> For the complete documentation index, see [llms.txt](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/sessions/phase37-session05-g6-ui-cinematics/validation.md).

# Validation Report

**Session ID**: `phase37-session05-g6-ui-cinematics` **Validated**: 2026-06-29 **Result**: PASS

## Validation Summary

| Check                     | Status | Notes                                                                                                                                         |
| ------------------------- | ------ | --------------------------------------------------------------------------------------------------------------------------------------------- |
| Code Review               | PASS   | `code-review.md` exists with `Result: RESOLVED` and scope "All uncommitted changes in the working tree".                                      |
| Tasks Complete            | PASS   | 23/23 tasks complete in `tasks.md`.                                                                                                           |
| Files Exist               | PASS   | 22/22 declared deliverables exist and are non-empty.                                                                                          |
| ASCII Encoding            | PASS   | 19 text deliverables plus session docs are ASCII/LF; 3 binary PNG deliverables are valid PNG files.                                           |
| Tests Passing             | PASS   | 4,446 repo Vitest tests, 410 AI Rogue Vitest tests, 67 focused tests, and 25 broader AI Rogue Playwright tests passed.                        |
| Database/Schema Alignment | N/A    | N/A -- no DB-layer, migration, SQL, persistence-schema, or package dependency changes.                                                        |
| Quality Gates             | PASS   | Packer, typecheck, lint, targeted Prettier, asset-size check, and `git diff --check` passed.                                                  |
| Conventions               | PASS   | Targeted convention spot-check found no naming, structure, error-handling, comment, testing, or UI-surface violations.                        |
| Security & GDPR           | PASS   | Security PASS; GDPR N/A. See `security-compliance.md`.                                                                                        |
| Behavioral Quality        | PASS   | Spot-check found no trust-boundary, lifecycle, mutation, failure-path, contract, or product-surface violations.                               |
| UI Product Surface        | PASS   | Desktop/mobile browser proof and code inspection found no debug diagnostics, G6 frame-name leakage, overflow, or unclear control replacement. |

**Overall**: PASS

## Evidence Ledger

* Project state
  * Command:

    ```bash
    if [ -d ".spec_system/scripts" ]; then bash .spec_system/scripts/analyze-project.sh --json; else bash /home/aiwithapex/.codex/plugins/cache/apex-spec-system/apex-spec/2.1.3-codex/scripts/analyze-project.sh --json; fi
    ```
  * Result: PASS
  * Evidence: Current session resolved to `phase37-session05-g6-ui-cinematics`; session directory exists; repo is not detected as monorepo.
* Code review
  * Inspection: `.spec_system/specs/phase37-session05-g6-ui-cinematics/code-review.md`
  * Result: PASS
  * Evidence: File exists; `Result: RESOLVED`; scope states all uncommitted changes were reviewed.
* Task completion
  * Inspection: `.spec_system/specs/phase37-session05-g6-ui-cinematics/tasks.md`
  * Result: PASS
  * Evidence: Header says `Tasks Completed: 23 / 23`; all task checklist rows are `[x]`.
* Deliverables
  * Command:

    ```bash
    while IFS= read -r f; do if [ -s "$f" ]; then printf 'PASS %s %s\n' "$(stat -c%s "$f")" "$f"; else printf 'FAIL 0 %s\n' "$f"; fi; done
    ```
  * Result: PASS
  * Evidence: 22/22 declared deliverables reported `PASS` with non-zero size.
* ASCII/LF
  * Commands:

    ```bash
    file [text deliverables and session docs]
    LC_ALL=C grep -n '[^[:print:][:space:]]' [text deliverables and session docs]
    grep -l $'\r' [text deliverables and session docs]
    ```
  * Result: PASS
  * Evidence: Text deliverables and session docs reported ASCII/JSON text and LF only; PNG deliverables reported valid PNG dimensions.
* Generator
  * Command: `python3 scripts/extensions/ai-rogue/pack-visual-assets.py`
  * Result: PASS
  * Evidence: gameplay 234 frames, UI 146 frames, manifest 210 accepted / 31 rejected, preview 228,335 bytes.
* Typecheck
  * Command: `bun run typecheck`
  * Result: PASS
  * Evidence: `tsc --noEmit` completed with exit 0.
* Lint
  * Command: `bun run lint`
  * Result: PASS
  * Evidence: ESLint completed with exit 0.
* Formatting
  * Command:

    ```bash
    bunx prettier --check .spec_system/specs/phase37-session05-g6-ui-cinematics/spec.md .spec_system/specs/phase37-session05-g6-ui-cinematics/tasks.md .spec_system/specs/phase37-session05-g6-ui-cinematics/implementation-notes.md .spec_system/specs/phase37-session05-g6-ui-cinematics/code-review.md docs/extensions/ai-rogue/visual-assets.md docs/ongoing-projects/generated/ai-rogue-visual-audio-assets/crop-manifest.json src/assets/ai-rogue/ui-atlas.json src/assets/ai-rogue/gameplay-atlas.json src/extensions/ai-rogue/runtime/types-assets.ts src/extensions/ai-rogue/runtime/assets.ts src/extensions/ai-rogue/runtime/effects-cinematics.ts src/extensions/ai-rogue/runtime/render-hud.ts src/extensions/ai-rogue/views/reward-icon.tsx src/extensions/ai-rogue/views/play-view.tsx src/extensions/ai-rogue/views/ledger-view.tsx src/extensions/ai-rogue/views/loadout-view.tsx src/extensions/ai-rogue/views/settings-view.tsx src/extensions/ai-rogue/runtime/__tests__/assets.test.ts src/extensions/ai-rogue/runtime/__tests__/render-model.test.ts src/extensions/ai-rogue/__tests__/client.test.tsx tests/e2e/ai-rogue-runtime.spec.ts tests/e2e/ai-rogue-mobile.spec.ts
    ```
  * Result: PASS
  * Evidence: All matched files use Prettier code style.
* Validation artifact formatting
  * Command: `bunx prettier --check .spec_system/specs/phase37-session05-g6-ui-cinematics/security-compliance.md .spec_system/specs/phase37-session05-g6-ui-cinematics/validation.md`
  * Result: PASS
  * Evidence: Both generated validation reports use Prettier code style after report write.
* Validation artifact ASCII/LF
  * Command:

    ```bash
    for f in .spec_system/specs/phase37-session05-g6-ui-cinematics/security-compliance.md .spec_system/specs/phase37-session05-g6-ui-cinematics/validation.md .spec_system/state.json; do LC_ALL=C grep -n '[^[:print:][:space:]]' "$f"; grep -l $'\r' "$f"; done
    ```
  * Result: PASS
  * Evidence: `security-compliance.md`, `validation.md`, and `state.json` are ASCII with LF endings.
* Asset sizes
  * Command: `bash scripts/check-asset-sizes.sh`
  * Result: PASS
  * Evidence: All assets within configured size limits; total asset size 15M.
* Whitespace
  * Command: `git diff --check`
  * Result: PASS
  * Evidence: No whitespace errors.
* Focused Vitest
  * Command: `bunx vitest run src/extensions/ai-rogue/runtime/__tests__/assets.test.ts src/extensions/ai-rogue/runtime/__tests__/render-model.test.ts src/extensions/ai-rogue/__tests__/client.test.tsx`
  * Result: PASS
  * Evidence: 3 test files passed; 67 tests passed.
* AI Rogue Vitest
  * Command: `bunx vitest run src/extensions/ai-rogue`
  * Result: PASS
  * Evidence: 49 test files passed; 410 tests passed.
* Repo Vitest
  * Command: `bun run test`
  * Result: PASS
  * Evidence: 387 test files passed; 4,446 tests passed.
* Focused Playwright
  * Command: `PLAYWRIGHT_PORT=5391 PLAYWRIGHT_PUBLIC_DEMO_PORT=5392 bunx playwright test tests/e2e/ai-rogue-runtime.spec.ts tests/e2e/ai-rogue-mobile.spec.ts --project=chromium`
  * Result: PASS
  * Evidence: 22 browser tests passed.
* Broader AI Rogue Playwright
  * Command: `PLAYWRIGHT_PORT=5393 PLAYWRIGHT_PUBLIC_DEMO_PORT=5394 bunx playwright test tests/e2e/ai-rogue-ledger.spec.ts tests/e2e/ai-rogue-runtime.spec.ts tests/e2e/ai-rogue-enablement.spec.ts tests/e2e/ai-rogue-mobile.spec.ts tests/e2e/ai-rogue-persistence.spec.ts --project=chromium`
  * Result: PASS
  * Evidence: 25 browser tests passed.
* Database/schema
  * Command:

    ```bash
    git diff --name-only HEAD | rg '(^|/)(migrations?|schema|prisma|drizzle|sql)(/|\.)|\.sql$' || true
    ```
  * Result: N/A
  * Evidence: No migration, schema, Prisma, Drizzle, SQL, or DB artifact changes.
* Non-functional boundaries
  * Command:

    ```bash
    git diff --name-only HEAD | rg 'src/extensions/ai-rogue/runtime/(simulation|combat|persistence|save|renderer|input|world|collector|worker)|src/server|wrangler|schema|migration|\.sql|package.json|bun.lock' || true
    ```
  * Result: PASS
  * Evidence: No simulation, renderer lifecycle, persistence schema, server, worker, dependency, migration, or SQL files changed.
* Success criteria
  * Inspection: `spec.md` plus generator/typecheck/test/browser commands above.
  * Result: PASS
  * Evidence: Functional, testing, non-functional, and quality-gate requirements are met.
* Conventions
  * Inspection: `.spec_system/CONVENTIONS.md`, touched file snippets, `bun run lint`, targeted Prettier, and test paths.
  * Result: PASS
  * Evidence: Existing TypeScript, React, testing, media policy, and file structure conventions are followed.
* Security/GDPR
  * Commands:

    ```bash
    rg -n "api[_-]?key|secret|token|password|Authorization|Bearer|dangerouslySetInnerHTML|innerHTML|eval\(|new Function|child_process|exec\(|spawn\(|fetch\(|postMessage|document\.cookie|localStorage|indexedDB" [session files]
    git diff -- package.json bun.lock
    ```
  * Result: PASS/N/A
  * Evidence: No actionable secret, injection, dynamic-code, network, cookie, or dependency findings. GDPR N/A because no personal data handling was introduced.
* Behavioral quality
  * Commands:

    ```bash
    sed -n [targeted ranges] src/extensions/ai-rogue/views/play-view.tsx src/extensions/ai-rogue/views/ledger-view.tsx src/extensions/ai-rogue/views/loadout-view.tsx src/extensions/ai-rogue/views/settings-view.tsx src/extensions/ai-rogue/views/reward-icon.tsx
    rg -n "RewardIcon|aria-label|role=|disabled=|loadoutActionInFlightRef|claimActionInFlightRef|onClick|onCheckedChange|storage|publicDemo|error|fallback|missing" src/extensions/ai-rogue/views/play-view.tsx src/extensions/ai-rogue/views/ledger-view.tsx src/extensions/ai-rogue/views/loadout-view.tsx src/extensions/ai-rogue/views/settings-view.tsx src/extensions/ai-rogue/views/reward-icon.tsx
    ```
  * Result: PASS
  * Evidence: Guards, labels, failure states, fallback behavior, and mutation-prevention paths remain present.
* UI product surface
  * Command:

    ```bash
    rg -n "G6 HUD|end-screen|React surfaces|horizontal document overflow|route-visible|debug|telemetry|frame|seed|G6 frame names|no G6" tests/e2e/ai-rogue-runtime.spec.ts tests/e2e/ai-rogue-mobile.spec.ts src/extensions/ai-rogue/__tests__/client.test.tsx
    ```
  * Result: PASS
  * Evidence: Browser tests cover G6 assets, no overflow, no bridge requests on non-Play routes, no frame/debug/telemetry/seed label leakage, and no route-visible G6 frame names.

## 1. Code Review Gate

### Status: PASS

**Report**: `code-review.md` **Result**: RESOLVED **Issues**: None remaining. The report lists two low-severity findings, both fixed during `creview`.

## 2. Task Completion

### Status: PASS

**Tasks**: 23/23 complete **Incomplete tasks**: None

## 3. Deliverables Verification

### Status: PASS

| File                                                                              | Found | Status |
| --------------------------------------------------------------------------------- | ----- | ------ |
| `.spec_system/specs/phase37-session05-g6-ui-cinematics/implementation-notes.md`   | Yes   | PASS   |
| `docs/ongoing-projects/generated/ai-rogue-visual-audio-assets/crop-manifest.json` | Yes   | PASS   |
| `src/assets/ai-rogue/ui-atlas.png`                                                | Yes   | PASS   |
| `src/assets/ai-rogue/ui-atlas.json`                                               | Yes   | PASS   |
| `src/assets/ai-rogue/gameplay-atlas.png`                                          | Yes   | PASS   |
| `src/assets/ai-rogue/gameplay-atlas.json`                                         | Yes   | PASS   |
| `docs/extensions/ai-rogue/generated/ai-rogue-production-atlas-preview.png`        | Yes   | PASS   |
| `src/extensions/ai-rogue/runtime/types-assets.ts`                                 | Yes   | PASS   |
| `src/extensions/ai-rogue/runtime/assets.ts`                                       | Yes   | PASS   |
| `src/extensions/ai-rogue/runtime/effects-cinematics.ts`                           | Yes   | PASS   |
| `src/extensions/ai-rogue/runtime/render-hud.ts`                                   | Yes   | PASS   |
| `src/extensions/ai-rogue/views/reward-icon.tsx`                                   | Yes   | PASS   |
| `src/extensions/ai-rogue/views/play-view.tsx`                                     | Yes   | PASS   |
| `src/extensions/ai-rogue/views/ledger-view.tsx`                                   | Yes   | PASS   |
| `src/extensions/ai-rogue/views/loadout-view.tsx`                                  | Yes   | PASS   |
| `src/extensions/ai-rogue/views/settings-view.tsx`                                 | Yes   | PASS   |
| `src/extensions/ai-rogue/runtime/__tests__/assets.test.ts`                        | Yes   | PASS   |
| `src/extensions/ai-rogue/runtime/__tests__/render-model.test.ts`                  | Yes   | PASS   |
| `src/extensions/ai-rogue/__tests__/client.test.tsx`                               | Yes   | PASS   |
| `tests/e2e/ai-rogue-runtime.spec.ts`                                              | Yes   | PASS   |
| `tests/e2e/ai-rogue-mobile.spec.ts`                                               | Yes   | PASS   |
| `docs/extensions/ai-rogue/visual-assets.md`                                       | Yes   | PASS   |

**Missing deliverables**: None

## 4. ASCII Encoding Check

### Status: PASS

| File group                                                                 | Encoding                         | Line Endings | Status |
| -------------------------------------------------------------------------- | -------------------------------- | ------------ | ------ |
| 19 text deliverables                                                       | ASCII / JSON text                | LF           | PASS   |
| `spec.md`, `tasks.md`, `implementation-notes.md`, `code-review.md`         | ASCII                            | LF           | PASS   |
| `src/assets/ai-rogue/ui-atlas.png`                                         | PNG image data, 512 x 256 RGBA   | Binary       | PASS   |
| `src/assets/ai-rogue/gameplay-atlas.png`                                   | PNG image data, 512 x 230 RGBA   | Binary       | PASS   |
| `docs/extensions/ai-rogue/generated/ai-rogue-production-atlas-preview.png` | PNG image data, 1072 x 1080 RGBA | Binary       | PASS   |

**Encoding issues**: None

## 5. Test Results

### Status: PASS

| Metric      | Value                                                         |
| ----------- | ------------------------------------------------------------- |
| Total Tests | 4,446 repo Vitest tests; 25 broader AI Rogue Playwright tests |
| Passed      | 4,446 Vitest; 25 Playwright                                   |
| Failed      | 0                                                             |
| Coverage    | Not collected; session did not require a coverage gate        |

**Additional focused evidence**:

* `bunx vitest run src/extensions/ai-rogue/runtime/__tests__/assets.test.ts src/extensions/ai-rogue/runtime/__tests__/render-model.test.ts src/extensions/ai-rogue/__tests__/client.test.tsx` - PASS, 67 tests.
* `bunx vitest run src/extensions/ai-rogue` - PASS, 410 tests.
* `PLAYWRIGHT_PORT=5391 PLAYWRIGHT_PUBLIC_DEMO_PORT=5392 bunx playwright test tests/e2e/ai-rogue-runtime.spec.ts tests/e2e/ai-rogue-mobile.spec.ts --project=chromium` - PASS, 22 tests.

**Failed tests**: None

## 6. Database/Schema Alignment

### Status: N/A

N/A -- no DB-layer changes. Evidence command: `git diff --name-only HEAD | rg '(^|/)(migrations?|schema|prisma|drizzle|sql)(/|\.)|\.sql$' || true`

**Issues found**: None

## 7. Success Criteria

From `spec.md`:

**Functional requirements**:

* PASS - G6 accepted/rejected candidates are recorded in `crop-manifest.json`; `jq` reports 39 G6 records, 31 accepted and 8 rejected.
* PASS - Runtime UI atlas regenerates successfully; packer reports UI 146 frames and `assets.ts` includes `AI_ROGUE_G6_UI_FRAME_NAMES` in required UI frames.
* PASS - End-screen panel and badge art render through G6 frames while title, stats, prompts, and numbers remain Pixi text; covered by runtime code inspection and Playwright G6 proof.
* PASS - HUD and React surfaces use G6 art only for domain readability; standard controls remain Lucide/native controls where appropriate.
* PASS - Play, Ledger, Loadout, and Settings preserve loading, empty, error, storage-unavailable, public-demo, and recovery states; covered by focused client tests and broader AI Rogue Playwright tests.

**Testing requirements**:

* PASS - `python3 scripts/extensions/ai-rogue/pack-visual-assets.py`
* PASS - `bun run typecheck`
* PASS - `bash scripts/check-asset-sizes.sh`
* PASS - Focused assets, render-model, and client tests
* PASS - `bunx playwright test tests/e2e/ai-rogue-runtime.spec.ts`
* PASS - `bunx playwright test tests/e2e/ai-rogue-mobile.spec.ts`

**Non-functional requirements**:

* PASS - Non-functional boundary command found no simulation, combat, input, persistence-schema, public-demo boundary, hosted-runtime, collector, analytics, remote-loading, worker, or WebGPU-only behavior files changed.
* PASS - AI Rogue enablement posture preserved; broader Playwright command includes `tests/e2e/ai-rogue-enablement.spec.ts`.
* PASS - Asset-size command passed with committed runtime assets within policy caps.
* PASS - Desktop/mobile browser tests passed with no overflow, no frame-name leakage, and stable G6 surface proof.

**Quality gates**:

* PASS - Text deliverables ASCII-encoded.
* PASS - Text deliverables use LF line endings.
* PASS - Code follows project conventions by targeted inspection, lint, typecheck, and tests.
* PASS - Primary user-facing surfaces contain product-facing copy only, verified by client/e2e assertions.
* PASS - `git diff --check` passed.

## 8. Conventions Compliance

### Status: PASS

**Categories spot-checked**: naming, file structure, error handling, comments, testing, media policy, accessibility labels, UI control familiarity, and database conventions when relevant.

**Evidence**:

* `.spec_system/CONVENTIONS.md` inspection - PASS, current files stay under existing `src/extensions/ai-rogue` runtime/view/test and docs locations.
* `bun run lint` - PASS.
* Targeted `bunx prettier --check ...` over session text files - PASS.
* `bash scripts/check-asset-sizes.sh` - PASS.
* `git diff --name-only HEAD | rg '(^|/)(migrations?|schema|prisma|drizzle|sql)(/|\.)|\.sql$' || true` - N/A for database conventions; no DB files changed.

**Convention violations**: None

## 9. Security & GDPR Compliance

### Status: PASS

**Full report**: See `security-compliance.md` in this session directory.

#### Summary

| Area     | Status | Findings |
| -------- | ------ | -------- |
| Security | PASS   | 0 issues |
| GDPR     | N/A    | 0 issues |

**Critical violations**: None

## 10. Behavioral Quality Spot-Check

### Status: PASS

**Checklist applied**: Yes **Files spot-checked**:

* `src/extensions/ai-rogue/views/play-view.tsx`
* `src/extensions/ai-rogue/views/ledger-view.tsx`
* `src/extensions/ai-rogue/views/loadout-view.tsx`
* `src/extensions/ai-rogue/views/settings-view.tsx`
* `src/extensions/ai-rogue/views/reward-icon.tsx`

**Categories spot-checked**: trust boundaries, resource cleanup, mutation safety, failure paths, contract alignment, accessibility, and product surface discipline.

**Violations found**: None

**Evidence**:

* `sed -n '150,450p' src/extensions/ai-rogue/views/play-view.tsx` - PASS, seed replay/copy paths use sanitized seed-share helpers, clipboard failure has visible fallback, and persistence failure states remain explicit.
* `sed -n '180,330p' src/extensions/ai-rogue/views/ledger-view.tsx` - PASS, claim action remains disabled unless `canClaim`, loading/offline/storage/error states remain visible, and browser-local demo copy remains scoped.
* `sed -n '90,260p' src/extensions/ai-rogue/views/loadout-view.tsx` - PASS, `loadoutActionInFlightRef`, disabled states, and `finally` cleanup preserve duplicate-action prevention.
* `sed -n '250,520p' src/extensions/ai-rogue/views/settings-view.tsx` - PASS, settings controls use platform inputs/buttons, `disabled={!canWrite}` guards, explicit reset confirmation, and visible error/status paths.
* `sed -n '150,210p' src/extensions/ai-rogue/views/reward-icon.tsx` - PASS, missing frames return `null`, meaningful icons get `role="img"` and labels, decorative icons are hidden from assistive tech, and dimensions are stable.

**Fixes applied during validation**: None

## 11. UI Product-Surface Spot-Check

### Status: PASS

**Surfaces inspected**: AI Rogue Play desktop and mobile, Ledger, Loadout, Settings, runtime end screen, HUD descriptors, React icon surfaces, and mobile layout viewports through the focused and broader Playwright commands.

**Diagnostics found in primary UI**: None

**Allowed debug/admin surfaces**: None

**Evidence**:

* `PLAYWRIGHT_PORT=5391 PLAYWRIGHT_PUBLIC_DEMO_PORT=5392 bunx playwright test tests/e2e/ai-rogue-runtime.spec.ts tests/e2e/ai-rogue-mobile.spec.ts --project=chromium` - PASS, 22 tests.
* `PLAYWRIGHT_PORT=5393 PLAYWRIGHT_PUBLIC_DEMO_PORT=5394 bunx playwright test tests/e2e/ai-rogue-ledger.spec.ts tests/e2e/ai-rogue-runtime.spec.ts tests/e2e/ai-rogue-enablement.spec.ts tests/e2e/ai-rogue-mobile.spec.ts tests/e2e/ai-rogue-persistence.spec.ts --project=chromium` - PASS, 25 tests.
* `rg -n "G6 HUD|end-screen|React surfaces|horizontal document overflow|route-visible|debug|telemetry|frame|seed|G6 frame names|no G6" tests/e2e/ai-rogue-runtime.spec.ts tests/e2e/ai-rogue-mobile.spec.ts src/extensions/ai-rogue/__tests__/client.test.tsx` - PASS, tests assert no route-visible G6 names, no frame/debug/telemetry/seed sprite-label leakage, no horizontal overflow, no non-Play bridge requests, and preserved product-facing surfaces.

**Fixes applied during validation**: None

## Validation Result

### PASS

The session satisfies the `validate` gate. Code review is resolved, all tasks and deliverables are complete, generator/typecheck/lint/tests/browser checks passed, security is clean, GDPR is N/A, and no database/schema, behavioral, or UI product-surface blocker remains.

### Unresolved Failures And Blockers

None

## Next Steps

Next command: `updateprd`


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/sessions/phase37-session05-g6-ui-cinematics/validation.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.