feat: upgrade QA pipeline to Gemini 3.x models

- qa-record.ts, qa-analyze-pr.ts: gemini-2.5-flash/pro → gemini-3.1-pro-preview
- qa-video-review.ts, qa-generate-test.ts: gemini-2.5-flash → gemini-3-flash-preview
- pr-qa.yaml: update hardcoded model reference
- Add docs/qa/models.md with model comparison and rationale

.github/workflows/pr-qa.yaml

@@ -672,7 +672,7 @@ jobs:
               --artifacts-dir qa-artifacts \
               --output-dir video-reviews \
               --video-file "$vid" \
-              --model gemini-2.5-flash $PR_CTX_FLAG $BEFORE_FLAG $TARGET_URL_FLAG || true
+              --model gemini-3-flash-preview $PR_CTX_FLAG $BEFORE_FLAG $TARGET_URL_FLAG || true
             echo "::endgroup::"
           done
 

docs/qa/models.md

@@ -0,0 +1,58 @@
+# QA Pipeline Model Selection
+
+## Current Configuration
+
+| Script | Role | Model | Why |
+|---|---|---|---|
+| `qa-analyze-pr.ts` | PR/issue analysis, QA guide generation | `gemini-3.1-pro-preview` | Needs deep reasoning over PR diffs, screenshots, and issue threads |
+| `qa-record.ts` | Playwright step generation | `gemini-3.1-pro-preview` | Step quality is critical — must understand ComfyUI's canvas UI and produce precise action sequences |
+| `qa-video-review.ts` | Video comparison review | `gemini-3-flash-preview` | Video analysis with structured output; flash is sufficient and faster |
+| `qa-generate-test.ts` | Regression test generation | `gemini-3-flash-preview` | Code generation from QA reports; flash handles this well |
+
+## Model Comparison
+
+### Gemini 3.1 Pro vs GPT-5.4
+
+| | Gemini 3.1 Pro Preview | GPT-5.4 |
+|---|---|---|
+| Context window | 1M tokens | 1M tokens |
+| Max output | 65K tokens | 128K tokens |
+| Video input | Yes | No |
+| Image input | Yes | Yes |
+| Audio input | Yes | No |
+| Pricing (input) | $2/1M tokens | $2.50/1M tokens |
+| Pricing (output) | $12/1M tokens | $15/1M tokens |
+| Function calling | Yes | Yes |
+| Code execution | Yes | Yes (interpreter) |
+| Structured output | Yes | Yes |
+
+**Why Gemini over GPT for QA:**
+- Native video understanding (can review recordings directly)
+- Lower cost at comparable quality
+- Native multimodal input (screenshots, videos, audio from issue threads)
+- Better price/performance for high-volume CI usage
+
+### Gemini 3 Flash vs GPT-5.4 Mini
+
+| | Gemini 3 Flash Preview | GPT-5.4 Mini |
+|---|---|---|
+| Context window | 1M tokens | 1M tokens |
+| Pricing (input) | $0.50/1M tokens | $0.40/1M tokens |
+| Pricing (output) | $3/1M tokens | $1.60/1M tokens |
+| Video input | Yes | No |
+
+**Why Gemini Flash for video review:**
+- Video input support is required — GPT models cannot process video files
+- Good enough quality for structured comparison reports
+
+## Upgrade History
+
+| Date | Change | Reason |
+|---|---|---|
+| 2026-03-24 | `gemini-2.5-flash` → `gemini-3.1-pro-preview` (record) | Shallow step generation; pro model needed for complex ComfyUI interactions |
+| 2026-03-24 | `gemini-2.5-pro` → `gemini-3.1-pro-preview` (analyze) | Keep analysis on latest pro |
+| 2026-03-24 | `gemini-2.5-flash` → `gemini-3-flash-preview` (review, test-gen) | Latest flash for cost-efficient tasks |
+
+## Override
+
+All scripts accept `--model <name>` to override the default. Pass any Gemini model ID.

scripts/qa-analyze-pr.ts

@@ -11,7 +11,7 @@
  *     --pr-number 10270 \
  *     --repo owner/repo \
  *     --output-dir qa-guides/ \
- *     [--model gemini-2.5-pro]
+ *     [--model gemini-3.1-pro-preview]
  *
  * Env: GEMINI_API_KEY (required)
  */
@@ -67,7 +67,7 @@ interface Options {
 function parseArgs(): Options {
   const args = process.argv.slice(2)
   const opts: Partial<Options> = {
-    model: 'gemini-2.5-pro',
+    model: 'gemini-3.1-pro-preview',
     apiKey: process.env.GEMINI_API_KEY || '',
     mediaBudgetBytes: 20 * 1024 * 1024,
     maxVideoBytes: 10 * 1024 * 1024,

scripts/qa-generate-test.ts

@@ -8,7 +8,7 @@
  *     --qa-report <path>       QA video review report (markdown)
  *     --pr-diff <path>         PR diff file
  *     --output <path>          Output .spec.ts file path
- *     --model <name>           Gemini model (default: gemini-2.5-flash)
+ *     --model <name>           Gemini model (default: gemini-3-flash-preview)
  */
 import { readFile, writeFile } from 'node:fs/promises'
 import { basename, resolve } from 'node:path'
@@ -26,7 +26,7 @@ const DEFAULTS: CliOptions = {
   qaReport: '',
   prDiff: '',
   output: '',
-  model: 'gemini-2.5-flash'
+  model: 'gemini-3-flash-preview'
 }
 
 // ── Fixture API reference for the prompt ────────────────────────────
@@ -171,7 +171,7 @@ Options:
   --qa-report <path>   QA video review report (markdown) [required]
   --pr-diff <path>     PR diff file [required]
   --output <path>      Output .spec.ts path [required]
-  --model <name>       Gemini model (default: gemini-2.5-flash)`)
+  --model <name>       Gemini model (default: gemini-3-flash-preview)`)
         process.exit(0)
     }
   }

scripts/qa-record.ts

@@ -65,7 +65,7 @@ interface Options {
 function parseArgs(): Options {
   const args = process.argv.slice(2)
   const opts: Partial<Options> = {
-    model: 'gemini-2.5-flash',
+    model: 'gemini-3.1-pro-preview',
     serverUrl: 'http://127.0.0.1:8188',
     apiKey: process.env.GEMINI_API_KEY || ''
   }

scripts/qa-video-review.ts

@@ -29,7 +29,7 @@ const DEFAULT_OPTIONS: CliOptions = {
   videoFile: '',
   beforeVideo: '',
   outputDir: './tmp',
-  model: 'gemini-2.5-flash',
+  model: 'gemini-3-flash-preview',
   requestTimeoutMs: 300_000,
   dryRun: false,
   prContext: '',
@@ -50,7 +50,7 @@ Options:
   --output-dir <path>           Output directory for markdown reports
                                  (default: ./tmp)
   --model <name>                Gemini model
-                                 (default: gemini-2.5-flash)
+                                 (default: gemini-3-flash-preview)
   --request-timeout-ms <n>      Request timeout in milliseconds
                                  (default: 300000)
   --pr-context <file>           File with PR context (title, body, diff)