mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-06-09 08:21:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

docs(update): document updates.* config keys (pre_update_backup, backup_keep, non_interactive_local_changes) (#40617)

Browse source 
Salvaged from #40540; re-verified on main, tightened, tested.

Co-authored-by: jiangkoumo <jiangkoumo@users.noreply.github.com>
This commit is contained in:
Teknium 2026-06-07 18:29:56 -07:00 • committed by GitHub
parent 2aa316ec9c
commit ad399b9229
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 3 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

2
cli-config.yaml.example
View file

@ -885,7 +885,7 @@ delegation:
max_iterations: 50 # Max tool-calling turns per child (default: 50)
# max_concurrent_children: 3 # Max parallel child agents per batch (default: 3, floor: 1, no ceiling).
# WARNING: values above 10 multiply API cost linearly.
# max_spawn_depth: 1 # Delegation tree depth (floor 1, no ceiling; default: 1 = flat).
# max_spawn_depth: 1 # Delegation tree depth cap (range: 1-3, default: 1 = flat).
# Raise to 2 to allow workers to spawn their own subagents.
# Requires role="orchestrator" on intermediate agents.
# orchestrator_enabled: true # Kill switch for role="orchestrator" children (default: true).

16
website/docs/reference/cli-commands.md
View file

@ -1361,22 +1361,6 @@ hermes dashboard
hermes dashboard --port 8080 --no-open
```
### `hermes dashboard register`
Register this install as a self-hosted dashboard with your Nous Portal account, so the dashboard's OAuth (Nous) auth gate can be used. Resolves your existing Nous login (run `hermes setup` first if you're not logged in), creates an OAuth client, writes `HERMES_DASHBOARD_OAUTH_CLIENT_ID` into `~/.hermes/.env`, and prints how to engage the login gate. You can also register, name, and revoke dashboards from the Portal [`/local-dashboards`](https://portal.nousresearch.com/local-dashboards) page.
| Option | Default | Description |
|--------|---------|-------------|
| `--name` | auto-generated | Human-readable label for the dashboard |
| `--redirect-uri` | — | Public HTTPS OAuth redirect URI for an internet-facing host, e.g. `https://hermes.example.com/auth/callback`. Omit for localhost-only use. |
```bash
hermes dashboard register
# ✓ Registered dashboard "swift_falcon"
# …writes HERMES_DASHBOARD_OAUTH_CLIENT_ID to ~/.hermes/.env
```
## `hermes profile`
```bash

4
website/docs/user-guide/configuration.md
View file

@ -1691,7 +1691,7 @@ delegation:
# api_key: "local-key" # API key for base_url (falls back to OPENAI_API_KEY)
# api_mode: "" # Wire protocol for base_url: "chat_completions", "codex_responses", or "anthropic_messages". Empty = auto-detect from URL (e.g. /anthropic suffix → anthropic_messages). Set explicitly for non-standard endpoints the heuristic can't detect.
max_concurrent_children: 3 # Parallel children per batch (floor 1, no ceiling). Also via DELEGATION_MAX_CONCURRENT_CHILDREN env var.
max_spawn_depth: 1 # Delegation tree depth (floor 1, no ceiling). 1 = flat (default): parent spawns leaves that cannot delegate. 2 = orchestrator children can spawn leaf grandchildren. 3+ = deeper trees.
max_spawn_depth: 1 # Delegation tree depth cap (1-3, clamped). 1 = flat (default): parent spawns leaves that cannot delegate. 2 = orchestrator children can spawn leaf grandchildren. 3 = three levels.
orchestrator_enabled: true # Global kill switch. When false, role="orchestrator" is ignored and every child is forced to leaf regardless of max_spawn_depth.
```
@ -1705,7 +1705,7 @@ The delegation provider uses the same credential resolution as CLI/gateway start
**Precedence:** `delegation.base_url` in config → `delegation.provider` in config → parent provider (inherited). `delegation.model` in config → parent model (inherited). Setting just `model` without `provider` changes only the model name while keeping the parent's credentials (useful for switching models within the same provider like OpenRouter).
**Width and depth:** `max_concurrent_children` caps how many subagents run in parallel per batch (default `3`, floor of 1, no ceiling). Can also be set via the `DELEGATION_MAX_CONCURRENT_CHILDREN` env var. When the model submits a `tasks` array longer than the cap, `delegate_task` returns a tool error explaining the limit rather than silently truncating. `max_spawn_depth` controls the delegation tree depth (floor of 1, no upper ceiling). At the default `1`, delegation is flat: children cannot spawn grandchildren, and passing `role="orchestrator"` silently degrades to `leaf`. Raise to `2` so orchestrator children can spawn leaf grandchildren; `3` for three-level trees, and higher for deeper ones. The agent opts into orchestration per call via `role="orchestrator"`; `orchestrator_enabled: false` forces every child back to leaf regardless. Cost scales multiplicatively — at `max_spawn_depth: 3` with `max_concurrent_children: 3`, the tree can reach 3×3×3 = 27 concurrent leaf agents. See [Subagent Delegation → Depth Limit and Nested Orchestration](features/delegation.md#depth-limit-and-nested-orchestration) for usage patterns.
**Width and depth:** `max_concurrent_children` caps how many subagents run in parallel per batch (default `3`, floor of 1, no ceiling). Can also be set via the `DELEGATION_MAX_CONCURRENT_CHILDREN` env var. When the model submits a `tasks` array longer than the cap, `delegate_task` returns a tool error explaining the limit rather than silently truncating. `max_spawn_depth` controls the delegation tree depth (clamped to 1-3). At the default `1`, delegation is flat: children cannot spawn grandchildren, and passing `role="orchestrator"` silently degrades to `leaf`. Raise to `2` so orchestrator children can spawn leaf grandchildren; `3` for three-level trees. The agent opts into orchestration per call via `role="orchestrator"`; `orchestrator_enabled: false` forces every child back to leaf regardless. Cost scales multiplicatively — at `max_spawn_depth: 3` with `max_concurrent_children: 3`, the tree can reach 3×3×3 = 27 concurrent leaf agents. See [Subagent Delegation → Depth Limit and Nested Orchestration](features/delegation.md#depth-limit-and-nested-orchestration) for usage patterns.
## Clarify