Files
Thomas Kosiewski 06bad73df4 feat: add admin-configurable advisor API, SDK, and queries (#24621)
## Summary

Add the **admin-configurable advisor configuration**: database-backed storage, SDK types, and the experimental HTTP handlers that back the admin settings UI (later PRs). Follows the same "site-configs" pattern as Virtual Desktop.

## Motivation

The advisor needs runtime-tunable knobs (enable/disable, per-run cap, max output tokens, reasoning effort, optional model override) without a service restart or redeploy. Using the existing `site_configs` K/V table keeps this pattern consistent with other admin features and avoids a bespoke schema.

## Changes

### Database (`coderd/database/queries/siteconfig.sql`)
- `GetChatAdvisorConfig` returns the stored JSON blob (default `'{}'`) under key `agents_advisor_config`.
- `UpsertChatAdvisorConfig` uses the standard `INSERT ... ON CONFLICT` pattern.
- Regenerated via `make gen` (queries.sql.go + mocks).

### SDK (`codersdk/chats.go`)
- `AdvisorConfig` type with `Enabled`, `MaxUsesPerRun`, `MaxOutputTokens`, `ReasoningEffort` (`""` / `low` / `medium` / `high`), `ModelConfigID uuid.UUID`.
- Client methods: `ChatAdvisorConfig(ctx)` / `UpdateChatAdvisorConfig(ctx, cfg)`.

### API (`coderd/exp_chats.go`)
- `GET /api/experimental/chats/config/advisor`: reads current config; relies on `ActorFromContext` validation.
- `PUT /api/experimental/chats/config/advisor`: requires `policy.ActionUpdate` on `rbac.ResourceDeploymentConfig`.
- Handlers unmarshal `{}` to a typed zero value and re-marshal on upsert for schema stability.
- Tests in `exp_chats_test.go` cover empty defaults, round-trip update, unauthorized update, and invalid body.

## Stack context

This is **PR 3 of 6** in the advisor feature stack. Consumed by:
- PR 4 (`feat/advisor-04-chatd-runtime`), which reads this config on every `runChat`.
- PR 6 (`feat/advisor-06-admin-settings-ui`), which renders the admin form.

## Scope / non-goals

- No `chatd` read path (lands in PR 4).
- No UI (lands in PR 6).
- `agents_advisor_config` remains a single-row JSON blob; we intentionally do not shard per-org/per-template yet.

## Validation

- `make gen`
- `go test ./coderd/database/... -run TestChatAdvisor`
- `go test ./coderd/... -run TestChatAdvisorConfig`
- `make lint`

---

<details>
<summary>📋 Implementation Plan (shared across the advisor stack)</summary>

# Plan: Add a Mux-style advisor tool to coder agents/chatd

## Outcome

Add a first-class `advisor` tool to agent chats in `coderd/x/chatd` that feels native to Coder:

- it is a built-in server-side tool, not an MCP/dynamic-tool workaround;
- it performs a nested **tool-less** model call for strategic advice;
- it is exposed only when eligible, and the prompt mentions it only when it is actually available;
- it is treated as a **planning-only** tool so it does not run alongside action tools in the same batch;
- it tracks usage/cost separately enough for operators to reason about it;
- it has a minimally polished UI in the Agents page;
- and it ships with explicit dogfooding evidence, including screenshots and repro videos.

## Design decisions to lock before coding

1. **Primary architecture:** native built-in tool in `chattool/`, backed by a small `chatadvisor` package.
2. **Nested model execution:** reuse chatd's existing model/provider stack for a one-step, tool-less advisor call rather than inventing a new provider pathway.
3. **Execution policy:** treat `advisor` as an exclusive/planning-only tool; mixed batches must return structured policy errors and force the model to retry cleanly.
4. **Availability:** initial rollout is for root agent chats only; disable for child/sub-agent chats until recursion/cost policy is proven.
5. **Prompt sync:** use one eligibility boolean to drive both tool registration and advisor guidance injection.
6. **Persistence/cost split:** MVP should keep advisor usage visible in result metadata and server metrics; only add DB schema if product/billing explicitly needs queryable advisor-specific cost.
7. **UI scope:** generic tool rendering is an acceptable temporary milestone during backend bring-up, but the release candidate should include a dedicated lightweight advisor renderer.

## Delivery model

The work should be executed as coordinated workstreams with one integration owner and parallel contributors for low-conflict areas. The integration owner should own `coderd/x/chatd/chatd.go` because prompt assembly, tool registration, and model resolution all converge there.

## Detailed workstreams

### Repo evidence used for this plan

<details>
<summary>Mux reference and current chatd seams</summary>

**Mux reference implementation**

- `src/node/services/tools/advisor.ts` — native advisor tool implementation.
- `src/common/constants/advisor.ts` — advisor prompt/constants and truncation policy.
- `src/common/utils/tools/tools.ts` — conditional tool registration.
- `src/node/services/streamContextBuilder.ts` — injects advisor guidance only when the tool is available.

**Current chatd seams**

- `coderd/x/chatd/chatd.go`
  - `processChat()` — tool assembly, prompt assembly, and chatloop invocation.
  - `resolveChatModel()` — current model/provider/key resolution seam.
  - `type Config struct` — server-level chatd configuration surface.
- `coderd/x/chatd/chatloop/chatloop.go`
  - `Run()` — main streaming/model loop.
  - `executeTools()` — built-in tool execution/batching seam.
- `coderd/x/chatd/chattool/` — built-in tool implementations.
- `site/src/pages/AgentsPage/components/ChatElements/tools/Tool.tsx` — tool renderer dispatch.
- `site/src/pages/AgentsPage/components/ChatConversation/messageParsing.ts` and `ConversationTimeline.tsx` — tool/result merge and rendering flow.

</details>

### Workstream map and ownership

| Workstream | Primary owner | Main files | Can run in parallel? | Done when |
|---|---|---|---|---|
| 0. Integration + gating | Integration lead | `coderd/x/chatd/chatd.go` | No; central merge lane | Tool registration, prompt sync, and model selection are wired together |
| 1. Advisor runtime + tool | Backend agent | new `coderd/x/chatd/chatadvisor/`, new `coderd/x/chatd/chattool/advisor.go` | Yes | Tool can perform a tool-less advisor call in memory and return structured results |
| 2. Planning-only execution policy | Chatloop agent | `coderd/x/chatd/chatloop/chatloop.go`, related tests | Yes | Mixed `advisor` + action-tool batches are rejected cleanly and deterministically |
| 3. Metrics/usage/config | Backend/telemetry agent | `chatd.go`, `chatloop/metrics.go`, optional config plumbing | Partially; coordinate with integration lead | Advisor usage is separately visible in metadata/metrics and limits are enforced |
| 4. Frontend rendering | Frontend agent | `site/.../tools/Tool.tsx`, new `AdvisorTool.tsx`, stories | Yes after result schema stabilizes | Advisor renders as a readable card and story tests pass |
| 5. Dogfood + QA evidence | QA agent | dev server, Storybook, dogfood output | After backend + UI are usable | Repro videos, screenshots, and a concise QA report exist |

### Parallelization rules

- **Do not split `coderd/x/chatd/chatd.go` across multiple execution agents without an integration lead.** That file owns prompt building, tool registration, model resolution, and cost persistence.
- Workstreams 1 and 2 can be developed in parallel and then stacked onto the integration branch.
- Workstream 4 should begin once the backend result schema is agreed on, even if the backend is still behind a feature flag.
- Any agent that needs to re-check Mux behavior should clone `coder/mux` into a temporary directory (for example, `$(mktemp -d)/mux`) and inspect it read-only; do not vendor or copy code from Mux directly.

## Phase 0 — Preflight and guardrails

### Goals

- Align the team on the smallest shippable architecture.
- Prevent scope creep into MCP/dynamic-tool/sub-agent variants.
- Decide upfront what is MVP vs. follow-up.

### Tasks

1. **Confirm the MVP boundary.**
   - Ship a built-in advisor tool first.
   - Do **not** make MCP, dynamic tools, or sub-agents the primary implementation.
   - Do **not** add transient streaming phases in the first backend PR unless they fall out almost for free.

2. **Confirm local workflow hygiene before coding.**
   - Ensure the repo is using the project git hooks from `scripts/githooks`.
   - Do not bypass hooks with `--no-verify`.
   - Use `./scripts/develop.sh` for the full dev server rather than manual build/run commands.

3. **Lock the model-selection policy.**
   - **Recommended MVP:** advisor uses the same resolved provider/model/cost config as the current chat, with advisor-specific max-output and usage caps.
   - **Follow-up only if required:** add a separate `AdvisorModelConfigID`-style override that resolves through the existing `configCache`/model-config path. Do not invent a new free-form `provider:model` parser if chatd already stores provider/model separately.

4. **Lock the persistence policy.**
   - **Recommended MVP:** no DB migration. Persist advisor-visible metadata in the tool result and record separate metrics in memory/Prometheus.
   - **Only if product/billing explicitly asks for queryable advisor cost:** add a later DB migration or usage table, following the normal `queries/*.sql` + `make gen` workflow.

5. **Create an execution ADR note in the work item or tracking doc.**
   - Capture: built-in tool, tool-less nested call, root-chat-only rollout, exclusive execution policy, MVP no-DB-migration default.

### Quality gate

- Everyone on the team can state the same answers to these questions:
  - Is advisor a built-in tool? **Yes.**
  - Can advisor run with action tools in the same batch? **No.**
  - Does advisor get tools of its own? **No.**
  - Is a DB migration required for MVP? **No, unless billing insists.**

## Phase 1 — Build the advisor runtime and tool wrapper

### Goals

Create the core advisor implementation in a way that is easy to test and keeps `chattool/` thin.

### Files to add

- `coderd/x/chatd/chatadvisor/types.go`
- `coderd/x/chatd/chatadvisor/guidance.go`
- `coderd/x/chatd/chatadvisor/handoff.go`
- `coderd/x/chatd/chatadvisor/runtime.go`
- `coderd/x/chatd/chatadvisor/runner.go`
- `coderd/x/chatd/chattool/advisor.go`

### Responsibilities by file

1. **`types.go`**
   - Define the input/result schema used by the tool and UI.
   - Keep the result shape close to Mux so the UI and model both have predictable cases.
   - Recommended result variants:
     - `advice`
     - `limit_reached`
     - `error`

   Recommended shape:

   ```go
   type AdvisorArgs struct {
       Question string `json:"question"`
   }

   type AdvisorResult struct {
       Type          string              `json:"type"`
       Advice        string              `json:"advice,omitempty"`
       Error         string              `json:"error,omitempty"`
       AdvisorModel  string              `json:"advisor_model,omitempty"`
       RemainingUses int                 `json:"remaining_uses,omitempty"`
       Usage         *AdvisorUsageResult `json:"usage,omitempty"`
   }
   ```

2. **`guidance.go`**
   - Hold two strings:
     - the nested advisor system prompt;
     - the parent-agent guidance block to inject into the outer system prompt.
   - The nested advisor prompt must say, in plain language:
     - you are advising the parent agent;
     - you do not address the end user directly;
     - you do not claim actions happened;
     - you return concise strategic guidance and tradeoffs.

3. **`runtime.go`**
   - Define the per-run runtime state.
   - Recommended fields:
     - resolved model + model config;
     - provider keys/options reused from the outer chat;
     - `MaxUsesPerRun`;
     - `MaxOutputTokens`;
     - atomic/current call counter;
     - callback(s) to obtain the current prompt snapshot and current-step snapshot;
     - optional metrics/usage hook.
   - Add fail-fast validation for impossible config: nil model, non-positive limits, empty prompt builders, etc.

4. **`handoff.go`**
   - Build the advisor handoff message from:
     - the explicit question;
     - the exact prompt/messages the parent model just used;
     - the current step's text/reasoning snapshot, if available;
     - the most recent relevant tool outputs, if they are already in the prompt snapshot.
   - **Important:** use the already-prepared outer prompt tail, not a fresh DB reload. That keeps the advisor aligned with compaction and the exact context the outer model saw.
   - Apply hard truncation budgets with recent-context bias.

5. **`runner.go`**
   - Execute the nested advisor call.
   - **Recommended implementation:** call `chatloop.Run()` in an in-memory, one-step mode:
     - `Tools: nil`
     - `ProviderTools: nil`
     - `MaxSteps: 1`
     - `PersistStep`: capture the assistant output in memory instead of writing DB rows
   - Reuse the existing provider/model/cost path instead of building a second provider runner.
   - Assert that no tool definitions are passed to the nested call.

6. **`chattool/advisor.go`**
   - Keep this file thin and consistent with other built-ins.
   - Responsibilities:
     - decode `AdvisorArgs`;
     - validate `Question` is non-empty and bounded;
     - call the `chatadvisor` runner;
     - return a structured tool response.

### Defensive programming requirements

- Assert `Question` is non-empty after trimming.
- Assert runtime limits are positive.
- Assert the nested advisor call runs with zero tools/provider tools.
- Assert `AdvisorResult.Type` is one of the known variants before returning.
- Assert remaining uses never goes negative.

### Acceptance criteria

- A unit test can call the advisor tool with a fake model and receive a stable `advice` result.
- The nested advisor call is impossible to run with tools accidentally attached.
- The core logic lives in `chatadvisor/`, not embedded inside `chatd.go`.

## Phase 2 — Wire advisor into chatd and keep prompt/tool availability in sync

### Goals

Register the tool in the right place, expose it only when eligible, and inject system guidance only when the tool is present.

### Files to modify

- `coderd/x/chatd/chatd.go`
- optionally a small helper file if `chatd.go` becomes too crowded

### Tasks

1. **Compute one eligibility boolean in `processChat()`.**
   Recommended inputs:
   - server-level advisor enabled flag;
   - root chat only (`chat.ParentChatID == uuid.Nil` or equivalent existing root/child check);
   - a usable resolved model/provider exists;
   - optional experiment/workspace/org gate if product wants staged rollout.

2. **Create the runtime once per outer chat run.**
   - Use the model/config/keys resolved by `resolveChatModel()`.
   - Reuse provider options from the current chat's `ChatModelCallConfig`.
   - Set `MaxUsesPerRun` and `MaxOutputTokens` from advisor config defaults.

3. **Register the tool in the built-in tool block.**
   - Insert after the skill tools and before MCP tools in `processChat()`.
   - Record `builtinToolNames["advisor"] = true` so metrics stay bounded.

4. **Inject advisor guidance into the outer system prompt using the same boolean.**
   - Use `chatprompt.InsertSystem()` in the same prompt assembly path that already injects user/system instructions.
   - Place the block near the existing instruction insertion, before plan-path/skill context blocks.
   - Wrap the guidance in an explicit tag like `<advisor-guidance>` so it is easy to spot in tests and future refactors.

5. **Keep advisor out of child chats for the first release.**
   - That avoids recursion/cost blowups with `spawn_agent` / `wait_agent` flows.
   - Document this explicitly in the rollout notes and tests.

### Acceptance criteria

- If advisor is disabled, neither the tool nor the prompt guidance appears.
- If advisor is enabled, both the tool and the prompt guidance appear.
- Root chats can use advisor; child chats cannot.
- Built-in tool names include `advisor` so metrics do not collapse it into the generic `mcp` label.

## Phase 3 — Enforce planning-only execution policy in `chatloop`

### Goals

Prevent the model from calling `advisor` and action tools in the same execution batch.

### Files to modify

- `coderd/x/chatd/chatloop/chatloop.go`
- related chatloop tests

### Recommended implementation

Keep the MVP small; do **not** build a general policy engine yet.

1. Add a minimal field to `chatloop.RunOptions`, for example:

   ```go
   ExclusiveToolName *string
   ```

2. In `Run()` / `executeTools()`, detect the case where the exclusive tool appears in the same local-tool batch as any other locally executed tool.

3. When that happens, synthesize structured tool-result errors for the affected calls instead of executing anything in the batch.
   - `advisor` should receive a clear error like: _advisor must be called by itself before action tools_.
   - The sibling action tools should receive a paired policy error like: _this tool was skipped because advisor must run alone_.

4. Let the outer model see those tool errors and retry cleanly.
   - This is simpler and safer than partial execution or hidden deferral.
   - It preserves deterministic transcript history for debugging.

5. Pass the just-finished step snapshot into the tool execution context.
   - The advisor runtime should be able to see the current step's text/reasoning content, because that is often the best hint about what the outer model is trying to decide.

### Why this is the right fit

- It matches the intended semantics: advisor is consulted **before** taking action.
- It avoids subtle race conditions caused by concurrent built-in tool execution.
- It keeps the behavior easy to test with fake models.

### Acceptance criteria

- A model-emitted batch containing only `advisor` succeeds.
- A model-emitted batch containing `advisor` plus any other locally executed tool returns deterministic policy errors and executes nothing.
- Non-advisor tool execution stays unchanged for normal chats.

## Phase 4 — Usage limits, metrics, and configuration

### Goals

Make advisor safe to operate without over-designing billing/storage in the first release.

### Files to modify

- `coderd/x/chatd/chatd.go`
- `coderd/x/chatd/chatloop/metrics.go` as needed
- `coderd/x/chatd/chatd.go` `Config` struct and constructor path
- optional follow-up config/db files only if a separate advisor model or persistent billing is required

### Tasks

1. **Add explicit server config knobs for MVP.**
   Recommended fields on `chatd.Config` or a nested advisor config struct:
   - `AdvisorEnabled bool`
   - `AdvisorMaxUsesPerRun int`
   - `AdvisorMaxOutputTokens int64`

2. **Track usage per outer run.**
   - Reset the counter for each `processChat()` invocation.
   - Return `remaining_uses` in the tool result.
   - Return `limit_reached` when the cap is exhausted.

3. **Expose advisor usage metadata in the tool result.**
   - Include model name and token/cost summary if available.
   - Use the same `callConfig.Cost` calculation path as the outer chat for MVP if advisor reuses the same model.

4. **Record server-side metrics.**
   - Count advisor invocations, failures, and latency.
   - Ensure they show up under the built-in tool label `advisor`.

5. **Optional decision gate: separate advisor model.**
   - If product insists on a stronger/different advisor model, add a follow-up config hook that resolves another existing chat model config through the same `configCache` path.
   - Keep that out of the first landing PR unless it is required for acceptance.

6. **Optional decision gate: queryable advisor cost.**
   - If this becomes required, spin a follow-up DB task:
     - update `coderd/database/queries/*.sql`;
     - add migration files;
     - run `make gen`;
     - update audit mappings if a new auditable type/field is introduced.

### Acceptance criteria

- Advisor calls are capped per outer run.
- Limit exhaustion is user-visible in the tool result.
- Metrics distinguish advisor calls from other built-in tools.
- MVP does not require a schema migration unless explicitly approved.

## Phase 5 — Frontend rendering and Storybook coverage

### Goals

Make advisor feel intentional in the Agents UI without blocking the backend on fancy streaming UI.

### Files to modify

- `site/src/pages/AgentsPage/components/ChatElements/tools/Tool.tsx`
- new `site/src/pages/AgentsPage/components/ChatElements/tools/AdvisorTool.tsx`
- Storybook story file(s) in the same tools directory

### Delivery strategy

1. **Intermediate milestone during backend bring-up:** rely on the existing generic tool renderer if needed.
   - This is acceptable only as a short-lived integration checkpoint.

2. **Release milestone:** add a dedicated lightweight `AdvisorTool` renderer.
   - Reuse existing primitives:
     - `ToolCollapsible`
     - `ToolIcon`
     - `Response` for markdown/prose rendering
     - `ScrollArea` if the advice can be long
   - Keep styling light and consistent with the Agents page.
   - Do not add unnecessary React memoization in `site/src/pages/AgentsPage/`; that area is already React-Compiler aware.

3. **Render the structured result states cleanly.**
   - `advice` — readable prose/markdown with optional metadata footer.
   - `limit_reached` — warning-style message.
   - `error` — error state with visible fallback text.
   - `running` — existing tool loading state/spinner is enough for MVP.

4. **Add Storybook coverage instead of ad-hoc component tests.**
   Recommended stories:
   - successful advice;
   - running/loading;
   - limit reached;
   - error.

5. **Keep the UI contract narrow.**
   - Prefer one text field like `advice` plus small metadata rather than a deeply nested schema.
   - That keeps the UI resilient to prompt iteration.

### Acceptance criteria

- The advisor tool card renders readable content rather than raw quoted JSON in the final release branch.
- Running, limit, and error states are visibly distinct.
- Storybook stories and play assertions cover the new states.
- Existing tool rendering flows remain unchanged.

## Phase 6 — Automated tests and validation gates

### Backend tests to add

1. **Advisor runtime/tool tests**
   - question validation;
   - tool-less nested execution assertion;
   - success result shaping;
   - limit-reached result shaping;
   - error result shaping.

2. **Prompt/gating tests in chatd**
   - advisor disabled ⇒ no tool, no guidance;
   - advisor enabled/root chat ⇒ tool + guidance;
   - child chat ⇒ advisor absent.

3. **Chatloop policy tests**
   - advisor alone runs;
   - advisor + action tool mixed batch returns deterministic policy errors;
   - non-advisor tools still execute normally.

4. **Usage/metrics tests**
   - per-run cap resets correctly;
   - builtin tool labeling includes `advisor`;
   - returned metadata includes model/usage summary when available.

### Frontend tests to add

- Storybook `play()` assertions for the advisor renderer states.
- Verify expand/collapse behavior and visible fallback text.
- Verify the message timeline still renders adjacent tools correctly.

### Recommended command sequence

Run these as the implementation matures, not only at the end:

1. Backend-focused gate after phases 1–4:
   - `make test RUN=TestAdvisor`
   - `make test RUN=TestChatloopAdvisor`
   - `make lint`

2. Frontend-focused gate after phase 5:
   - `pnpm test:storybook src/pages/AgentsPage/components/ChatElements/tools/AdvisorTool.stories.tsx`
   - `pnpm lint`
   - `pnpm format`

3. Final repo gate before handoff:
   - `make pre-commit`
   - run any additional targeted `make test RUN=...` selections covering touched chatd paths

> Use the exact new test names the implementing agents create; the names above are recommended anchors, not existing tests.

## Dogfooding plan

### Principle

Dogfood the change as a real agent feature, not just a unit-tested backend. Per the dogfood and `agent-browser` skills, the reviewer should get **watchable repro videos** plus screenshots that make the behavior obvious without reading logs.

### Required setup

1. Start the full dev environment with:
   - `./scripts/develop.sh`
2. If the frontend renderer changes, also start Storybook from `site/` with:
   - `pnpm storybook --no-open`
3. Use `agent-browser` directly — **never `npx agent-browser`**.
4. Use named browser sessions and an output folder such as:
   - `./dogfood-output/advisor/`
   - with subfolders `screenshots/` and `videos/`

### Evidence protocol

For every interactive scenario below:

1. Start video recording **before** the action.
2. Capture step-by-step screenshots at human pace.
3. Capture one annotated screenshot of the final state.
4. Stop the recording.
5. Note the exact pass/fail observation in the QA report.

For static UI states (for example Storybook error/limit cards), an annotated screenshot is sufficient; video is optional but still encouraged by this project’s review preference.

### Dogfood scenarios

#### Scenario A — Happy path in the real Agents UI

**Goal:** prove that a root agent chat can invoke advisor and produce a readable recommendation before taking further action.

Steps:

1. Open the Agents page with an advisor-enabled root chat.
2. Start a repro video.
3. Send a prompt that should reasonably trigger strategic planning, such as an architecture or multi-tradeoff question.
4. Capture screenshots of:
   - the prompt before send;
   - the running advisor state;
   - the completed advisor card and the assistant’s follow-up response.
5. Stop recording.

Pass criteria:

- advisor appears in the timeline;
- the rendered result is readable;
- the assistant can continue after consuming the advisor output.

#### Scenario B — Advisor unavailable path

**Goal:** prove the feature is truly gated.

Suggested variants (at least one is required, both are better):

- feature flag/config off;
- child/sub-agent chat.

Evidence:

- annotated screenshot of the chat/tool state showing advisor is absent;
- short video if toggling the gate live is part of the repro.

Pass criteria:

- no advisor tool is available;
- no advisor-specific prompt behavior leaks through.

#### Scenario C — UI states in Storybook

**Goal:** prove the renderer handles non-happy states cleanly.

Required story states:

- success/advice;
- running;
- limit reached;
- error.

Evidence:

- one screenshot per state;
- at least one short video showing collapse/expand behavior.

Pass criteria:

- success renders readable advice;
- limit/error have visible fallback text;
- the component behaves like the other tool cards.

#### Scenario D — Regression sweep of nearby tools

**Goal:** ensure advisor does not break the surrounding chat timeline.

Check at minimum:

- another existing built-in tool still renders correctly near advisor;
- sub-agent/tool cards still expand/collapse normally;
- no obvious console errors appear in the Agents page during the advisor flow.

Evidence:

- screenshots of adjacent tool cards;
- console/error capture if anything suspicious appears.

### `agent-browser` usage notes for the QA agent

- Prefer `agent-browser batch` for 2+ sequential commands when no intermediate parsing is needed.
- Use `snapshot -i` to discover interactive refs.
- Re-snapshot after navigation or major DOM changes.
- Avoid `wait --load networkidle` unless the page is known to go idle; prefer explicit element/text waits or short fixed waits.
- Record videos at human pace and include pauses that a reviewer can follow.

## Rollout plan

### Initial rollout

- Gate behind a server-side advisor-enabled flag.
- Enable only for selected internal/root agent chats first.
- Watch metrics for:
  - invocation count;
  - failure rate;
  - latency;
  - obvious retry loops.

### Expansion conditions

Expand beyond the initial rollout only after the following are true:

- mixed-batch policy behavior is stable;
- cost impact is understood;
- frontend UX is readable in production-like dogfood;
- no recursion surprises have appeared with sub-agent flows.

### Explicit non-goals for the first release

- advisor inside child/sub-agent chats;
- provider-agnostic streaming phase UI;
- MCP-based external advisor implementation;
- mandatory DB-backed advisor cost reporting.

## Final acceptance checklist

- [ ] `advisor` is a built-in chatd tool, not an MCP/dynamic-tool substitute.
- [ ] The nested advisor call is tool-less and bounded to one in-memory step.
- [ ] One eligibility boolean controls both tool registration and prompt guidance injection.
- [ ] Root chats can use advisor; child chats cannot in the initial rollout.
- [ ] Mixed advisor/action batches produce deterministic policy errors instead of partial execution.
- [ ] Per-run usage caps and limit-reached behavior work.
- [ ] Advisor usage is visible in metadata/metrics without forcing a DB migration for MVP.
- [ ] The Agents UI has a readable advisor card and Storybook coverage.
- [ ] Dogfooding produced screenshots and repro videos for the required scenarios.
- [ ] Validation commands (`make lint`, targeted `make test`, Storybook tests, `make pre-commit`) passed before handoff.

## Suggested PR split

1. **PR 1 — Backend foundation**
   - `chatadvisor/` package
   - `chattool/advisor.go`
   - `chatloop` exclusive policy
   - chatd gating/prompt sync
   - backend tests

2. **PR 2 — Frontend + QA**
   - advisor renderer
   - stories/play assertions
   - dogfood artifacts and QA notes

3. **PR 3 — Optional follow-ups only if demanded by stakeholders**
   - separate advisor model override
   - persistent advisor billing/queryability
   - transient phase-stream UX


</details>

---
_Generated with [`mux`](https://github.com/coder/mux) • Model: `anthropic:claude-opus-4-7` • Thinking: `max`_
2026-04-30 14:53:08 +02:00

526 lines
13 KiB
Go

package main
import (
"bytes"
"fmt"
"go/format"
"go/token"
"os"
"path/filepath"
"reflect"
"runtime"
"strings"
"github.com/dave/dst"
"github.com/dave/dst/decorator"
"github.com/dave/dst/decorator/resolver/goast"
"github.com/dave/dst/decorator/resolver/guess"
"golang.org/x/tools/imports"
"golang.org/x/xerrors"
"github.com/coder/coder/v2/scripts/atomicwrite"
)
var (
funcs []querierFunction
funcByName map[string]struct{}
)
func init() {
var err error
funcs, err = readQuerierFunctions()
if err != nil {
panic(err)
}
funcByName = map[string]struct{}{}
for _, f := range funcs {
funcByName[f.Name] = struct{}{}
}
}
func main() {
err := run()
if err != nil {
_, _ = fmt.Fprintf(os.Stderr, "error: %s\n", err)
os.Exit(1)
}
}
func run() error {
localPath, err := localFilePath()
if err != nil {
return err
}
databasePath := filepath.Join(localPath, "..", "..", "..", "coderd", "database")
err = orderAndStubDatabaseFunctions(filepath.Join(databasePath, "dbmetrics", "querymetrics.go"), "m", "queryMetricsStore", func(params stubParams) string {
return fmt.Sprintf(`
start := time.Now()
%s := m.s.%s(%s)
m.queryLatencies.WithLabelValues("%s").Observe(time.Since(start).Seconds())
m.queryCounts.WithLabelValues(httpmw.ExtractHTTPRoute(ctx), httpmw.ExtractHTTPMethod(ctx), "%s").Inc()
return %s
`, params.Returns, params.FuncName, params.Parameters, params.FuncName, params.FuncName, params.Returns)
})
if err != nil {
return xerrors.Errorf("stub dbmetrics: %w", err)
}
err = orderAndStubDatabaseFunctions(filepath.Join(databasePath, "dbauthz", "dbauthz.go"), "q", "querier", func(_ stubParams) string {
return `panic("not implemented")`
})
if err != nil {
return xerrors.Errorf("stub dbauthz: %w", err)
}
err = generateUniqueConstraints()
if err != nil {
return xerrors.Errorf("generate unique constraints: %w", err)
}
err = generateForeignKeyConstraints()
if err != nil {
return xerrors.Errorf("generate foreign key constraints: %w", err)
}
err = generateCheckConstraints()
if err != nil {
return xerrors.Errorf("generate check constraints: %w", err)
}
return nil
}
type stubParams struct {
FuncName string
Parameters string
Returns string
}
// orderAndStubDatabaseFunctions orders the functions in the file and stubs them.
// This is useful for when we want to add a new function to the database and
// we want to make sure that it's ordered correctly.
//
// querierFuncs is a list of functions that are in the database.
// file is the path to the file that contains all the functions.
// structName is the name of the struct that contains the functions.
// stub is a string that will be used to stub the functions.
func orderAndStubDatabaseFunctions(filePath, receiver, structName string, stub func(params stubParams) string) error {
declByName := map[string]*dst.FuncDecl{}
packageName := filepath.Base(filepath.Dir(filePath))
externalMethods, err := loadExternalReceiverMethods(
filepath.Dir(filePath),
filepath.Base(filePath),
structName,
)
if err != nil {
return xerrors.Errorf("load external receiver methods: %w", err)
}
contents, err := os.ReadFile(filePath)
if err != nil {
return xerrors.Errorf("read file: %w", err)
}
// Required to preserve imports!
f, err := decorator.NewDecoratorWithImports(token.NewFileSet(), packageName, goast.New()).Parse(contents)
if err != nil {
return xerrors.Errorf("parse file: %w", err)
}
pointer := false
for i := 0; i < len(f.Decls); i++ {
funcDecl, ok := f.Decls[i].(*dst.FuncDecl)
if !ok || funcDecl.Recv == nil || len(funcDecl.Recv.List) == 0 {
continue
}
var ident *dst.Ident
switch t := funcDecl.Recv.List[0].Type.(type) {
case *dst.Ident:
ident = t
case *dst.StarExpr:
ident, ok = t.X.(*dst.Ident)
if !ok {
continue
}
pointer = true
}
if ident == nil || ident.Name != structName {
continue
}
if _, ok := funcByName[funcDecl.Name.Name]; !ok {
continue
}
declByName[funcDecl.Name.Name] = funcDecl
f.Decls = append(f.Decls[:i], f.Decls[i+1:]...)
i--
}
for _, fn := range funcs {
if _, ok := externalMethods[fn.Name]; ok {
continue
}
var bodyStmts []dst.Stmt
decl, ok := declByName[fn.Name]
if !ok {
typeName := structName
if pointer {
typeName = "*" + typeName
}
params := make([]string, 0)
if fn.Func.Params != nil {
for _, p := range fn.Func.Params.List {
for _, name := range p.Names {
params = append(params, name.Name)
}
}
}
returns := make([]string, 0)
if fn.Func.Results != nil {
for i := range fn.Func.Results.List {
returns = append(returns, fmt.Sprintf("r%d", i))
}
}
funcDecl, err := compileFuncDecl(stub(stubParams{
FuncName: fn.Name,
Parameters: strings.Join(params, ","),
Returns: strings.Join(returns, ","),
}))
if err != nil {
return xerrors.Errorf("compile func decl: %w", err)
}
// Not implemented!
decl = &dst.FuncDecl{
Name: dst.NewIdent(fn.Name),
Type: &dst.FuncType{
Func: true,
TypeParams: fn.Func.TypeParams,
Params: fn.Func.Params,
Results: fn.Func.Results,
Decs: fn.Func.Decs,
},
Recv: &dst.FieldList{
List: []*dst.Field{{
Names: []*dst.Ident{dst.NewIdent(receiver)},
Type: dst.NewIdent(typeName),
}},
},
Decs: dst.FuncDeclDecorations{
NodeDecs: dst.NodeDecs{
Before: dst.EmptyLine,
After: dst.EmptyLine,
},
},
Body: &dst.BlockStmt{
List: append(bodyStmts, funcDecl.Body.List...),
},
}
}
if ok {
for i, pm := range fn.Func.Params.List {
if len(decl.Type.Params.List) < i+1 {
decl.Type.Params.List = append(decl.Type.Params.List, pm)
}
if !reflect.DeepEqual(decl.Type.Params.List[i].Type, pm.Type) {
decl.Type.Params.List[i].Type = pm.Type
}
}
for i, res := range fn.Func.Results.List {
if len(decl.Type.Results.List) < i+1 {
decl.Type.Results.List = append(decl.Type.Results.List, res)
}
if !reflect.DeepEqual(decl.Type.Results.List[i].Type, res.Type) {
decl.Type.Results.List[i].Type = res.Type
}
}
}
f.Decls = append(f.Decls, decl)
}
// Required to preserve imports!
restorer := decorator.NewRestorerWithImports(packageName, guess.New())
restored, err := restorer.RestoreFile(f)
if err != nil {
return xerrors.Errorf("restore package: %w", err)
}
var buf bytes.Buffer
err = format.Node(&buf, restorer.Fset, restored)
if err != nil {
return xerrors.Errorf("format package: %w", err)
}
data, err := imports.Process(filePath, buf.Bytes(), &imports.Options{
Comments: true,
})
if err != nil {
return xerrors.Errorf("process imports: %w", err)
}
return atomicwrite.File(filePath, data)
}
// compileFuncDecl extracts the function declaration from the given code.
func compileFuncDecl(code string) (*dst.FuncDecl, error) {
f, err := decorator.Parse(fmt.Sprintf(`package stub
func stub() {
%s
}`, strings.TrimSpace(code)))
if err != nil {
return nil, err
}
if len(f.Decls) != 1 {
return nil, xerrors.Errorf("expected 1 decl, got %d", len(f.Decls))
}
decl, ok := f.Decls[0].(*dst.FuncDecl)
if !ok {
return nil, xerrors.Errorf("expected func decl, got %T", f.Decls[0])
}
return decl, nil
}
type querierFunction struct {
// Name is the name of the function. Like "GetUserByID"
Name string
// Func is the AST representation of a function.
Func *dst.FuncType
}
// readQuerierFunctions reads the functions from coderd/database/querier.go
func readQuerierFunctions() ([]querierFunction, error) {
f, err := parseDBFile("querier.go")
if err != nil {
return nil, xerrors.Errorf("parse querier.go: %w", err)
}
funcs, err := loadInterfaceFuncs(f, "sqlcQuerier")
if err != nil {
return nil, xerrors.Errorf("load interface %s funcs: %w", "sqlcQuerier", err)
}
customFile, err := parseDBFile("modelqueries.go")
if err != nil {
return nil, xerrors.Errorf("parse modelqueriers.go: %w", err)
}
// Custom funcs should be appended after the regular functions
customFuncs, err := loadInterfaceFuncs(customFile, "customQuerier")
if err != nil {
return nil, xerrors.Errorf("load interface %s funcs: %w", "customQuerier", err)
}
return append(funcs, customFuncs...), nil
}
func parseDBFile(filename string) (*dst.File, error) {
localPath, err := localFilePath()
if err != nil {
return nil, err
}
querierPath := filepath.Join(localPath, "..", "..", "..", "coderd", "database", filename)
querierData, err := os.ReadFile(querierPath)
if err != nil {
return nil, xerrors.Errorf("read %s: %w", filename, err)
}
f, err := decorator.Parse(querierData)
return f, err
}
func loadExternalReceiverMethods(
dirPath string,
excludeFile string,
structName string,
) (map[string]struct{}, error) {
methods := make(map[string]struct{})
entries, err := os.ReadDir(dirPath)
if err != nil {
return nil, xerrors.Errorf("read dir %s: %w", dirPath, err)
}
for _, entry := range entries {
name := entry.Name()
if entry.IsDir() || name == excludeFile || !strings.HasSuffix(name, ".go") || strings.HasSuffix(name, "_test.go") {
continue
}
contents, err := os.ReadFile(filepath.Join(dirPath, name))
if err != nil {
return nil, xerrors.Errorf("read %s: %w", name, err)
}
f, err := decorator.Parse(contents)
if err != nil {
return nil, xerrors.Errorf("parse %s: %w", name, err)
}
for _, decl := range f.Decls {
funcDecl, ok := decl.(*dst.FuncDecl)
if !ok || funcDecl.Recv == nil || len(funcDecl.Recv.List) == 0 {
continue
}
var ident *dst.Ident
switch recv := funcDecl.Recv.List[0].Type.(type) {
case *dst.Ident:
ident = recv
case *dst.StarExpr:
ident, ok = recv.X.(*dst.Ident)
if !ok {
continue
}
}
if ident == nil || ident.Name != structName {
continue
}
methods[funcDecl.Name.Name] = struct{}{}
}
}
return methods, nil
}
func loadInterfaceFuncs(f *dst.File, interfaceName string) ([]querierFunction, error) {
var querier *dst.InterfaceType
for _, decl := range f.Decls {
genDecl, ok := decl.(*dst.GenDecl)
if !ok {
continue
}
for _, spec := range genDecl.Specs {
typeSpec, ok := spec.(*dst.TypeSpec)
if !ok {
continue
}
// This is the name of the interface. If that ever changes,
// this will need to be updated.
if typeSpec.Name.Name != interfaceName {
continue
}
querier, ok = typeSpec.Type.(*dst.InterfaceType)
if !ok {
return nil, xerrors.Errorf("unexpected sqlcQuerier type: %T", typeSpec.Type)
}
break
}
}
if querier == nil {
return nil, xerrors.Errorf("querier not found")
}
funcs := []querierFunction{}
allMethods := interfaceMethods(querier)
for _, method := range allMethods {
funcType, ok := method.Type.(*dst.FuncType)
if !ok {
continue
}
for _, t := range []*dst.FieldList{funcType.Params, funcType.Results, funcType.TypeParams} {
if t == nil {
continue
}
for _, f := range t.List {
var ident *dst.Ident
switch t := f.Type.(type) {
case *dst.Ident:
ident = t
case *dst.StarExpr:
ident, ok = t.X.(*dst.Ident)
if !ok {
continue
}
case *dst.SelectorExpr:
ident, ok = t.X.(*dst.Ident)
if !ok {
continue
}
case *dst.ArrayType:
ident, ok = t.Elt.(*dst.Ident)
if !ok {
continue
}
}
if ident == nil {
continue
}
// If the type is exported then we should be able to find it
// in the database package!
if !ident.IsExported() {
continue
}
ident.Path = "github.com/coder/coder/v2/coderd/database"
}
}
funcs = append(funcs, querierFunction{
Name: method.Names[0].Name,
Func: funcType,
})
}
return funcs, nil
}
// localFilePath returns the location of `main.go` in the dbgen package.
func localFilePath() (string, error) {
_, filename, _, ok := runtime.Caller(0)
if !ok {
return "", xerrors.Errorf("failed to get caller")
}
return filename, nil
}
// nameFromSnakeCase converts snake_case to CamelCase.
func nameFromSnakeCase(s string) string {
var ret string
for _, ss := range strings.Split(s, "_") {
switch ss {
case "id":
ret += "ID"
case "ids":
ret += "IDs"
case "jwt":
ret += "JWT"
case "idx":
ret += "Index"
case "api":
ret += "API"
case "uuid":
ret += "UUID"
case "gitsshkeys":
ret += "GitSSHKeys"
case "fkey":
// ignore
default:
ret += strings.Title(ss)
}
}
return ret
}
// interfaceMethods returns all embedded methods of an interface.
func interfaceMethods(i *dst.InterfaceType) []*dst.Field {
var allMethods []*dst.Field
for _, field := range i.Methods.List {
switch fieldType := field.Type.(type) {
case *dst.FuncType:
allMethods = append(allMethods, field)
case *dst.InterfaceType:
allMethods = append(allMethods, interfaceMethods(fieldType)...)
case *dst.Ident:
// Embedded interfaces are Idents -> TypeSpec -> InterfaceType
// If the embedded interface is not in the parsed file, then
// the Obj will be nil.
if fieldType.Obj != nil {
objDecl, ok := fieldType.Obj.Decl.(*dst.TypeSpec)
if ok {
isInterface, ok := objDecl.Type.(*dst.InterfaceType)
if ok {
allMethods = append(allMethods, interfaceMethods(isInterface)...)
}
}
}
}
}
return allMethods
}