Matt VollmerandNick Vigilante
75e0790cd7
Removes all references to "beta" from the Coder Agents documentation under `docs/ai-coder/agents/` and the corresponding `"state": ["beta"]` entries in `docs/manifest.json`. Also updates screenshots, video, and hero image, and regenerates the auto-generated feature-stages table. **Beta reference removal:** - `getting-started.md`: Removed "Coder Agents is in Beta" from the top note, "is in beta" from the Chats API note, and "during Beta" from the feedback section. Removed the version/stability note pinning 2.33.1. - `index.md`: Removed the "Product status" section that stated Coder Agents is in Beta. - `manifest.json`: Removed `"state": ["beta"]` from 17 entries for pages under `docs/ai-coder/agents/`. Preserved all `premium` and `early access` states. - `feature-stages.md`: Regenerated the auto-generated beta features table, which no longer lists Coder Agents. **Asset updates:** - `coder-agents-ui.mp4`: Updated demo video on the agents landing page. - `llm-providers.png`: Updated LLM provider support screenshot. - `models-list.png`: Updated models list screenshot. - `models-add-model.png`: Updated add model form screenshot. - `agents-hero-image.png`: Updated hero image on the `docs/ai-coder` landing page. Two references in `models.md` (`v1beta` in the Google Gemini API URL and `anthropic-beta` in the Anthropic header name) were left unchanged as they are provider API identifiers, not product status labels. PR generated with Coder Agents --------- Co-authored-by: Nick Vigilante <nickvigilante@users.noreply.github.com>
2.1 KiB
Advisor
Note
This feature is experimental. Pin a release before broad rollout and review the release notes before upgrading.
Enable the experiment
coder server --experiments=chat-advisor
Or set the environment variable:
CODER_EXPERIMENTS=chat-advisor
What it does
Lets a root agent pause its current turn and request strategic guidance from a separate, single-step model call. The advisor sees recent conversation context, runs without any tools, and returns concise advice for the root agent rather than the end user. While active, it is the only tool the root agent can call for that turn.
Useful for planning ambiguity, architectural tradeoffs, debugging strategy after repeated failures, or risk reduction before a destructive operation.
Configuration
Once the experiment is enabled, configure the advisor under AI Settings > Coder Agents > Advisor.
| Field | Default | Notes |
|---|---|---|
| Max uses per turn | 0 (unlimited) |
Caps how many times the root agent can call the advisor in a single chat turn. Must be a non-negative integer. |
| Max output tokens | 0 (server default) |
Caps the advisor model's response length. 0 uses the server default of 16,384 tokens. Must be a non-negative integer. |
| Advisor model | Use chat model | Optional dedicated chat model config for the advisor. When unset, the advisor reuses the root agent's model. |
| Reasoning effort | Model default | Overrides the selected advisor model's reasoning effort. Available only when the model supports selectable effort. |
The advisor is not available in plan mode or to subagents. Failed advisor invocations refund the per-turn budget.
The same configuration is available at:
GET /api/v2/chats/config/advisorPUT /api/v2/chats/config/advisor