes kanban show <id>`` prints a "Latest summary:" block
when ``tasks.result`` is empty but a run has produced a summary
(the existing "Result:" section still wins when populated, so the
back-compat path for hand-edited results is untouched). JSON output
gains a top-level ``latest_summary`` field.
* Dashboard ``/board`` and ``/tasks/{id}`` now include a
``latest_summary`` field on every task. Cards on /board carry a
200-character preview (cheap to render, plenty for "what did this
worker do?" at a glance); the drawer/detail endpoint returns the
full summary.
* Five new tests cover: empty-runs case, post-complete surface,
newest-of-multiple selection, empty-string skip, batch with
missing tasks + empty input.
Smoke-tested locally against the live profile DB on the three
acceptance-criterion targets (t_f08fef91 cron-hygiene-audit,
t_007b7f1c EMA-analysis, t_05746fa4 self-assessment) — all three now
return their populated summaries via both ``latest_summary`` and
``latest_summaries``.
Test plan: 255/255 kanban tests pass + 91/91 dashboard plugin tests
pass. No regression on tasks where ``tasks.result`` is explicitly
populated (the existing "Result:" branch is preserved).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR makes kanban task run handoffs visible to operators by surfacing the latest non-empty task_runs.summary as latest_summary in both the dashboard API and the CLI kanban show output, avoiding blank “Result” sections when workers complete via kanban_complete(summary=...).
Changes:
- Add
kanban_db.latest_summary()and batchkanban_db.latest_summaries()helpers to fetch the latest non-empty run summary (batch via a single window-function query). - Extend dashboard
/board(preview-truncated) and/tasks/{id}(full text) responses to includelatest_summaryper task. - Update
hermes kanban show <id>to print aLatest summary:block (and includelatest_summaryin JSON output) whentasks.resultis empty.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
hermes_cli/kanban_db.py |
Adds single-task and batch DB helpers to retrieve latest non-empty run summaries. |
plugins/kanban/dashboard/plugin_api.py |
Attaches latest_summary to task payloads for board cards (preview) and task detail (full). |
hermes_cli/kanban.py |
Enhances kanban show to surface the run summary when task.result is empty; JSON includes latest_summary. |
tests/hermes_cli/test_kanban_db.py |
Adds unit tests covering latest_summary/latest_summaries behavior and edge cases. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+813
to
+820
| # row to exist with a later ended_at. | ||
| conn.execute( | ||
| "UPDATE tasks SET status='ready', completed_at=NULL WHERE id=?", | ||
| (t,), | ||
| ) | ||
| # Sleep 1s so the second run's ended_at is provably later than | ||
| # the first (complete_task uses int(time.time())). | ||
| time.sleep(1.05) |
Comment on lines
+3497
to
+3504
| Picks the most recent run by ``ended_at`` (falling back to ``id`` | ||
| for ties or unfinished rows). Returns None if no run has a summary. | ||
| """ | ||
| row = conn.execute( | ||
| "SELECT summary FROM task_runs " | ||
| "WHERE task_id = ? AND summary IS NOT NULL AND summary != '' " | ||
| "ORDER BY COALESCE(ended_at, started_at) DESC, id DESC LIMIT 1", | ||
| (task_id,), |
Comment on lines
+3526
to
+3542
| placeholders = ",".join("?" for _ in ids) | ||
| rows = conn.execute( | ||
| f""" | ||
| SELECT task_id, summary FROM ( | ||
| SELECT task_id, summary, | ||
| ROW_NUMBER() OVER ( | ||
| PARTITION BY task_id | ||
| ORDER BY COALESCE(ended_at, started_at) DESC, id DESC | ||
| ) AS rn | ||
| FROM task_runs | ||
| WHERE task_id IN ({placeholders}) | ||
| AND summary IS NOT NULL AND summary != '' | ||
| ) WHERE rn = 1 | ||
| """, | ||
| ids, | ||
| ).fetchall() | ||
| return {r["task_id"]: r["summary"] for r in rows} |
Contributor
|
Merged via PR #20448 (rebase-merge, commit |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
The kanban-worker skill (built into the gateway dispatcher's spawn prompt) instructs every worker to hand off via
kanban_complete(summary=..., metadata=...). That writes the summary onto the closingtask_runsrow, not ontotasks.result— the latter is left NULL unless the caller explicitly passesresult=.A glance at the dashboard or
hermes kanban show <id>then shows a blank "Result:" section even when the worker did real work. On a multi-lane host this caused a 2026-05-05 false-alarm ("Hermes did nothing") on a task whose run carried a 10-line completion summary.This PR surfaces the latest non-null run summary as
latest_summaryso the worker's actual handoff lands in front of operators.Changes
kanban_db.latest_summary(conn, task_id)andkanban_db.latest_summaries(conn, task_ids). The batch variant uses a single window-function SELECT so the dashboard board endpoint doesn't pay N+1 on multi-hundred-task boards.hermes kanban show <id>prints aLatest summary:block whentasks.resultis empty but a run has produced a summary. The existingResult:section still wins when populated, so any hand-edited results path is untouched. JSON output gains a top-levellatest_summaryfield./boardand/tasks/{id}now include alatest_summaryfield on every task. Cards on/boardcarry a 200-character preview; the drawer/detail endpoint returns the full summary.Test plan
latest_summary*unit tests pass.tests/hermes_cli/test_kanban_*+ 91/91 intests/plugins/test_kanban_dashboard_plugin.py+tests/tools/test_kanban_tools.py.t_f08fef91,t_007b7f1c,t_05746fa4) — all return populated summaries via both helpers.latest_summarypreview.hermes kanban show <id>on a task whose worker calledkanban_complete(summary=...)(e.g. one of the three above) and verify the newLatest summary:block.Back-compat
tasks.resultIS populated (manual completion viahermes kanban complete <id> --result \"...\") keep the existingResult:section —latest_summaryis only used as a fallback whentasks.resultis empty._task_dictaddslatest_summaryas a new keyword argument with a None default, so existing callers (create-task / update-task responses) work unchanged and emitlatest_summary: nullin their payloads.🤖 Generated with Claude Code