@dikshanty94/webnav 0.2.0

package/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Dikshant Yadav
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/README.md

@@ -0,0 +1,283 @@
+# webnav
+
+[![CI](https://github.com/lucyfuur94/webnav-core/actions/workflows/ci.yml/badge.svg)](https://github.com/lucyfuur94/webnav-core/actions/workflows/ci.yml)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![TypeScript](https://img.shields.io/badge/TypeScript-strict-3178c6.svg)](https://www.typescriptlang.org/)
+[![PRs welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)
+![zero-LLM](https://img.shields.io/badge/runtime-zero--LLM-7c4dff.svg)
+
+**Stop your web-browsing AI agent from re-exploring the same sites every run.** Your agent maps
+a website **once** — then travels it forever with `webnav walk`: deterministic, zero-LLM,
+page-to-page autopilot that pauses only at genuine forks (what to buy, an irreversible button)
+and hands the wheel back. It's a **reusable site map, not page compression** — most token-saving
+tools shrink what the agent *reads*; webnav remembers *where things are* so it stops re-finding
+the route. webnav is the map and the mechanics; the agent keeps all the judgment.
+
+## See it
+
+A real run against saucedemo's full checkout flow (map + credentials already recorded):
+
+```console
+$ webnav walk --start www.saucedemo.com:login --goal www.saucedemo.com:checkout-overview
+{ "status": "needs-navigation",
+  "semanticStep": "open the shopping cart",
+  "question": "before \"open the shopping cart\", fire these in-page affordances: aff_addcart",
+  "snapshot": "…", "session": "walk-w-…", "browserSession": "w-…" }
+   # ^ paused at a REAL fork: webnav won't decide what you buy. The agent picks from the snapshot:
+
+$ webnav use click e54 --session w-…          # add-to-cart — the agent's one judgment call
+$ webnav walk-resume walk-w-… --ref e124      # continue; e124 = the icon-only cart badge
+{ "status": "done", "cost": { "playwright_calls": 12 } }
+```
+
+**4 agent-visible CLI calls**, login → inventory → cart → checkout form (**auto-filled from
+locally-stored creds** — never in the map) → overview. 12 browser actions underneath, zero
+agent tokens spent on navigation.
+
+In our [navigation benchmark](bench/results/2026-06-13-nav-v2.md) (both arms on Haiku, the same
+browser underneath), on a deep multi-step route **`walk` used ~3× fewer agent steps than an agent
+ad-hoc-driving the raw browser — median 6 calls vs 18 — and reached the goal more reliably (3/3 vs
+2/3).** Honest caveat, also in that file: the win shows up on *deep, reliably-walked* routes; on
+shallow 1–2-hop routes, or when the agent falls back to manual driving, the two tie. webnav helps
+most exactly where ad-hoc driving hurts most — the long, repeated journeys.
+
+## Drive a tab from a side panel (Chrome extension)
+
+There's also a Chrome extension in [`webnav-extension/`](webnav-extension/) — a docked side
+panel where you type a goal and watch the agent drive your **active tab** (read / click / type /
+scroll, via `chrome.debugger`/CDP), on your own Claude Code subscription. It **recalls first**
+(`list_routes` → `check_route`) so a site you've mapped is replayed, not re-explored — and every
+run is recorded back into the map, so the *next* time is the cheap deterministic `walk`.
+
+<img src="docs/media/extension-sidebar-light.png#gh-light-mode-only" alt="webnav agent side panel — a goal, recall-first action trail, and a streamed reply" width="420">
+<img src="docs/media/extension-sidebar-dark.png#gh-dark-mode-only" alt="webnav agent side panel — a goal, recall-first action trail, and a streamed reply" width="420">
+
+- **Ask** (approve a plan first) or **Act** (run on its own); irreversible steps (pay / place
+  order / delete) always pause for you.
+- **Watch every step** — narration + the tool trail render live; a cursor glides to each action.
+- **Take over** any time, drive by hand, hand back.
+
+**Try it** (needs the local server for the zero-LLM navigation + recording):
+
+```console
+cd webnav-extension && npm i && npm run build   # emits the *.js next to *.ts
+webnav dev agent-serve --port 7779              # prints a token — paste it into the panel
+```
+
+Then `chrome://extensions` → Developer mode → **Load unpacked** → pick `webnav-extension/`,
+open the panel (toolbar icon or **⌘/Ctrl-E**), paste the token, and type a goal. Runs show up on
+the dashboard tagged **Extension**. Full walkthrough: [`webnav-extension/README.md`](webnav-extension/README.md).
+
+## Why
+
+Web agents re-discover the same websites every single day, paying the same token bill every
+time: snapshot → reason → click → snapshot. For sites you (or your agents) use repeatedly —
+internal tools, automation testing, back-office workflows — that navigation should be
+**remembered, not re-reasoned**. webnav stores the durable *intent* of each step, replays it
+deterministically, self-heals when the site drifts, and **never** auto-fires an irreversible
+action: commit points always pause for the agent (or you) to decide.
+
+## Quickstart (≈60 seconds to a working walk)
+
+```bash
+npm install && npm link     # Node 18/20/22; installs `webnav` on PATH (runs src via tsx — NO build step)
+                            # also needs `playwright-cli` on PATH
+
+# walk a site WITHOUT learning it — import a map someone already made:
+webnav dev import-map mappacks/orangehrm.mappack.json     # 17 states, in-page repertoire + domain shadow
+webnav dev creds set opensource-demo.orangehrmlive.com username=Admin password=admin123   # YOUR creds, local only
+webnav walk --start opensource-demo.orangehrmlive.com:auth-login \
+            --goal  opensource-demo.orangehrmlive.com:recruitment-viewcandidates --headless
+#  → webnav drives login → dashboard → … → the Candidates list, pausing only at genuine forks.
+
+webnav dev list             # the sites you have maps for (saucedemo ships seeded by default)
+```
+
+Three packs ship in [`mappacks/`](mappacks/) (saucedemo · OrangeHRM · automationexercise) — skeleton
+only, never credentials. To map **your own** site, hand an agent the prompt in
+[`docs/LEARNING-A-SITE.md`](docs/LEARNING-A-SITE.md). Dev/contributor commands:
+
+```bash
+webnav --help               # the tool menu (a peer of playwright-cli)
+npm test                    # unit tests (+ gated browser e2e)
+npm run build               # tsc -> dist/ (only for the published build; the CLI runs src directly)
+```
+
+**Using it from an MCP client (Claude Desktop/Code, etc.)** — webnav serves every verb as an MCP
+tool over stdio, so your agent gets `walk`/`use`/`search`/… natively, no shelling out. One line:
+
+```json
+{ "mcpServers": { "webnav": { "command": "webnav", "args": ["mcp"] } } }
+```
+
+## How the map grows (start here if you're new)
+
+webnav is a **map** — and a fresh install is **not** blank, but it is small. Here's
+honestly what you get and how it grows, so there are no surprises:
+
+- **What ships, out of the box.** The first time you run any verb, webnav seeds a shared
+  map at **`~/.webnav/webnav.db`** (per-user, shared across every terminal/folder on the
+  machine — *not* a per-directory file). It comes pre-seeded with **one** worked example:
+  **saucedemo.com** — a full login→browse→cart→checkout `walk` map. This works immediately:
+  ```bash
+  webnav walk --start www.saucedemo.com:login \
+              --goal www.saucedemo.com:checkout-complete      # saucedemo, seeded
+  ```
+  Nothing else is seeded — webnav is a blank-slate map tool, and saucedemo is the single
+  example that proves it works. **You record your own sites** (see below); that's the
+  product. This fits any flow you repeat against the same site: automation testing,
+  internal tools, back-office workflows, recurring agent tasks. (An earlier GitHub-recall
+  + internet-graph engine — the v1 proof-of-engine — was removed from the tree 2026-06-13;
+  it lives in git history if that surface ever returns.)
+- **The map persists and self-heals.** It's saved to `~/.webnav/webnav.db` and reused on
+  every run — you do **not** rebuild it each time. When a remembered step drifts (a renamed
+  or moved element), a `walk` escalates once for the agent to pick the element, then **writes
+  the fix back** so the next run resolves it deterministically (principle #3). Routes you use
+  stay fresh. Credentials for login-gated sites live **outside** the
+  map, locally, at `~/.webnav/credentials.json` (chmod 600) — never in the DB, never shared.
+- **Mapping a NEW site — hand your AGENT the learn prompt.** webnav is built for agents, so you
+  don't map by hand: you give an agent (even a cheap one — we use Haiku) the reusable prompt in
+  **[`docs/LEARNING-A-SITE.md`](docs/LEARNING-A-SITE.md)** and let it run autonomously. It drives the
+  site once through webnav's `use` primitives while recording, then `dev graph-analyse --draft` folds
+  that into a SELF-VERIFIED map (absolute URLs, unique element fingerprints, the in-page affordance
+  repertoire, the declared domain shadow) which it persists with `dev graph-edit`. No hand-authoring
+  of fingerprints or URLs. (That prompt learned the seeded OrangeHRM map — login + 11 modules,
+  exercised — in a single one-shot run.) Re-learn cleanly with `dev node-clear`.
+- **Or skip learning — import a map pack someone already made.** A map travels as a pack, so only the
+  first person learns a site. `webnav dev import-map <pack.json>` loads a site's skeleton; set your own
+  login with `dev creds set` (packs are skeleton-only, never carry credentials). Two packs ship in
+  **[`mappacks/`](mappacks/)** (saucedemo, OrangeHRM); `dev export-map <site>` makes your own to share.
+- **Or record a site by browsing it yourself.** No agent needed: run `webnav dev record-live
+  --session S --url <site>` — it opens a headed browser at that URL, and you click through the
+  flow naturally. Every action you take is captured (real playwright a11y snapshots, never typed
+  values — only which field changed) into the same session store the agent-record path uses. Stop
+  with Ctrl-C or `webnav dev record-stop --session S`, then it's the same `dev graph-analyse
+  <session> --draft` → `graph-edit` → `walk` pipeline.
+- **Or drive + record from the Chrome extension** — the [side panel](#drive-a-tab-from-a-side-panel-chrome-extension)
+  above: give the agent a goal, it drives your active tab (recalling known routes first), and the
+  run is captured back into the map. (An earlier extension *capture-only* path that approximated the
+  a11y tree from the raw DOM is retired — it broke on SPAs; the current extension captures via real
+  CDP accessibility instead. `dev ingest` still exists as that legacy receiver.)
+- **Inspect what you have** anytime: `webnav dev dashboard` (a localhost operator UI). Its
+  **Sessions** tab lists every recorded run — tagged by source (**Extension** / **Agent** /
+  **Manual**), with a filter, step counts, and a Verified badge — plus record-by-clicking + replay:
+
+  <img src="docs/media/dashboard-sessions-light.png#gh-light-mode-only" alt="webnav dashboard — Sessions tab with Extension/Agent/Manual source tags and a source filter" width="820">
+  <img src="docs/media/dashboard-sessions-dark.png#gh-dark-mode-only" alt="webnav dashboard — Sessions tab with Extension/Agent/Manual source tags and a source filter" width="820">
+
+  Or the text views `dev outline <site>` / `dev mermaid <site>`.
+
+**TL;DR:** out of the box you can `walk` saucedemo; everything else you map yourself. Same
+machine + a mapped site → instant, cached, self-healing. A brand-new site → you (or your
+agent) record it once first.
+
+## Verbs
+
+```
+# Travel a map you've built (the core win: deterministic, low-token replay)
+webnav walk --start <state> --goal <state>   autopilot a multi-step route; pauses at genuine forks
+webnav walk-resume <session> --ref|--classify   answer a paused walk's fork and continue
+webnav creds set <site> key=value...         store login/form creds locally (~/.webnav, chmod 600)
+
+# Drive a live browser one step at a time (explore/build; each step recordable)
+webnav use navigate <url> --session S        open a URL (records a landing if S is recording)
+webnav use snapshot --session S              read the page + element refs (never records)
+webnav use click <ref> / use type <ref> <t>  act on a ref; records the before/after effect
+webnav read <url> [--raw]                    open a URL -> distilled content
+webnav search "<query>" [--top N]            open-web search -> extracted evidence
+webnav eval <url> "<js>" | network <url>     targeted JS extraction | the page's API calls
+
+# Author a site's map (the record -> analyse -> edit flow)
+webnav dev record-start / record-stop        bracket a mapping session
+webnav dev record-live --session S --url U   headed browser; click through it yourself, webnav records
+webnav dev agent-serve [--port 7779]         local server the Chrome extension drives (SSE + CDP); records each run
+webnav dev ingest [--port 7778]              legacy receiver for the retired DOM-capture extension path
+webnav dev graph-analyse --session S [--draft]  mechanical structure from what you recorded
+                                             (--draft = a self-verified, ready-to-edit graph spec)
+webnav dev graph-edit --node <id> --graph J  write the validated graph
+webnav dev effects --session S               the RAW recorded before/after snapshots
+webnav dev outline <site> | mermaid <site>   completeness check | renderable diagram
+webnav dev graph-show --node <id>            a site's stored states + edges (JSON)
+webnav dev export-map <site>                 a site's map pack as JSON (skeleton only, no creds)
+webnav dev dashboard [--port N]              local operator UI: sites + JSON map + credentials
+webnav dev list                              the sites you have maps for + state counts
+webnav dev node-clear / node-rm --node <id>  empty a site's map (re-learn) / delete it entirely
+webnav dev node-add / edge-add / capture     teach + inspect helpers
+```
+`webnav <verb> --help` for details. Output is JSON on stdout; exit 0 ok / 2 error / 3 empty.
+
+### MCP server
+
+`webnav mcp` serves every verb as an MCP tool over stdio — point an MCP client at it and
+agents get the verbs natively (no shelling out). Tools are generated from the same command
+registry as `--help`, and every call runs the real CLI, so the two surfaces can't drift:
+
+```json
+{ "mcpServers": { "webnav": { "command": "webnav", "args": ["mcp"] } } }
+```
+
+Consumer verbs can also be invoked canonically as `webnav use <verb> ...` and map-authoring verbs as `webnav dev <verb> ...`; bare consumer verbs (e.g. `webnav read ...`) still work too.
+
+### Inspect a site's map
+The map is for the calling AGENT (walk), not a human dashboard. To inspect
+what's captured, use the text views — no UI:
+```bash
+webnav dev outline www.saucedemo.com    # top-to-bottom states + affordances + completeness cues
+webnav dev mermaid www.saucedemo.com     # paste into GitHub/mermaid.live to render
+webnav dev graph-show --node <id>        # raw JSON
+```
+
+## Architecture (one CLI, three components, ZERO LLM)
+
+- **Explorer** — reads a site's declared structure (observe-first), folds a recording into a
+  self-verified map draft (states, typed affordances, the declared domain shadow), recognizes states.
+- **MapStore** — SQLite persistence: states (+ affordances + declared shadow), projected edges, the
+  site-node index, and record sessions.
+- **Router** — walks a route, replays it (cached selector → deterministic fingerprint re-resolve),
+  self-heals, returns evidence OR a `needs-navigation`/`needs-classification` "your move" response for
+  the agent. Never judges, never calls an LLM.
+
+## Source map (`src/`)
+
+```
+cli.ts, cli-spec.ts, cli-help.ts     CLI: parsing, command registry, help rendering
+protocol.ts, contract.ts             walk response types · published @dikshanty94/webnav types
+paths.ts, creds.ts, hosted.ts        ~/.webnav paths · local credential store · remote-map client
+mcp/       server.ts                 `webnav mcp`: every verb as an MCP tool (generated from cli-spec)
+mapstore/  types.ts, store.ts, record.ts, schema.sql   SQLite persistence (states+affordances+shadow, edges, nodes, node_edges, record sessions)
+playwright/ adapter.ts, snapshot.ts, capture.ts, fingerprint.ts, sessions.ts, throttle.ts   playwright-cli child-process · a11y snapshot parser · element fingerprints · session guardrails
+explorer/  analyse.ts, diff.ts, draft.ts, shadow.ts, fingerprint.ts, fingerprint-page.ts   analyse a recording → self-verified draft (affordances + declared domain shadow) + state recognition
+router/    resolve.ts, replay.ts, path.ts, walk.ts, walk-live.ts, walk-session.ts   deterministic resolve/replay + interactive multi-step walk + pathfinding
+           readiness.ts, extract.ts, extract-content.ts, tokens.ts, browse.ts, read.ts   bot-wall detection · signal/content extraction · token-savings · page reading
+           search.ts, search-providers.ts, search-live.ts                 multi-provider open-web search
+           catalog.ts                                                     dev list (the map index)
+graph/     seed.ts, teach.ts, edit.ts, show.ts, coverage.ts               map authoring + inspection (saucedemo seed, graph-edit, graph-show, outline/mermaid)
+dashboard/ server.ts, shell.ts                                            `webnav dev dashboard` local operator UI
+```
+Tests mirror this under `tests/`. The live e2e walk tests are gated behind `WEBNAV_LIVE=1`.
+
+## Principles (full list in CLAUDE.md)
+
+1. Observe first, traverse rarely. 2. Never traverse a declared commit point. 3. Store durable
+semantic routes; cache selectors. 4. Usage-learned weights are a hosted-service concern. 5. The map
+surfaces evidence; the **agent** judges. **5a. ZERO LLM in webnav** — all reasoning offloaded to
+the calling agent via a call-and-response protocol. 6. The map is a use-case-independent
+navigation skeleton; goals declare signal interests. **Never evade bot-walls** — detect + escalate.
+
+## Status
+
+All current work is merged to `main`, tests green. See **`docs/STATUS.md`** for the live
+checklist, pending work, and known limitations; **`CLAUDE.md`** holds the settled design,
+mental model, and principles. Design docs: `docs/superpowers/specs/`.
+
+## Contributing
+
+PRs welcome — see [`CONTRIBUTING.md`](CONTRIBUTING.md) (the settled principles, dev setup, and how
+to contribute a **site map** — the highest-leverage contribution). Report security issues privately
+per [`SECURITY.md`](SECURITY.md). Be excellent to each other: [`CODE_OF_CONDUCT.md`](CODE_OF_CONDUCT.md).
+
+## License
+
+[Apache License 2.0](LICENSE). Free to use, modify, and redistribute (including commercially)
+**with attribution**: retain the copyright notice and the [`NOTICE`](NOTICE) file. Includes an
+explicit patent grant. Copyright 2026 Dikshant Yadav.

package/bin/webnav

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+# webnav launcher — runs the TypeScript CLI directly via the project's local tsx,
+# so `webnav` works on PATH with NO build step (always runs current src/).
+# Resolve the repo root from this script's location (bin/ is at the repo root),
+# following symlinks (npm link puts a symlink on PATH).
+SOURCE="${BASH_SOURCE[0]}"
+while [ -L "$SOURCE" ]; do
+  DIR="$(cd -P "$(dirname "$SOURCE")" >/dev/null 2>&1 && pwd)"
+  SOURCE="$(readlink "$SOURCE")"
+  [[ $SOURCE != /* ]] && SOURCE="$DIR/$SOURCE"
+done
+ROOT="$(cd -P "$(dirname "$SOURCE")/.." >/dev/null 2>&1 && pwd)"
+# In the repo: run current src/ via tsx (no build step). In the published
+# package (no src/, only dist/): run the compiled CLI.
+if [ -f "$ROOT/src/cli.ts" ] && [ -x "$ROOT/node_modules/.bin/tsx" ]; then
+  exec "$ROOT/node_modules/.bin/tsx" "$ROOT/src/cli.ts" "$@"
+fi
+exec node "$ROOT/dist/cli.js" "$@"

package/dist/agent/loop.d.ts

@@ -0,0 +1,59 @@
+import { z } from 'zod';
+import type { MapStore } from '../mapstore/store.js';
+import type { State } from '../mapstore/types.js';
+import type { WalkBrowser } from '../router/walk.js';
+import type { AgentEvent } from './server.js';
+export interface ToolDef {
+    name: string;
+    description: string;
+    shape: z.ZodRawShape;
+    handler: (args: Record<string, unknown>, extra: unknown) => Promise<{
+        content: Array<{
+            type: 'text';
+            text: string;
+        }>;
+    }>;
+}
+export type QueryFn = (params: {
+    prompt: string;
+    tools: ToolDef[];
+    mode: 'ask' | 'act';
+    model?: string;
+    resume?: string;
+    emit: (e: AgentEvent) => void;
+    signal?: AbortSignal;
+}) => AsyncIterable<unknown>;
+export interface RunAgentGoalArgs {
+    goal: string;
+    sessionId: string;
+    mode: 'ask' | 'act';
+    model?: string;
+    browser: WalkBrowser;
+    store: MapStore;
+    states: State[];
+    emit: (e: AgentEvent) => void;
+    query?: QueryFn;
+    signal?: AbortSignal;
+    resumeSessionId?: string;
+    onSdkSession?: (sdkSessionId: string) => void;
+    awaitApproval?: () => Promise<boolean>;
+}
+/**
+ * Run one agent goal. Streams SDK narration back as AgentEvents:
+ *  - assistant text  -> { type: 'turn', text }
+ *  - tool-use blocks -> { type: 'narrate', label } (display-only; the REAL CDP `action`
+ *                       events come from the channel in server.ts, never from here)
+ *  - final result    -> { type: 'done', summary }
+ *  - any throw        -> { type: 'error', message }
+ *
+ * Ask/Auto/Act gate semantics (crit #3/#4 — these three are OBSERVABLY different):
+ *  - ACT:  no confirmations. Drives freely. (Commit points are still protected by
+ *          walkRoute's needs-classification — never auto-fired.)
+ *  - AUTO: drives freely EXCEPT it pauses for approval before a goto to a NEW ORIGIN
+ *          (cross-site navigation = the cheap "meaningful action" signal). Gate lives in
+ *          the goto tool handler (buildTools). Same-origin driving is never gated.
+ *  - ASK:  emit the plan, then BLOCK the whole run on awaitApproval() BEFORE the query's
+ *          first driving tool can run. Approve → run. Deny → emit a "denied" done and
+ *          return without ever starting the query (nothing drives).
+ */
+export declare function runAgentGoal(args: RunAgentGoalArgs): Promise<void>;