feat(kanban): add human_review status + review/approve/reject tools and CLI by sahilm-ti · Pull Request #30967 · NousResearch/hermes-agent

sahilm-ti · 2026-05-23T13:46:14Z

What

Differentiates automated review (existing review status — dispatcher auto-spawns the sdlc-review agent) from human review (new human_review status — parked, waits for the human reviewer to approve / reject).

Also surfaces a CLI + tool API for manual transitions, so a worker can request review itself after opening a PR.

running ─► review ──[agent passes; merges PR]──► human_review ──[approve]──► done
                                                              ──[reject]───► ready
        ─► review ──[agent rejects]────────────────────────────────────────► ready

Changes

hermes_cli/kanban_db.py

human_review added to VALID_STATUSES.
New atomic CAS helpers: move_to_review, move_to_human_review, approve_task, reject_task. Each writes a dedicated audit event (review_requested / human_review_requested / approved / rejected) so the notifier and dashboard can render different glyphs per kind.
approve_task clears the failure counter, recomputes ready for dependents, and cleans up the workspace (mirrors complete_task).
reject_task flips status back to ready (not stuck running without a claim) and synthesises a closing run so the rejection rationale surfaces via the normal prior-runs path on the next worker's kanban_show.
dispatch_once skips human_review tasks: no auto-spawn. The gateway notifier path is the only thing that fires for them.

hermes_cli/kanban.py (CLI)

New subcommands: hermes kanban review, human-review, approve, reject. Pattern matches the existing block / unblock / complete subcommands.

tools/kanban_tools.py (worker tool surface)

kanban_review, kanban_human_review, kanban_approve, kanban_reject. Mirror the kanban_block / kanban_complete shape. Worker-ownership enforced on the worker-initiated transitions.

gateway/run.py (notifier)

TERMINAL_KINDS extended with the three new event kinds.
Renders ⏳ for human_review_requested, ✅ for approved, ↩ for rejected. All capped at NOTIFY_BLOCKED_REASON_MAX (1500 chars), consistent with the blocked-reason path.

Tests

tests/hermes_cli/test_kanban_human_review.py — 12 tests covering: status validity, each transition (success + rejection from wrong source status), CAS atomicity (approve_task is idempotent on the second call), and the dispatcher's hands-off behavior for human_review.
tests/gateway/test_kanban_notifier_human_review.py — 3 tests pinning the glyph + content of each new notifier message.

All 174 kanban + notifier tests pass locally. Ruff clean on all touched files.

Out of scope

The sdlc-review skill itself (already proposed in a separate config repo PR).
Updating orchestrator / worker / engineering-process skills to teach them the new flow (separate task).

The kanban terminal-event notifier was hard-truncating payloads at 160-200 chars, which made blocked notifications routinely unactionable — users couldn't see the question the worker was asking without opening the dashboard. Extract the caps as named module-level constants and bump them per event kind: - NOTIFY_BLOCKED_REASON_MAX = 1500 (was 160; this is the one users actually answer) - NOTIFY_DONE_SUMMARY_MAX = 800 (was 200) - NOTIFY_GAVE_UP_ERROR_MAX = 600 (was 200) - NOTIFY_DONE_RESULT_LEGACY_MAX = 400 (was 160; legacy task.result field, kept smaller because new code uses summary) All caps stay under Discord/Slack's ~2000-char single-message ceiling so the largest payload still fits in one chat message on the tightest platform we target. Telegram (4096) has plenty of headroom. Tests cover: blocked carries the full reason, blocked truncates at the documented cap on overflow, done carries the extended summary, gave_up carries the extended error, and the cap budget stays ordered (blocked > done > error > legacy result) so a chatty done summary can't crowd out a critical blocked reason.

…ions Adds a second review-flavored status to differentiate automated review (the existing 'review' column the dispatcher auto-claims with the sdlc-review agent) from human review (parked, awaiting Sahil's decision). Workflow: running -> review --[agent passes; merges PR]--> human_review --[approve]--> done --[reject]---> ready -> review --[agent rejects]----------------> ready kanban_db.py - 'human_review' added to VALID_STATUSES. - New atomic helpers: move_to_review, move_to_human_review, approve_task, reject_task. Each does CAS on the expected source status and writes a dedicated audit event (review_requested / human_review_requested / approved / rejected) so the notifier and dashboard can render differently per kind. approve_task also clears the failure counter, recomputes ready for dependents, and cleans up the workspace (mirroring complete_task). - dispatch_once skips human_review tasks: no auto-spawn. The gateway notifier subscription path is the only thing that fires for them. CLI (hermes_cli/kanban.py) - New subcommands: review / human-review / approve / reject. Pattern matches block/unblock/complete: positional task_id, optional reason with a comment+event audit trail. Tool surface (tools/kanban_tools.py) - kanban_review, kanban_human_review, kanban_approve, kanban_reject. Mirror kanban_block/kanban_complete shape. Worker-ownership enforced on the worker-initiated transitions (review, human_review). Gateway notifier (gateway/run.py) - TERMINAL_KINDS includes the three new event kinds. - Renders ⏳ for human_review_requested, ✅ for approved, ↩ for rejected, all capped at NOTIFY_BLOCKED_REASON_MAX. Tests - tests/hermes_cli/test_kanban_human_review.py: 12 tests covering status validity, each transition, CAS atomicity, and dispatcher hands-off behavior. - tests/gateway/test_kanban_notifier_human_review.py: 3 tests pinning the notifier glyph + content for each new event kind. 174 kanban + notifier tests pass; ruff clean on all touched files.

daimon-nous · 2026-05-23T13:54:36Z

Implements #29171 (first-class waiting states for human/approval/review gates). Also addresses #29457 (task request for approval). Related to closed #27890 (awaiting_human_ops, earlier attempt).

sahilm-ti · 2026-05-23T13:56:44Z

Closing — opened in error by a kanban worker. Will be reopened against sahilm-ti/hermes-agent (the personal fork). Hermes-agent PRs from this install should target the fork only, not upstream.

Add the new 'human_review' status (introduced alongside the kanban_review/approve/reject machinery) to the dashboard's column list so cards in that state are actually visible on the board. Backend: append "human_review" between "review" and "done" in plugins/kanban/dashboard/plugin_api.py::BOARD_COLUMNS. The endpoint already buckets tasks by status into BOARD_COLUMNS, so this is the only Python change required. Frontend (dist/index.js — there is no src/ tree, the bundled JS is the canonical UI): - COLUMN_ORDER: extended to the full status list (scheduled and review were also missing from the JS fallback). The render loop iterates board.columns from the API, so missing keys here would just degrade labels; aligning it with the backend keeps the frontend's hard-coded order honest. - FALLBACK_COLUMN_LABEL / FALLBACK_COLUMN_HELP: added entries for scheduled, review, and human_review so the dashboard renders sane text when the i18n catalog has no key. - COLUMN_DOT: added scheduled/review/human_review classes. Style (dist/style.css): added .hermes-kanban-dot-scheduled, .hermes-kanban-dot-review, .hermes-kanban-dot-human-review with distinct colors so the new columns are visually distinguishable. The Python human_review status itself ships on the feat/kanban-human-review branch and PR NousResearch#30967; this change is a no-op until that lands but is safe to merge independently — any tasks ever set to status='human_review' will now have a home.

Add the new 'human_review' status (introduced alongside the kanban_review/approve/reject machinery) to the dashboard's column list so cards in that state are actually visible on the board. Backend: append "human_review" between "review" and "done" in plugins/kanban/dashboard/plugin_api.py::BOARD_COLUMNS. The endpoint already buckets tasks by status into BOARD_COLUMNS, so this is the only Python change required. Frontend (dist/index.js — there is no src/ tree, the bundled JS is the canonical UI): - COLUMN_ORDER: extended to the full status list (scheduled and review were also missing from the JS fallback). The render loop iterates board.columns from the API, so missing keys here would just degrade labels; aligning it with the backend keeps the frontend's hard-coded order honest. - FALLBACK_COLUMN_LABEL / FALLBACK_COLUMN_HELP: added entries for scheduled, review, and human_review so the dashboard renders sane text when the i18n catalog has no key. - COLUMN_DOT: added scheduled/review/human_review classes. Style (dist/style.css): added .hermes-kanban-dot-scheduled, .hermes-kanban-dot-review, .hermes-kanban-dot-human-review with distinct colors so the new columns are visually distinguishable. The Python human_review status itself ships on the feat/kanban-human-review branch and PR NousResearch#30967; this change is a no-op until that lands but is safe to merge independently — any tasks ever set to status='human_review' will now have a home. Co-authored-by: Sahil Marwaha <sahilm@triangleinvestments.com>

Sahil Marwaha added 2 commits May 23, 2026 18:20

daimon-nous Bot added type/feature New feature or request P3 Low — cosmetic, nice to have comp/cli CLI entry point, hermes_cli/, setup wizard comp/gateway Gateway runner, session dispatch, delivery comp/tools Tool registry, model_tools, toolsets labels May 23, 2026

sahilm-ti closed this May 23, 2026

This was referenced May 25, 2026

feat(kanban): add human_review status + review/approve/reject tools and CLI sahilm-ti/hermes-agent#1

Merged

fix(kanban-dashboard): add human_review column to BOARD_COLUMNS sahilm-ti/hermes-agent#3

Closed

alt-glitch mentioned this pull request Jun 9, 2026

Kanban review status exists but has no first-class request-review transition #42896

Open

Navigation Menu

Uh oh!

feat(kanban): add human_review status + review/approve/reject tools and CLI - #30967

feat(kanban): add human_review status + review/approve/reject tools and CLI#30967
sahilm-ti wants to merge 2 commits into
NousResearch:mainfrom
sahilm-ti:feat/kanban-human-review

sahilm-ti commented May 23, 2026

Uh oh!

daimon-nous Bot commented May 23, 2026

Uh oh!

sahilm-ti commented May 23, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

sahilm-ti commented May 23, 2026

What

Changes

Tests

Out of scope

Uh oh!

daimon-nous Bot commented May 23, 2026

Uh oh!

sahilm-ti commented May 23, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant