@openlines/opl-pi-sht 0.1.16 → 0.1.18

package/README.md

@@ -11,8 +11,8 @@ A portable collection of various Pi coding agent extensions. Repository director
 Install a versioned release from npm or GitHub. Both ship identical content; pick one source per machine, because Pi treats the npm and Git entries as separate packages and installing both loads every extension twice.
 
 ```bash
-pi install npm:@openlines/opl-pi-sht@0.1.15
-pi install git:github.com/linellazatin/opl-pi-sht@v0.1.15
+pi install npm:@openlines/opl-pi-sht@0.1.18
+pi install git:github.com/linellazatin/opl-pi-sht@v0.1.18
 ```
 
 > Omitting the version on the npm source tracks the latest published release; Git refs stay pinned, so move them with `pi install ...@v<new>`.
@@ -34,7 +34,7 @@ npx playwright install chromium
 {
   "packages": [
     {
-      "source": "npm:@openlines/opl-pi-sht@0.1.15",
+      "source": "npm:@openlines/opl-pi-sht@0.1.18",
       "extensions": ["extensions/opl-init/index.ts", "extensions/opl-todo/index.ts"]
     }
   ]
@@ -64,7 +64,7 @@ Copy mode overwrites matching destinations. Link mode skips existing destination
 | [`opl-init`](extensions/opl-init/README.md)                   | Fingerprinted repository-guide generator.                                                                                                                                                                                    | `/init`; no config.                                                                                            |
 | [`opl-simplebench`](extensions/opl-simplebench/README.md)     | Auditable provider-aware model benchmark with JSON artifacts and metrics.                                                                                                                                                    | `/simplebench`, `simplebench`; supports Ollama, OpenAI-compatible providers, and Bedrock; optional `opl-simplebench.json`. |
 | [`opl-webaccess`](extensions/opl-webaccess/README.md)         | Search plus readable URL/PDF retrieval with session recovery.                                                                                                                                                                | `web_search`, `fetch_content`, `get_search_content`; `opl-webaccess.json`.                                     |
-| [`opl-browser`](extensions/opl-browser/README.md)             | Chromium automation via Playwright; single dispatcher tool replacing the chrome-devtools MCP.                                                                                                                                | `browser` (action-based); `opl-browser.json`.                                                                  |
+| [`opl-browser`](extensions/opl-browser/README.md)             | Chromium automation via Playwright with structured extraction of rendered pages; single dispatcher tool replacing the chrome-devtools MCP.                                                                                   | `browser` (action-based); `opl-browser.json`.                                                                  |
 | [`opl-ctxtrim`](extensions/opl-ctxtrim/README.md)             | Trims verbose`ctx_*` tool-schema descriptions on outbound provider requests (~67% smaller schema, ~4,700-6,300 tokens/request). Built specifically for the [context-mode](https://github.com/mksglu/context-mode) extension. | No commands/tools; no config.                                                                                  |
 | [`opl-todo`](extensions/opl-todo/README.md)                   | Branch-aware task tool, overlay, and task list.                                                                                                                                                                              | `todo`, `/todos`; `opl-todo.json`.                                                                             |
 | [`opl-questionnaire`](extensions/opl-questionnaire/README.md) | Interactive structured-choice tool.                                                                                                                                                                                          | `questionnaire`; no config.                                                                                    |
@@ -103,7 +103,7 @@ Cold prompt-cache write, measured /init session (opl-modes lazy tools + MCP adap
 
 - **`opl-init`** writes a fingerprinted `AGENTS.md` so any agent starts already oriented in a repo. It writes a baseline before asking the model to refine the guide, so smaller models cannot leave the update only in chat; it re-runs only when the tree actually changes.
 ![init](images/ss-init.png)
-- **`opl-browser`** gives full Chromium automation (navigate, snapshot, interact, screenshot, console/network capture, evaluate) through a single tool, with handle+preview output for large results.
+- **`opl-browser`** gives full Chromium automation (navigate, snapshot, extract rendered-page markdown, interact, screenshot, console/network capture, evaluate) through a single tool, with handle+preview output for large results.
 - **`opl-webaccess`** adds provider-backed search plus readable URL and PDF extraction, with session recovery of earlier results.
 - **`opl-simplebench`** benchmarks models on deterministic closed-answer contracts, instruction-following, and tool-call generation so you pick a model on evidence, not vibes.
 ![simplebench](images/ss-simplebench.png)
@@ -142,7 +142,7 @@ Installing extensions adds tool schemas (name + description + JSON parameters) t
 
 | Extension | Adds to resting prompt | Est. tokens |
 |---|---|---|
-| `opl-browser` | `browser` tool schema | ~554 |
+| `opl-browser` | `browser` tool schema | ~575 |
 | `opl-questionnaire` | `questionnaire` schema + prompt guidelines | ~532 |
 | `opl-webaccess` | `web_search`, `fetch_content`, `get_search_content` | ~394 |
 | `opl-simplebench` | `simplebench` schema | ~230 |
@@ -200,7 +200,7 @@ npx playwright install chromium
 
 A Pi package (npm or Git) still needs the one-time `npx playwright install chromium` command shown above.
 
-`opl-simplebench` writes a full JSON benchmark artifact in Pi's current working directory by default. `--test-all` additionally writes `research.md` and `page.html` beside `result.json` in a result bundle. `/simplebench --sequence` runs a templated multi-run protocol (for example a model warm-up curve) defined in the `runSequence` block, with per-iteration tags, optional llama-server/llamagputop metrics, and a configurable pause between iterations. Copy `configs/opl-simplebench.json.sample` to `~/.pi/agent/configs/opl-simplebench.json` to configure DDGS/SearXNG research, optional llama-server/llamagputop metadata endpoints, and the run sequence. Use `/simplebench --no-artifact` or `simplebench({ no_artifact: true })` when responses must not be written to disk. Provider credentials remain outside tracked configuration; configure them through Pi provider settings, environment variables, or Pi authentication.
+`opl-simplebench` writes a full JSON benchmark artifact in Pi's current working directory by default. `--test-all` additionally writes `research.md` and `page.html` beside `result.json` in a result bundle. `/simplebench --sequence[=<name>]` runs a named templated multi-run protocol (for example a model warm-up curve) defined in the `runSequence.sequences` block, with per-iteration tags, optional llama-server/llamagputop metrics, and a configurable pause between iterations; block-level `llamaMetrics`/`pauseMs` are defaults a profile can override. Copy `configs/opl-simplebench.json.sample` to `~/.pi/agent/configs/opl-simplebench.json` to configure DDGS/SearXNG research, optional llama-server/llamagputop metadata endpoints, and the run sequence. Use `/simplebench --no-artifact` or `simplebench({ no_artifact: true })` when responses must not be written to disk. Provider credentials remain outside tracked configuration; configure them through Pi provider settings, environment variables, or Pi authentication.
 
 ## Tests
 
@@ -208,4 +208,4 @@ A Pi package (npm or Git) still needs the one-time `npx playwright install chrom
 npm test
 ```
 
-Run one extension suite with `npm run test:opl-<name>` for `footer`, `init`, `input`, `modes`, `questionnaire`, `todo`, `webaccess`, `simplebench`, or `ctxtrim`. Every helper, functional, and selected-entrypoint smoke check uses Bun's named-test reporter; output includes per-test status, timings, and pass/fail totals. Functional tests cover deterministic helpers where practical; smoke tests bundle entrypoints and parse config. They do not test live TUI behavior, provider credentials, network access, or PDF extraction.
+Run one extension suite with `npm run test:opl-<name>` for `browser`, `footer`, `init`, `input`, `modes`, `questionnaire`, `todo`, `webaccess`, `simplebench`, or `ctxtrim`. Every helper, functional, and selected-entrypoint smoke check uses Bun's named-test reporter; output includes per-test status, timings, and pass/fail totals. Functional tests cover deterministic helpers where practical; smoke tests bundle entrypoints and parse config. They do not test live TUI behavior, provider credentials, network access, or PDF extraction.

package/configs/opl-simplebench.json.sample

@@ -1,5 +1,5 @@
 {
-  "_comment": "Copy to ~/.pi/agent/configs/opl-simplebench.json. Endpoints are optional and only used by their corresponding Simplebench flags. runSequence powers /simplebench --sequence: each entry is a flag string; llamaMetrics appends --llama-server --llamagputop to every entry; pauseMs sleeps between iterations.",
+  "_comment": "Copy to ~/.pi/agent/configs/opl-simplebench.json. Endpoints are optional and only used by their corresponding Simplebench flags. runSequence powers /simplebench --sequence[=<name>]: each profile has a single-word name and an iterations list of flag strings; llamaMetrics appends --llama-server --llamagputop to every entry and pauseMs sleeps between iterations. Block-level llamaMetrics/pauseMs are the defaults; a profile may override either. A bare --sequence runs the only defined profile and otherwise lists the names. The legacy flat runSequence.sequence array is still accepted as an anonymous profile.",
   "researchSearchProvider": "ddgs",
   "researchSearchUrl": "http://127.0.0.1:8000",
   "researchMaxResults": 5,
@@ -9,11 +9,25 @@
     "enabled": false,
     "llamaMetrics": true,
     "pauseMs": 5000,
-    "sequence": [
-      "--coding-lite --tag=coldest",
-      "--3ptest --tag=colder",
-      "--coding-lite --tag=semiwarm",
-      "--test-all --research-live --tag=warm"
+    "sequences": [
+      {
+        "name": "warmup",
+        "iterations": [
+          "--coding-lite --tag=coldest",
+          "--3ptest --tag=colder",
+          "--coding-lite --tag=semiwarm",
+          "--test-all --research-live --tag=warm"
+        ]
+      },
+      {
+        "name": "coding-only",
+        "llamaMetrics": false,
+        "pauseMs": 3000,
+        "iterations": [
+          "--coding-lite --tag=coldest",
+          "--coding-lite --tag=warmer"
+        ]
+      }
     ]
   }
 }

package/extensions/opl-browser/README.md

@@ -14,6 +14,8 @@ No slash commands. The extension registers a single tool, `browser`, chosen by a
 ```ts
 browser({ action: "navigate", url: "https://example.com" })
 browser({ action: "snapshot" })
+browser({ action: "extract" })                          // rendered-page markdown
+browser({ action: "extract", selector: "#about-gcash" }) // one element, verbatim
 browser({ action: "click", selector: "button.login" })
 browser({ action: "fill", selector: "#email", text: "a@b.com" })
 browser({ action: "evaluate", script: "document.title" })
@@ -25,9 +27,9 @@ browser({ action: "close" })
 ```
 
 Full action set: `navigate` (url, or `back`/`forward`/`reload`), `snapshot`,
-`screenshot`, `click`, `fill`, `hover`, `press`, `select`, `evaluate`, `console`,
-`network`, `wait_for`, `pages`, `new_page`, `select_page`, `close_page`, `resize`,
-`get`, `close`.
+`extract`, `screenshot`, `click`, `fill`, `hover`, `press`, `select`, `evaluate`,
+`console`, `network`, `wait_for`, `pages`, `new_page`, `select_page`, `close_page`,
+`resize`, `get`, `close`.
 
 ## Extension features
 
@@ -37,6 +39,12 @@ Full action set: `navigate` (url, or `back`/`forward`/`reload`), `snapshot`,
   evaluate output) are kept out of context: the tool returns a truncated preview
   plus a `responseId`; call `action: "get"` with that id for the full text.
   Screenshots are written to a file, never inlined as base64.
+- **Structured extraction.** `extract` runs Readability + Turndown over the
+  *rendered* (post-JS) DOM — the complement to `opl-webaccess`'s `fetch_content`,
+  which only sees raw HTTP HTML. Static pages: `fetch_content`; rendered or
+  interacted-with pages: `browser:extract`. With a `selector`, the matched element
+  is converted verbatim (no article detection): Readability's candidate scoring is
+  a whole-document heuristic and mispicks inside small subtrees.
 - **Real Chromium via Playwright.** Navigation with `domcontentloaded` waits,
   CSS-selector interaction, viewport control, multi-page management.
 - **Per-page capture.** Console messages and network requests are buffered per
@@ -74,6 +82,8 @@ index.ts     Pi wiring: registers the single `browser` tool, TTL result store,
              preview/handle logic, and session_shutdown cleanup.
 browser.ts   Playwright driver: browser/context/page lifecycle, per-page console
              and network buffers, and the action switch.
+extract.ts   Pure rendered-HTML → markdown pipeline (linkedom + Readability +
+             turndown), duplicated from opl-webaccess to keep installs independent.
 config.ts    DEFAULT_CONFIG + loadUserConfig (user overrides win via ??).
 ```
 

package/extensions/opl-browser/browser.ts

@@ -1,4 +1,5 @@
 import { chromium, type Browser, type BrowserContext, type Page, type ConsoleMessage } from "playwright";
+import { extractMarkdown } from "./extract.js";
 import type { BrowserConfig } from "./config.js";
 
 // ponytail: single module-level Chromium instance reused across tool calls.
@@ -87,6 +88,14 @@ export async function runAction(p: BrowserParams, cfg: BrowserConfig): Promise<B
       const tree = await page().locator("body").ariaSnapshot();
       return { text: tree || "(empty snapshot)" };
     }
+    case "extract": {
+      const scoped = Boolean(p.selector);
+      const html = scoped
+        ? await page().locator(p.selector).evaluate((el: Element) => el.outerHTML)
+        : await page().content();
+      const { markdown } = extractMarkdown(html, { raw: scoped });
+      return { text: markdown || "(empty extraction)" };
+    }
     case "screenshot": {
       const file = p.path ?? `opl-browser-${Date.now()}.png`;
       await page().screenshot({ path: file, fullPage: p.fullPage ?? false });

package/extensions/opl-browser/extract.ts

@@ -0,0 +1,36 @@
+import { Readability } from "@mozilla/readability";
+import { parseHTML } from "linkedom";
+import TurndownService from "turndown";
+
+// Structured extraction of a rendered HTML string (post-JS DOM from Playwright).
+// Pipeline mirrors opl-webaccess/extract.ts on purpose; duplicated ~40 lines to
+// keep per-extension installs independent (see research/browser-structured-extraction-plan.md).
+
+const td = new TurndownService({
+  headingStyle: "atx",
+  codeBlockStyle: "fenced",
+});
+
+export interface ExtractedMarkdown {
+  title: string;
+  markdown: string;
+}
+
+export function extractMarkdown(html: string, opts?: { raw?: boolean }): ExtractedMarkdown {
+  // Readability's candidate scoring is a whole-document heuristic; on a small
+  // selector-scoped fragment it drops siblings. Pass raw:true for fragments.
+  if (opts?.raw) {
+    return { title: "", markdown: td.turndown(html) };
+  }
+  const { document } = parseHTML(html);
+  let article = null;
+  try {
+    article = new Readability(document as unknown as Document).parse();
+  } catch {
+    // Readability failed — fall back to raw turndown
+  }
+  if (!article?.content) {
+    return { title: "", markdown: td.turndown(html) };
+  }
+  return { title: article.title ?? "", markdown: td.turndown(article.content) };
+}

package/extensions/opl-browser/index.ts

@@ -19,7 +19,7 @@ function store(action: string, text: string): string {
 }
 
 const ACTIONS =
-  "navigate|snapshot|screenshot|click|fill|hover|press|select|evaluate|console|network|wait_for|pages|new_page|select_page|close_page|resize|get|close";
+  "navigate|snapshot|extract|screenshot|click|fill|hover|press|select|evaluate|console|network|wait_for|pages|new_page|select_page|close_page|resize|get|close";
 
 export default function (pi: ExtensionAPI) {
   const cfg = loadUserConfig();
@@ -33,14 +33,14 @@ export default function (pi: ExtensionAPI) {
     label: "Browser",
     description:
       `Drive a real Chromium browser (Playwright) for web testing and inspection. One dispatcher tool; pick action: ${ACTIONS}. ` +
-      "navigate(url|back|forward|reload); snapshot (accessibility tree); screenshot (saved to file, not inlined); " +
+      "navigate(url|back|forward|reload); snapshot (accessibility tree); extract (rendered-page markdown, optionally scoped to selector); screenshot (saved to file, not inlined); " +
       "click/fill/hover/select by CSS selector; press(key); evaluate(script in page); console/network (captured for active page); " +
       "wait_for(selector|text); pages/new_page/select_page/close_page; resize(width,height); get(responseId) to retrieve a stored large result; close to shut the browser. " +
       "Large outputs return a preview + responseId; call action:get with that id for the full text.",
     parameters: Type.Object({
       action: Type.String({ description: `One of: ${ACTIONS}` }),
       url: Type.Optional(Type.String({ description: "navigate/new_page: URL, or back|forward|reload for navigate" })),
-      selector: Type.Optional(Type.String({ description: "CSS selector for click/fill/hover/select/wait_for" })),
+      selector: Type.Optional(Type.String({ description: "CSS selector for click/fill/hover/select/wait_for/extract" })),
       text: Type.Optional(Type.String({ description: "fill: text to type; wait_for: text to await" })),
       key: Type.Optional(Type.String({ description: "press: key or combo, e.g. Enter, Control+A" })),
       values: Type.Optional(Type.Array(Type.String(), { description: "select: option values" })),

package/extensions/opl-browser/package-lock.json

@@ -1,15 +1,164 @@
 {
   "name": "opl-browser",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "opl-browser",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "license": "ISC",
       "dependencies": {
-        "playwright": "^1.49.0"
+        "@mozilla/readability": "^0.6.0",
+        "linkedom": "^0.18.13",
+        "playwright": "^1.49.0",
+        "turndown": "^7.2.4"
+      }
+    },
+    "node_modules/@mixmark-io/domino": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/@mixmark-io/domino/-/domino-2.2.0.tgz",
+      "integrity": "sha512-Y28PR25bHXUg88kCV7nivXrP2Nj2RueZ3/l/jdx6J9f8J4nsEGcgX0Qe6lt7Pa+J79+kPiJU3LguR6O/6zrLOw==",
+      "license": "BSD-2-Clause"
+    },
+    "node_modules/@mozilla/readability": {
+      "version": "0.6.0",
+      "resolved": "https://registry.npmjs.org/@mozilla/readability/-/readability-0.6.0.tgz",
+      "integrity": "sha512-juG5VWh4qAivzTAeMzvY9xs9HY5rAcr2E4I7tiSSCokRFi7XIZCAu92ZkSTsIj1OPceCifL3cpfteP3pDT9/QQ==",
+      "license": "Apache-2.0",
+      "engines": {
+        "node": ">=14.0.0"
+      }
+    },
+    "node_modules/boolbase": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/boolbase/-/boolbase-2.0.0.tgz",
+      "integrity": "sha512-DkVaaQHymRhpYEYo9x1oo7Q7B0Y6KJUsjm3c9eTyFDby4MHLBTwZ6ZDWBel5zrYxj1WsZgC5oLpiz+93MluXeA==",
+      "license": "ISC",
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
+    "node_modules/css-select": {
+      "version": "7.0.0",
+      "resolved": "https://registry.npmjs.org/css-select/-/css-select-7.0.0.tgz",
+      "integrity": "sha512-snmjEVXy+1LnwXdxhYvTMj1d9tOh4HxkA1YmoayVBeeyR2C14Pum7fcxJIm4SswYspVy866eYNwlH6xC3/VH5g==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "boolbase": "^2.0.0",
+        "css-what": "^8.0.0",
+        "domhandler": "^6.0.1",
+        "domutils": "^4.0.2",
+        "nth-check": "^3.0.1"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
+    "node_modules/css-what": {
+      "version": "8.0.0",
+      "resolved": "https://registry.npmjs.org/css-what/-/css-what-8.0.0.tgz",
+      "integrity": "sha512-DH0Bqq3DNp5tdOReuNyAA+Ev4Y2GS5FMbZpeTLP6C4CDi0h5nL0BmUPChXw3o/qbHLDWHl49sbNqQVY7bMSDdw==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
+    "node_modules/cssom": {
+      "version": "0.5.0",
+      "resolved": "https://registry.npmjs.org/cssom/-/cssom-0.5.0.tgz",
+      "integrity": "sha512-iKuQcq+NdHqlAcwUY0o/HL69XQrUaQdMjmStJ8JFmUaiiQErlhrmuigkg/CU4E2J0IyUKUrMAgl36TvN67MqTw==",
+      "license": "MIT"
+    },
+    "node_modules/dom-serializer": {
+      "version": "3.1.1",
+      "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-3.1.1.tgz",
+      "integrity": "sha512-4MEa38/QexBob6gFNwu+EGdWvhJ1OKuNwdYY3Y3NyeWDQfnGeDYQUDfIRzWu5B5gsv03so2Uxd28YC6zrsx3Lw==",
+      "license": "MIT",
+      "dependencies": {
+        "domelementtype": "^3.0.0",
+        "domhandler": "^6.0.0",
+        "entities": "^8.0.0"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/cheeriojs/dom-serializer?sponsor=1"
+      }
+    },
+    "node_modules/domelementtype": {
+      "version": "3.0.0",
+      "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-3.0.0.tgz",
+      "integrity": "sha512-umCQid3jKbDmVjx8jGaW7uUykm4DEUeyV21hPxNMo2nV955DhUThwqyOIDtreepP31hl84X7G5U9ZfsWvIB3Pg==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ],
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=20.19.0"
+      }
+    },
+    "node_modules/domhandler": {
+      "version": "6.0.1",
+      "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-6.0.1.tgz",
+      "integrity": "sha512-gYzvtM72ZtxQO0T048kd6HWSbbGCNOUwcnfQ01cqIJ4X2IYKFFHZ5mKvrQETcFXxsRObZulDaKmy//R7TPtsBg==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "domelementtype": "^3.0.0"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/fb55/domhandler?sponsor=1"
+      }
+    },
+    "node_modules/domutils": {
+      "version": "4.0.2",
+      "resolved": "https://registry.npmjs.org/domutils/-/domutils-4.0.2.tgz",
+      "integrity": "sha512-qI4JLRKnSzqFqr7hAlS5xQDusBCjKSEG4t4+7aNrIQMHBcsC2TGEhuyABJdYkgSewL57PNLYEiibY2iPKhKpaA==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "dom-serializer": "^3.0.0",
+        "domelementtype": "^3.0.0",
+        "domhandler": "^6.0.0"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/fb55/domutils?sponsor=1"
+      }
+    },
+    "node_modules/entities": {
+      "version": "8.1.0",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-8.1.0.tgz",
+      "integrity": "sha512-kxL7msIffSuh9aaFAMD7rxAIuTRMAHMeBtgHW2yUdWw732ZNh4MehkF2gdjvtdmikkaIP9bFDDJOPlsvm7avrA==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
       }
     },
     "node_modules/fsevents": {
@@ -26,6 +175,150 @@
         "node": "^8.16.0 || ^10.6.0 || >=11.0.0"
       }
     },
+    "node_modules/html-escaper": {
+      "version": "3.0.3",
+      "resolved": "https://registry.npmjs.org/html-escaper/-/html-escaper-3.0.3.tgz",
+      "integrity": "sha512-RuMffC89BOWQoY0WKGpIhn5gX3iI54O6nRA0yC124NYVtzjmFWBIiFd8M0x+ZdX0P9R4lADg1mgP8C7PxGOWuQ==",
+      "license": "MIT"
+    },
+    "node_modules/htmlparser2": {
+      "version": "10.1.0",
+      "resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-10.1.0.tgz",
+      "integrity": "sha512-VTZkM9GWRAtEpveh7MSF6SjjrpNVNNVJfFup7xTY3UpFtm67foy9HDVXneLtFVt4pMz5kZtgNcvCniNFb1hlEQ==",
+      "funding": [
+        "https://github.com/fb55/htmlparser2?sponsor=1",
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.3",
+        "domutils": "^3.2.2",
+        "entities": "^7.0.1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/dom-serializer": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-2.0.0.tgz",
+      "integrity": "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg==",
+      "license": "MIT",
+      "dependencies": {
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.2",
+        "entities": "^4.2.0"
+      },
+      "funding": {
+        "url": "https://github.com/cheeriojs/dom-serializer?sponsor=1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/dom-serializer/node_modules/entities": {
+      "version": "4.5.0",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-4.5.0.tgz",
+      "integrity": "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=0.12"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/domelementtype": {
+      "version": "2.3.0",
+      "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-2.3.0.tgz",
+      "integrity": "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ],
+      "license": "BSD-2-Clause"
+    },
+    "node_modules/htmlparser2/node_modules/domhandler": {
+      "version": "5.0.3",
+      "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-5.0.3.tgz",
+      "integrity": "sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "domelementtype": "^2.3.0"
+      },
+      "engines": {
+        "node": ">= 4"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/domhandler?sponsor=1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/domutils": {
+      "version": "3.2.2",
+      "resolved": "https://registry.npmjs.org/domutils/-/domutils-3.2.2.tgz",
+      "integrity": "sha512-6kZKyUajlDuqlHKVX1w7gyslj9MPIXzIFiz/rGu35uC1wMi+kMhQwGhl4lt9unC9Vb9INnY9Z3/ZA3+FhASLaw==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "dom-serializer": "^2.0.0",
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.3"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/domutils?sponsor=1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/entities": {
+      "version": "7.0.1",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-7.0.1.tgz",
+      "integrity": "sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=0.12"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
+    "node_modules/linkedom": {
+      "version": "0.18.13",
+      "resolved": "https://registry.npmjs.org/linkedom/-/linkedom-0.18.13.tgz",
+      "integrity": "sha512-ES/o9qotMpzpN2MHs+Iq/JcVoOj8Fa5wiQYrTdFpvAnwXL0g66XHHUc9WUMk6nAlBtGsFQ24ne+SYnvnaQ2FSw==",
+      "license": "ISC",
+      "dependencies": {
+        "css-select": "^7.0.0",
+        "cssom": "^0.5.0",
+        "html-escaper": "^3.0.3",
+        "htmlparser2": "^10.1.0",
+        "uhyphen": "^0.2.0"
+      },
+      "engines": {
+        "node": ">=16"
+      },
+      "peerDependencies": {
+        "canvas": ">= 2"
+      },
+      "peerDependenciesMeta": {
+        "canvas": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/nth-check": {
+      "version": "3.0.1",
+      "resolved": "https://registry.npmjs.org/nth-check/-/nth-check-3.0.1.tgz",
+      "integrity": "sha512-GX0gsdbGVCgnRgbeGaubfjpBXyYRWOOCVeYh08bSQvDZqxz5ndXs1OTfAt/h36G1xvI94YIspsI0sVFqAV9+RQ==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "boolbase": "^2.0.0"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/fb55/nth-check?sponsor=1"
+      }
+    },
     "node_modules/playwright": {
       "version": "1.62.1",
       "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.62.1.tgz",
@@ -55,6 +348,25 @@
       "engines": {
         "node": ">=20"
       }
+    },
+    "node_modules/turndown": {
+      "version": "7.2.4",
+      "resolved": "https://registry.npmjs.org/turndown/-/turndown-7.2.4.tgz",
+      "integrity": "sha512-I8yFsfRzmzK0WV1pNNOA4A7y4RDfFxPRxb3t+e3ui14qSGOxGtiSP6GjeX+Y6CHb7HYaFj7ECUD7VE5kQMZWGQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@mixmark-io/domino": "^2.2.0"
+      },
+      "engines": {
+        "node": ">=18",
+        "npm": ">=9"
+      }
+    },
+    "node_modules/uhyphen": {
+      "version": "0.2.0",
+      "resolved": "https://registry.npmjs.org/uhyphen/-/uhyphen-0.2.0.tgz",
+      "integrity": "sha512-qz3o9CHXmJJPGBdqzab7qAYuW8kQGKNEuoHFYrBwV6hWIMcpAmxDLXojcHfFr9US1Pe6zUswEIJIbLI610fuqA==",
+      "license": "ISC"
     }
   }
 }

package/extensions/opl-browser/package.json

@@ -1,10 +1,13 @@
 {
   "name": "opl-browser",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "description": "Chromium browser automation for pi via Playwright. A single dispatcher tool for navigation, snapshots, interaction, console/network capture, and evaluation — replaces the chrome-devtools MCP server.",
   "main": "index.js",
   "license": "ISC",
   "dependencies": {
-    "playwright": "^1.49.0"
+    "@mozilla/readability": "^0.6.0",
+    "linkedom": "^0.18.13",
+    "playwright": "^1.49.0",
+    "turndown": "^7.2.4"
   }
 }

package/extensions/opl-browser/turndown.d.ts

@@ -0,0 +1 @@
+declare module "turndown";

package/extensions/opl-simplebench/README.md

@@ -15,7 +15,7 @@ Auditable Pi model benchmark for closed-answer contracts, JSON instruction follo
 /simplebench <model> --llama-server
 /simplebench <model> --llamagputop
 /simplebench <model> --tag=<word>
-/simplebench <model> --sequence
+/simplebench <model> --sequence[=<name>]
 /simplebench --all [--no-artifact]
 /simplebench --all --test-all
 /simplebench --help
@@ -42,7 +42,7 @@ simplebench({ model: "global.openai.gpt-5.6-terra", test_all: true })
 - Six opt-in execution-backed coding tasks in disposable directories (`--coding-lite`).
 - `--test-all` runs baseline, coding-lite, and deterministic grounded research; `--research-live` adds the configured live research-artifact integration smoke test. `--all` still selects every Ollama model.
 - `--3ptest` is the explicit form of the default baseline suite (reasoning, instruction following, tool calls). It changes nothing about the run; artifacts already name the baseline suite `3ptest`.
-- `--sequence` runs the templated multi-iteration benchmark stored in `opl-simplebench.json` (`runSequence`): sequential iterations, per-entry flags and `--tag`, optional `llamaMetrics` and `pauseMs` cooldown. See "Run a templated sequence" below.
+- `--sequence[=<name>]` runs a named templated multi-iteration profile stored in `opl-simplebench.json` (`runSequence.sequences`): sequential iterations, per-entry flags and `--tag`, `llamaMetrics` and `pauseMs` cooldown with block-level defaults a profile can override. See "Run a templated sequence" below.
 - `--llama-server` (`llama_server: true`) captures configured direct llama-server `/props` and `/metrics` without changing inference routing, so it works with a LiteLLM proxy.
 - `--llamagputop` (`llamagputop: true`) captures configured llama.cpp `/stats` metadata independently of the inference provider; its served model ID is authoritative.
 - `--tag=<word>` (`tag: "<word>"`) labels a run: stored as `benchmark.tag` and prefixed onto the artifact file or bundle name, for example `simplebench-coldrun-coding-lite-<model>-...`. The tag must be a single word (letters, digits, dot, dash, underscore).
@@ -87,10 +87,10 @@ Use this in sensitive environments. The terminal summary still reports category
 ### Run a templated sequence
 
 ```text
-/simplebench --sequence
+/simplebench --sequence=<name>
 ```
 
-Repeating a warm-up protocol (first-run-after-boot coding check, then baseline, then the full suite) means re-typing the same flags every session. `--sequence` reads the `runSequence` block from `~/.pi/agent/configs/opl-simplebench.json` and runs each entry as its own iteration against the current model (or the model passed with `--sequence`):
+Repeating a warm-up protocol (first-run-after-boot coding check, then baseline, then the full suite) means re-typing the same flags every session. `--sequence` reads a named `runSequence` profile from `~/.pi/agent/configs/opl-simplebench.json` and runs each entry as its own iteration against the current model (or the model passed with `--sequence`):
 
 ```json
 {
@@ -98,22 +98,36 @@ Repeating a warm-up protocol (first-run-after-boot coding check, then baseline,
     "enabled": true,
     "llamaMetrics": true,
     "pauseMs": 5000,
-    "sequence": [
-      "--coding-lite --tag=coldest",
-      "--3ptest --tag=colder",
-      "--coding-lite --tag=semiwarm",
-      "--test-all --research-live --tag=warm"
+    "sequences": [
+      {
+        "name": "warmup",
+        "iterations": [
+          "--coding-lite --tag=coldest",
+          "--3ptest --tag=colder",
+          "--coding-lite --tag=semiwarm",
+          "--test-all --research-live --tag=warm"
+        ]
+      },
+      {
+        "name": "coding-only",
+        "llamaMetrics": false,
+        "pauseMs": 3000,
+        "iterations": ["--coding-lite --tag=coldest", "--coding-lite --tag=warmer"]
+      }
     ]
   }
 }
 ```
 
 - `enabled` gates the flag: `/simplebench --sequence` errors when it is missing or `false`. A bare `/simplebench` is unaffected.
-- Each `sequence` entry is the same flag string you would type after `/simplebench`, including its own `--tag`.
+- Profile names are single words (letters, digits, dot, dash, underscore) and must be unique. `/simplebench --sequence` without a name runs the only defined profile; with several profiles it errors and lists the available names.
+- Block-level `llamaMetrics` and `pauseMs` are defaults; a profile may override either, so a coding-only curve can skip server stats or use a different cooldown.
+- Each `iterations` entry is the same flag string you would type after `/simplebench`, including its own `--tag`.
 - `llamaMetrics: true` appends `--llama-server --llamagputop` to every entry, so local server stats are captured per iteration without repeating the flags.
 - `pauseMs` sleeps between iterations (never after the last one), including after a failed iteration, so thermal/KV-cache cooldown stays consistent across the warm-up curve.
 - Iterations run sequentially and each writes its normal artifact/bundle; a failed iteration is reported and the sequence continues. A final summary line counts completed iterations.
-- Entries containing `--all` or `--sequence` are rejected before anything runs, as are invalid configurations (empty sequence, negative `pauseMs`) and invalid per-entry tags. The outer `--tag` is ignored; each entry carries its own.
+- Entries containing `--all` or `--sequence` are rejected before anything runs, as are invalid configurations (no profiles, empty `iterations`, negative `pauseMs`) and invalid per-entry tags. The outer `--tag` is ignored; each entry carries its own.
+- The legacy flat `runSequence.sequence` array still works as an anonymous profile, so existing configs need no change. Selecting it by name is not possible; migrate to `sequences` when you need more than one protocol.
 
 ### Grounded research in `--test-all`
 

package/extensions/opl-simplebench/benchmark.ts

@@ -138,6 +138,7 @@ function makeOpenAiChatFn(baseUrl: string, apiKey?: string, thinkingMax = false)
 
     const controller = new AbortController();
     const timeoutId = setTimeout(() => controller.abort(), CONFIG.TOOL_TEST_TIMEOUT_MS);
+    const startedAt = new Date().toISOString();
     const start = Date.now();
     try {
       const res = await fetch(`${baseUrl}/chat/completions`, {
@@ -163,6 +164,8 @@ function makeOpenAiChatFn(baseUrl: string, apiKey?: string, thinkingMax = false)
         toolCalls: toolCalls && toolCalls.length > 0 ? toolCalls : undefined,
         elapsedMs,
         raw: parsed,
+        startedAt,
+        finishedAt: new Date().toISOString(),
       };
     } catch (e: any) {
       clearTimeout(timeoutId);
@@ -265,6 +268,7 @@ function makeBedrockChatFn(providerInfo: { region?: string }): ChatFn {
 
     const controller = new AbortController();
     const timeoutId = setTimeout(() => controller.abort(), CONFIG.TOOL_TEST_TIMEOUT_MS);
+    const startedAt = new Date().toISOString();
     const start = Date.now();
     try {
       const res = await fetch(`https://${host}${urlPath}`, {
@@ -284,7 +288,7 @@ function makeBedrockChatFn(providerInfo: { region?: string }): ChatFn {
       const toolCalls = blocks.filter((b: any) => b.toolUse).map((b: any) => ({
         function: { name: b.toolUse.name, arguments: b.toolUse.input ?? {} },
       }));
-      return { content, toolCalls: toolCalls.length > 0 ? toolCalls : undefined, elapsedMs, raw: parsed };
+      return { content, toolCalls: toolCalls.length > 0 ? toolCalls : undefined, elapsedMs, raw: parsed, startedAt, finishedAt: new Date().toISOString() };
     } catch (e: any) {
       clearTimeout(timeoutId);
       if (e.name === "AbortError") throw new Error(`Bedrock API timed out after ${msHuman(CONFIG.TOOL_TEST_TIMEOUT_MS)}`);
@@ -344,6 +348,7 @@ function makeOllamaToolChatFn(): ChatFn {
 
     const controller = new AbortController();
     const timeoutId = setTimeout(() => controller.abort(), CONFIG.TOOL_TEST_TIMEOUT_MS);
+    const startedAt = new Date().toISOString();
     const start = Date.now();
     try {
       const res = await fetch(`${ollamaBase()}/api/chat`, {
@@ -370,6 +375,8 @@ function makeOllamaToolChatFn(): ChatFn {
         toolCalls: toolCalls && toolCalls.length > 0 ? toolCalls : undefined,
         elapsedMs,
         raw: parsed,
+        startedAt,
+        finishedAt: new Date().toISOString(),
       };
     } catch (e: any) {
       clearTimeout(timeoutId);

package/extensions/opl-simplebench/index.ts

@@ -1,7 +1,7 @@
 import type { ExtensionAPI, AgentToolResult } from "@earendil-works/pi-coding-agent";
 import { debugLog } from "./util/debug";
 import { detectProvider } from "./util/providers";
-import { readTestConfig, TOOL_SUPPORT_CACHE_PATH, type ModelTestUserConfig } from "./util/config";
+import { readTestConfig, TOOL_SUPPORT_CACHE_PATH, type ModelTestUserConfig, type RunSequenceProfile } from "./util/config";
 import type { SimplebenchOptions } from "./types";
 import { createBenchmark } from "./benchmark";
 
@@ -13,25 +13,50 @@ export function parseCommandArgs(args: string): SimplebenchOptions {
     tag = tagToken.slice("--tag=".length);
     if (!/^[A-Za-z0-9][A-Za-z0-9._-]*$/.test(tag)) throw new Error(`--tag must be a single word (letters, digits, dot, dash, underscore): got "${tag}"`);
   }
-  return { model: tokens.find(token => !token.startsWith("--")), allModels: tokens.includes("--all"), writeArtifact: !tokens.includes("--no-artifact"), thinkingMax: tokens.includes("--thinking-max"), codingLite: tokens.includes("--coding-lite"), testAll: tokens.includes("--test-all"), researchLive: tokens.includes("--research-live"), llamaServer: tokens.includes("--llama-server"), llamagputop: tokens.includes("--llamagputop"), ...(tag ? { tag } : {}), ...(tokens.includes("--3ptest") ? { threePTest: true } : {}), ...(tokens.includes("--sequence") ? { sequence: true } : {}) };
+  const seqToken = tokens.find(token => token === "--sequence" || token.startsWith("--sequence="));
+  let sequence: boolean | string | undefined;
+  if (seqToken) {
+    if (seqToken === "--sequence") sequence = true;
+    else {
+      sequence = seqToken.slice("--sequence=".length);
+      if (!/^[A-Za-z0-9][A-Za-z0-9._-]*$/.test(sequence)) throw new Error(`--sequence= must name a single word (letters, digits, dot, dash, underscore): got "${seqToken.slice("--sequence=".length)}"`);
+    }
+  }
+  return { model: tokens.find(token => !token.startsWith("--")), allModels: tokens.includes("--all"), writeArtifact: !tokens.includes("--no-artifact"), thinkingMax: tokens.includes("--thinking-max"), codingLite: tokens.includes("--coding-lite"), testAll: tokens.includes("--test-all"), researchLive: tokens.includes("--research-live"), llamaServer: tokens.includes("--llama-server"), llamagputop: tokens.includes("--llamagputop"), ...(tag ? { tag } : {}), ...(tokens.includes("--3ptest") ? { threePTest: true } : {}), ...(sequence ? { sequence } : {}) };
 }
 
-export interface ResolvedRunSequence { runs: Array<{ entry: string; options: SimplebenchOptions }>; pauseMs: number }
+export interface ResolvedRunSequence { profile: string; runs: Array<{ entry: string; options: SimplebenchOptions }>; pauseMs: number; llamaMetrics: boolean }
 
-/** Expand the configured runSequence into per-iteration benchmark options. Throws on disabled/invalid configuration. */
-export function resolveRunSequence(userConfig: ModelTestUserConfig): ResolvedRunSequence {
+const PROFILE_NAME_RE = /^[A-Za-z0-9][A-Za-z0-9._-]*$/;
+
+/** Expand one configured runSequence profile into per-iteration benchmark options. Throws on disabled/invalid configuration. */
+export function resolveRunSequence(userConfig: ModelTestUserConfig, name?: string): ResolvedRunSequence {
   const rs = userConfig.runSequence;
   if (!rs?.enabled) throw new Error("runSequence is not enabled in opl-simplebench.json");
-  if (!Array.isArray(rs.sequence) || rs.sequence.length === 0) throw new Error("runSequence.sequence must be a non-empty array of flag strings");
-  const pauseMs = rs.pauseMs ?? 0;
-  if (typeof pauseMs !== "number" || !Number.isFinite(pauseMs) || pauseMs < 0) throw new Error(`runSequence.pauseMs must be a non-negative number: got ${JSON.stringify(rs.pauseMs)}`);
-  const runs = rs.sequence.map((entry: string) => {
+  const profiles: RunSequenceProfile[] = [];
+  if (Array.isArray(rs.sequence) && rs.sequence.length > 0) profiles.push({ name: "", iterations: rs.sequence });
+  for (const profile of rs.sequences ?? []) {
+    if (typeof profile?.name !== "string" || !PROFILE_NAME_RE.test(profile.name)) throw new Error(`runSequence profile name must be a single word (letters, digits, dot, dash, underscore): got ${JSON.stringify(profile?.name)}`);
+    if (!Array.isArray(profile.iterations) || profile.iterations.length === 0) throw new Error(`runSequence profile "${profile.name}" needs a non-empty iterations array`);
+    if (profiles.some(known => known.name === profile.name)) throw new Error(`duplicate runSequence profile name: "${profile.name}"`);
+    profiles.push(profile);
+  }
+  const label = (p: RunSequenceProfile) => p.name || "(legacy)";
+  if (profiles.length === 0) throw new Error("runSequence needs a non-empty sequence array or sequences list");
+  let chosen: RunSequenceProfile | undefined;
+  if (name) chosen = profiles.find(p => p.name === name);
+  else if (profiles.length === 1) chosen = profiles[0];
+  if (!chosen) throw new Error(name ? `unknown runSequence profile "${name}"; available: ${profiles.map(label).join(", ")}` : `--sequence needs a profile name; available: ${profiles.map(label).join(", ")}`);
+  const pauseMs = chosen.pauseMs ?? rs.pauseMs ?? 0;
+  if (typeof pauseMs !== "number" || !Number.isFinite(pauseMs) || pauseMs < 0) throw new Error(`runSequence.pauseMs must be a non-negative number: got ${JSON.stringify(chosen.pauseMs ?? rs.pauseMs)}`);
+  const llamaMetrics = (chosen.llamaMetrics ?? rs.llamaMetrics) === true;
+  const runs = chosen.iterations.map((entry: string) => {
     const tokens = String(entry).trim().split(/\s+/);
     if (tokens.includes("--all")) throw new Error(`runSequence entry cannot contain --all: "${entry}"`);
-    if (tokens.includes("--sequence")) throw new Error(`runSequence entry cannot contain --sequence: "${entry}"`);
-    return { entry: String(entry), options: parseCommandArgs(`${entry}${rs.llamaMetrics ? " --llama-server --llamagputop" : ""}`) };
+    if (tokens.some(token => token === "--sequence" || token.startsWith("--sequence="))) throw new Error(`runSequence entry cannot contain --sequence: "${entry}"`);
+    return { entry: String(entry), options: parseCommandArgs(`${entry}${llamaMetrics ? " --llama-server --llamagputop" : ""}`) };
   });
-  return { runs, pauseMs };
+  return { profile: chosen.name, runs, pauseMs, llamaMetrics };
 }
 
 export default function (pi: ExtensionAPI) {
@@ -40,7 +65,7 @@ export default function (pi: ExtensionAPI) {
 
 pi.registerCommand("simplebench", {
   description: "Benchmark a model with auditable closed-answer, instruction, and tool-use tests.",
-  detailedHelp: "\n\n🔍 Simplebench Extension\n\nThis extension tests AI models across multiple dimensions:\n• Closed-answer contract: 20 deterministic final-line answers (logic, math, spatial, commonsense)\n• Tool Usage: Ability to use available tools effectively\n• Instruction Following: How well the model follows complex JSON instructions\n• Coding Lite: Six isolated, execution-backed coding tasks\n\n📋 Usage Examples:\n  /simplebench                    # Test current model\n  /simplebench <model>           # Test a specific model\n  /simplebench --all             # Test all Ollama models\n  /simplebench <model> --3ptest  # Run the default 3ptest baseline explicitly\n  /simplebench <model> --coding-lite # Run only coding tasks\n  /simplebench <model> --test-all # Run baseline, coding, and grounded research\n  /simplebench <model> --research-live # Add live search integration smoke test\n  /simplebench --all --test-all  # Run complete suite for every Ollama model\n  /simplebench <model> --sequence # Run the configured runSequence template\n  /simplebench <model> --thinking-max # Request max reasoning\n  /simplebench <model> --llama-server # Capture configured /props and /metrics\n  /simplebench <model> --llamagputop # Capture configured llama.cpp stats\n  /simplebench <model> --tag=coldrun # Label the run: benchmark.tag plus artifact filename prefix\n  /simplebench --help            # Show this help\n  /simplebench --clear-cache     # Clear tool support cache\n\nCoding tasks run in disposable directories and never access the user repository.\n",
+  detailedHelp: "\n\n🔍 Simplebench Extension\n\nThis extension tests AI models across multiple dimensions:\n• Closed-answer contract: 20 deterministic final-line answers (logic, math, spatial, commonsense)\n• Tool Usage: Ability to use available tools effectively\n• Instruction Following: How well the model follows complex JSON instructions\n• Coding Lite: Six isolated, execution-backed coding tasks\n\n📋 Usage Examples:\n  /simplebench                    # Test current model\n  /simplebench <model>           # Test a specific model\n  /simplebench --all             # Test all Ollama models\n  /simplebench <model> --3ptest  # Run the default 3ptest baseline explicitly\n  /simplebench <model> --coding-lite # Run only coding tasks\n  /simplebench <model> --test-all # Run baseline, coding, and grounded research\n  /simplebench <model> --research-live # Add live search integration smoke test\n  /simplebench --all --test-all  # Run complete suite for every Ollama model\n  /simplebench <model> --sequence[=<name>] # Run a configured runSequence profile\n  /simplebench <model> --thinking-max # Request max reasoning\n  /simplebench <model> --llama-server # Capture configured /props and /metrics\n  /simplebench <model> --llamagputop # Capture configured llama.cpp stats\n  /simplebench <model> --tag=coldrun # Label the run: benchmark.tag plus artifact filename prefix\n  /simplebench --help            # Show this help\n  /simplebench --clear-cache     # Clear tool support cache\n\nCoding tasks run in disposable directories and never access the user repository.\n",
   getArgumentCompletions: async (prefix) => {
     try {
       const models = await getOllamaModels();
@@ -73,7 +98,7 @@ pi.registerCommand("simplebench", {
         "  /simplebench [model] --research-live - Add live-search integration smoke test\n" +
         "  /simplebench [model] --tag=<word> - Label the run (single word; added to benchmark.tag and the artifact name)\n" +
         "  /simplebench [model] --3ptest - Run the default baseline suite explicitly\n" +
-        "  /simplebench [model] --sequence - Run the templated multi-iteration sequence from opl-simplebench.json (runSequence; per-entry --tag, llamaMetrics and pauseMs supported; the outer --tag is ignored)\n" +
+        "  /simplebench [model] --sequence[=<name>] - Run a templated multi-iteration sequence profile from opl-simplebench.json (runSequence.sequences; bare --sequence needs exactly one profile; per-entry --tag, llamaMetrics and pauseMs supported, profile values override the block ones; the outer --tag is ignored)\n" +
         "  /simplebench --all --test-all - Run complete suite for all Ollama models\n" +
         "  /simplebench --clear-cache - Clear tool support cache\n",
         "info"
@@ -97,9 +122,10 @@ pi.registerCommand("simplebench", {
     }
 
     if (parsedArgs.sequence) {
+      const requested = typeof parsedArgs.sequence === "string" ? parsedArgs.sequence : undefined;
       let resolved: ResolvedRunSequence;
       try {
-        resolved = resolveRunSequence(readTestConfig());
+        resolved = resolveRunSequence(readTestConfig(), requested);
       } catch (e: any) {
         ctx.ui.notify(e?.message || String(e), "error");
         return;
@@ -109,7 +135,7 @@ pi.registerCommand("simplebench", {
         ctx.ui.notify("No model specified and no model currently selected", "error");
         return;
       }
-      ctx.ui.notify(`Running ${resolved.runs.length}-iteration sequence (${resolved.runs.map(r => r.entry).join(" | ")})...`, "info");
+      ctx.ui.notify(`Running ${resolved.runs.length}-iteration sequence${resolved.profile ? ` "${resolved.profile}"` : ""} (llamaMetrics ${resolved.llamaMetrics ? "on" : "off"}, pause ${resolved.pauseMs / 1000}s): ${resolved.runs.map(r => r.entry).join(" | ")}...`, "info");
       let completed = 0;
       for (let i = 0; i < resolved.runs.length; i++) {
         if (i > 0 && resolved.pauseMs > 0) {

package/extensions/opl-simplebench/types.ts

@@ -1,6 +1,6 @@
 import type { ServerStats } from "./llama-server";
 
-export interface SimplebenchOptions { model?: string; allModels: boolean; writeArtifact: boolean; thinkingMax?: boolean; codingLite?: boolean; testAll?: boolean; researchLive?: boolean; llamaServer?: boolean; llamagputop?: boolean; tag?: string; threePTest?: boolean; sequence?: boolean; }
+export interface SimplebenchOptions { model?: string; allModels: boolean; writeArtifact: boolean; thinkingMax?: boolean; codingLite?: boolean; testAll?: boolean; researchLive?: boolean; llamaServer?: boolean; llamagputop?: boolean; tag?: string; threePTest?: boolean; sequence?: boolean | string; }
 export interface RequestMetrics { requestCount: number; retryCount: number; wallTimeMs: number; timeToAnswerMs: number; timeToFirstTokenMs: number | null; startedAt: string | null; finishedAt: string | null; inputTokens: number | null; outputTokens: number | null; totalTokens: number | null; outputTokensPerSecond: number | null; toolCalls: Array<{ name: string; arguments?: unknown }>; }
 export interface TestRecord { id: string; kind: "reasoning" | "instructions" | "tools" | "coding" | "research-grounded" | "research-live"; category?: string; prompt: string; response: string | null; expectedAnswer?: string | string[]; extractedAnswer?: string; score: string; passed: boolean; error: string | null; metrics: RequestMetrics; coding?: { publicPassed: boolean; hiddenPassed: boolean; verifiedAfterEdit: boolean; unrelatedFiles: string[]; toolCalls: number; turns: number; efficiency?: "STRONG" | "MODERATE" | "WEAK" | "FAIL"; }; research?: { toolCalls: string[]; files: string[]; }; }
 export interface RunArtifact { schemaVersion: 1; benchmark: { name: "opl-simplebench"; suite?: "baseline" | "coding-lite" | "test-all"; tag?: string; model: string; provider: string; providerKind: string; thinking: { requested: "default" | "max"; effective: "provider-default" | "openai-reasoning-effort" | "pi-bedrock-reasoning"; level: "max" | null; modelMetadataSource: "active-context" | "scoped-model" | null; }; startedAt: string; finishedAt: string; wallTimeMs: number; artifactEnabled: boolean; }; tests: TestRecord[]; summary: Record<string, unknown> & { serverStats?: ServerStats }; }

package/extensions/opl-simplebench/util/config.ts

@@ -87,7 +87,18 @@ export interface RunSequenceConfig {
   enabled?: boolean;
   llamaMetrics?: boolean;
   pauseMs?: number;
+  /** Legacy anonymous sequence; still resolved when no `sequences` profile matches. */
   sequence?: string[];
+  /** Named sequences selectable with `/simplebench --sequence=<name>`. */
+  sequences?: RunSequenceProfile[];
+}
+
+/** One named sequence profile. `llamaMetrics` and `pauseMs` override the block-level values. */
+export interface RunSequenceProfile {
+  name: string;
+  iterations: string[];
+  llamaMetrics?: boolean;
+  pauseMs?: number;
 }
 
 /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openlines/opl-pi-sht",
-  "version": "0.1.16",
+  "version": "0.1.18",
   "description": "Pi coding-agent extension kit: token-efficient context, safe modes, fingerprinted /init, model benchmarking, web access, and browser automation.",
   "repository": {
     "type": "git",
@@ -41,7 +41,7 @@
   "type": "module",
   "scripts": {
     "test": "npm run test:opl-browser && npm run test:opl-footer && npm run test:opl-init && npm run test:opl-input && npm run test:opl-modes && npm run test:opl-questionnaire && npm run test:opl-todo && npm run test:opl-webaccess && npm run test:opl-simplebench && npm run test:opl-ctxtrim",
-    "test:opl-browser": "OPL_EXTENSION=opl-browser bun test tests/extension-smoke.test.mjs",
+    "test:opl-browser": "bun test tests/opl-browser-helpers.test.mjs && OPL_EXTENSION=opl-browser bun test tests/extension-smoke.test.mjs",
     "test:opl-footer": "bun test tests/opl-footer-helpers.test.mjs && OPL_EXTENSION=opl-footer bun test tests/extension-smoke.test.mjs",
     "test:opl-init": "bun test tests/opl-init-crawl.test.mjs && OPL_EXTENSION=opl-init bun test tests/extension-smoke.test.mjs",
     "test:opl-input": "bun test tests/opl-input-style.test.mjs && OPL_EXTENSION=opl-input bun test tests/extension-smoke.test.mjs",