hermes-agent/website/docs/user-guide
Teknium 2ba1cfeb2e
feat(goals): completion contracts for /goal — evidence-based judging (#50501)
Adds an optional structured completion contract to the standing-goal loop,
adapted from OpenAI Codex's /goal guidance (a durable objective works best
when it names what done means, how to prove it, what not to break, what's in
scope, and when to stop).

A contract has five optional fields — outcome, verification, constraints,
boundaries, stop_when. When set, the continuation prompt tells the agent to
target the verification surface and respect constraints, and the judge marks
the goal done only when the verification criterion is met with concrete
evidence (command result, file excerpt, test output) instead of a loose
"looks done" claim. This tightens the most common /goal failure mode:
premature completion / endless over-continuation on an underspecified goal.

Two ways to set a contract, both backward compatible (bare /goal <text>
behaves exactly as before):
- /goal draft <objective>  — expands plain text into a full contract via the
  goal_judge aux model (cache-safe side call), falls back to a free-form goal
  if the model is unavailable.
- /goal <text> with inline 'field: value' lines (verify:, constraints:,
  boundaries:, stop when:, ...). Plain goals with an incidental colon are not
  mangled — only known field prefixes are pulled out.
- /goal show prints the active contract.

Contracts persist in SessionDB.state_meta alongside the goal (survive /resume),
compose with /subgoal criteria, and old goal rows load unchanged. CLI + every
gateway platform via the shared GoalManager engine; zero new model tools.

Tests: +18 in tests/hermes_cli/test_goals.py (parse/serialize/judge-prompt/
draft/fallback), 73/73 green; 42/42 across the broader goal test surface;
live E2E roundtrip (set -> persist -> reload -> contract-aware prompts) green.
2026-06-22 12:20:09 -07:00
..
features feat(goals): completion contracts for /goal — evidence-based judging (#50501) 2026-06-22 12:20:09 -07:00
messaging Make email pairing opt-in 2026-06-21 22:43:57 -07:00
secrets feat(secrets/bitwarden): EU Cloud + self-hosted server URL support (#31378) 2026-05-24 02:19:57 -07:00
skills feat(providers): remove google-gemini-cli + google-antigravity OAuth providers (#50492) 2026-06-21 19:53:27 -07:00
_category_.json
checkpoints-and-rollback.md feat(checkpoints): v2 single-store rewrite with real pruning + disk guardrails (#20709) 2026-05-06 05:44:35 -07:00
cli.md docs: deep audit — registry drift, stale claims, 2-week PR coverage, dashboard screenshot (#40952) 2026-06-07 01:39:06 -07:00
configuration.md Make email pairing opt-in 2026-06-21 22:43:57 -07:00
configuring-models.md fix(cli): warn when in-session model switch will preflight-compress 2026-06-21 16:29:31 +05:30
desktop.md docs: sync documentation with current implementation 2026-06-20 23:23:47 -07:00
docker.md fix(docker): replace dashboard --insecure with basic-auth provider 2026-06-21 19:05:27 -07:00
git-worktrees.md docs: deep audit — registry drift, stale claims, 2-week PR coverage, dashboard screenshot (#40952) 2026-06-07 01:39:06 -07:00
managed-scope.md docs: add managed scope admin guide + cross-link from configuration 2026-06-19 07:46:33 -07:00
multi-profile-gateways.md docs(gateway): document multiplexing opt-in + contract changes 2026-06-19 07:34:15 -07:00
profile-distributions.md Expand .gitignore example 2026-06-20 20:42:49 -07:00
profiles.md fix: make profile subprocess HOME policy explicit 2026-06-14 03:20:21 -07:00
security.md Make email pairing opt-in 2026-06-21 22:43:57 -07:00
sessions.md docs: fix session recap image baseUrl 2026-05-29 12:06:22 -07:00
tui.md docs(tui): correct HERMES_TUI_GATEWAY_URL — dashboard-internal, not remote-attach (#42162) 2026-06-08 09:37:03 -07:00
windows-native.md docs(windows): correct native data dir to %LOCALAPPDATA%\hermes (#42856) 2026-06-09 14:11:20 -05:00
windows-wsl-quickstart.md fix(docs): update all install instructions everywhere 2026-06-04 21:07:45 -04:00