@mmerterden/multi-agent-pipeline 20.18.0 → 20.20.0

package/CHANGELOG.md

@@ -16,6 +16,31 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ## [Unreleased]
 
+## [20.20.0] - 2026-10-12
+
+### Added
+
+- The cross-CLI contract lists the multi-agent-toolkit 3.20.0 minimums: `expect_aria` and `web_assert_aria`, the web state tools (`web_route`, `web_network_state`, `web_clock`, `web_dialog`, `web_upload`, `web_drag`, `web_hover`, `web_fill_form`, `web_find`, `web_generate_locator`, `web_trace`), `web_scrape` with `web_crawl` / `web_map` sitemap and path scoping, and the `research_ask` modes, filters and follow-up threads.
+- `e2e-testing` covers error, empty, slow and offline web states with the toolkit's routing, offline, clock and dialog tools, `web_find` and locator objects, and `web_generate_locator` for a stable locator in a saved step or a generated test. Exploratory testing reaches the same states on purpose.
+- `web-testing` shows `toMatchAriaSnapshot`, `page.route`, `context.setOffline` and `page.clock` for a project's own Playwright tests.
+- `signal-community` uses the research modes, recency, domain and academic filters, arXiv and `fetch_content`, and treats a result whose untrusted fence carries injection flags as evidence to quote, never as an instruction.
+- Phase 1 reads a load-bearing `generic-doc` link through the toolkit's `web_scrape` when the server is registered, else WebFetch.
+- `/multi-agent:refactor` band E runs its research axes through the toolkit and watches `microsoft/playwright-mcp` and `firecrawl/firecrawl-mcp-server`, with a license check before any peer code is read.
+
+### Fixed
+
+- Unattended runs: the guard checks every entry of a `paths` list (`web_upload`) against the path rules instead of only single path arguments, and host-checks `web_scrape` and `web_map` URLs like `web_goto`.
+
+### Changed
+
+- The ecosystem doc and facts count the toolkit from its 3.20.0 `tools/list`: 189 tools in 19 categories.
+
+## [20.19.0] - 2026-10-09
+
+### Changed
+
+- `/multi-agent:update` ends with a note of what the update brought, in the user's language: every release between the installed and the new version (not only the last one, and not cut at 40 lines), grouped as new, fixed, changed and removed, plus each stack plugin the refresh moved and what its releases added. The note is written from `release-notes.mjs`, which reads the new release's CHANGELOG and each updated plugin's CHANGELOG and never fails the update; internal-only entries are left out and nothing is added that the CHANGELOGs do not say.
+
 ## [20.18.0] - 2026-10-09
 
 ### Added

package/README.md

@@ -443,7 +443,7 @@ Installing the pipeline is not only useful when you run it. Open an ordinary ses
 
 - **Services you already onboarded.** The token `setup` mapped is readable now - resolve the logical name through `credential-store.sh` and fetch the issue, the page, the log. **Reads are ordinary work; writes are not.** Posting a Jira comment, editing an issue or opening a PR goes through the pipeline commands, because the rules that make those safe (never auto-close, `Ref:` not `Closes:`, humanizer on outward prose) live there.
 - **The stack skills `/multi-agent:stack` enabled for the repo.** Each toolkit's own `index` skill routes; the pipeline keeps no copy of that table.
-- **The `multi-agent-toolkit` MCP.** 80+ tools for a running app - screen state, crash logs, design comparison, store pre-submission.
+- **The `multi-agent-toolkit` MCP.** 180+ tools for a running app - screen state, crash logs, design comparison, store pre-submission, web scraping and browser test states.
 
 Uninstall preserves this layer: the tokens, the reader that opens them, the mapping that names them, and the MCP registration. Removing the pipeline should not cost you the credentials you onboarded through it.
 

package/README.tr.md

@@ -443,7 +443,7 @@ Pipeline'ı kurmak yalnız onu çalıştırdığında işe yaramıyor. Sıradan
 
 - **Zaten onboard ettiğin servisler.** `setup`'ın eşlediği token okunabilir durumda - mantıksal adı `credential-store.sh` ile çöz, issue'yu, sayfayı, logu getir. **Okuma sıradan iş, yazma değil.** Jira yorumu, issue düzenleme ve PR açma pipeline komutlarından geçer, çünkü onları güvenli kılan kurallar (issue asla otomatik kapanmaz, `Closes:` değil `Ref:`, dışa dönük metinde humanizer) orada yaşıyor.
 - **`/multi-agent:stack`'in bu repo için açtığı stack skilleri.** Yönlendirmeyi her toolkit'in kendi `index` skill'i yapar; pipeline o tablonun kopyasını tutmaz.
-- **`multi-agent-toolkit` MCP.** Çalışan uygulama için 80+ araç - ekran durumu, crash logu, tasarım karşılaştırma, store ön-kontrolü.
+- **`multi-agent-toolkit` MCP.** Çalışan uygulama için 180+ araç - ekran durumu, crash logu, tasarım karşılaştırma, store ön-kontrolü, web kazıma ve tarayıcı test durumları.
 
 Uninstall bu katmanı korur: token'lar, onları açan okuyucu, adlarını tutan eşleme ve MCP kaydı. Pipeline'ı kaldırmak, onun üzerinden onboard ettiğin credential'ları kaybetmek anlamına gelmemeli.
 

package/docs/ecosystem.md

@@ -7,7 +7,7 @@ separately, wired together at install time and at run time:
 |---|---|---|
 | **`multi-agent-pipeline`** (this repo) | Orchestration: the 6-phase flow, the 64 slash commands, quality gates, review/triage, cross-CLI parity | npm package (`@mmerterden/multi-agent-pipeline`), installs itself onto Claude Code / Copilot CLI / Codex CLI |
 | **`multi-agent-plugins`** | Stack knowledge: per-platform component/lifecycle skills (iOS, Android, Frontend, Backend) + shared knowledge | Claude Code marketplace, 6 independently-versioned plugins |
-| **`multi-agent-toolkit-mcp`** | The pipeline's hands on devices and browsers: 118 MCP tools across 14 categories (simulator/emulator control, memory, crash diagnostics, accessibility audit, store compliance, web automation, Figma-vs-mock design audit, code intelligence, wallet passes, an agent-DSL batch runner, a full-text context index, provider-backed research, video key frames, offline security scoring) | npm package, registered as a standard stdio MCP server on every host |
+| **`multi-agent-toolkit-mcp`** | The pipeline's hands on devices and browsers: 189 MCP tools across 19 categories (simulator/emulator control, end-to-end locators and assertions, memory, crash diagnostics, accessibility audit, store compliance, web automation and scraping, Figma-vs-mock design audit, code intelligence, wallet passes, an agent-DSL batch runner, a full-text context index with text-to-image rendering, provider-backed research, video key frames, offline security scoring, travel document fixtures, a voice channel, App Store Connect and Play Console APIs, virtual iPhones) | npm package, registered as a standard stdio MCP server on every host |
 
 None of the three depends on the others at the code level. They compose through two
 narrow contracts: the **Skill tool** (pipeline → plugin, at Phase 2) and the **MCP
@@ -234,32 +234,37 @@ Detail: [`unattended-security.md`](../pipeline/multi-agent-refs/features/unatten
 
 ### multi-agent-toolkit-mcp's tools, by category
 
-118 tools in 14 categories, counted from the server's own `tools/list` response
-at toolkit 3.14.0 rather than from a README. Three families are defined in
+189 tools in 19 categories, counted from the server's own `tools/list` response
+at toolkit 3.20.0 rather than from a README. Three families are defined in
 modules the main file only spreads in, so a count taken from the source reads
 low; the response is the only place the whole surface appears at once.
 
 The families can be narrowed per host: `MCP_TOOLKIT_CAPS` serves only the named
-ones, and unset serves all 118. A frontend repo that sets `web,code,context`
-sees 29 tools instead of 118, which matters because every registered server's
+ones, and unset serves all 189. A frontend repo that sets `web,code,context`
+sees 47 tools instead of 189, which matters because every registered server's
 tool list is charged against the context window on every turn.
 
 | Category | Tools | Primary pipeline consumers |
 |---|---|---|
 | Device Control | 59 | `/multi-agent:test`, `test-dark-mode`, `test-accessibility`, `test-dynamic-type`, `test-screenshots`, `manual-test`, `design-check` |
+| End-to-end Testing | 5 (`ui_locate`, `ios_tap_element`, `ios_type_element`, `android_tap_element`, `android_type_element`) | `/multi-agent:test`, `/multi-agent:bug-bash`, the `e2e-testing` skill; with the `expect_*` steps of `agent_run_steps` |
 | Memory | 2 (`ios_leaks`, `android_meminfo`) | none yet; available outside the pipeline |
 | Crash Diagnostics | 2 (`ios_list_crashes`, `android_list_crashes`) | `/multi-agent:test` full scenario (end-of-run crash sweep), outside-the-pipeline sessions |
 | Accessibility Audit | 3 (`ios_accessibility_audit`, `android_accessibility_audit`, `ios_accessibility_audit_deep`) | `/multi-agent:test` accessibility scenario, `test-accessibility` |
 | Store Compliance | 5 | `store-ready`, `testflight-validation`, `apple-archive-compliance` skill, Phase 3 Security Auditor |
-| Web Automation | 18 | frontend-stack UI testing (via `test`); snapshot `ref` targeting, console/network capture, readable extraction and a bounded same-origin crawl |
+| Web Automation | 35 | frontend-stack UI testing (via `test`) and the `e2e-testing` skill: snapshot `ref` targeting and `web_find`, console/network capture with request detail, request mocking, offline, clock, dialogs, uploads, traces, ARIA assertions; `web_scrape` (formats, cache, change tracking) for Phase 1 `generic-doc` links; sitemap-aware `web_map` and `web_crawl` with `llms.txt` |
 | Design Audit | 7 | `design-check` (mock-mode vs Figma conformance, component variants) |
 | Autonomous Agent DSL | 2 (`agent_run_steps`, `agent_query_output`) | any skill that needs a scripted multi-step device flow in one round trip |
 | Code Intelligence | 8 (`code_definition`, `code_references`, `code_hover`, `code_diagnostics`, `code_document_symbols`, `code_workspace_symbols`, `code_index_status`, `code_server_reset`) | `/multi-agent:refactor`, Phase 3 reviewers needing a real symbol graph rather than grep |
 | Wallet Passes | 4 (`pass_build`, `pass_validate`, `pass_inspect`, `pass_certificates`) | pass-kit work outside the pipeline; no pipeline phase consumes them |
-| Context Index | 3 (`context_index`, `context_search`, `context_get`) | any skill holding an offloaded payload too large to read; ranks passages instead of grepping lines |
-| Research | 2 (`research_search`, `research_ask`) | closes the parity exemption that had web search outside the MCP channel |
+| Context Index | 4 (`context_index`, `context_search`, `context_get`, `context_render`) | any skill holding an offloaded payload too large to read; ranks passages instead of grepping lines. `context_render` pages long text into images and reports whether that is cheaper than the text |
+| Research | 2 (`research_search`, `research_ask`) | closes the parity exemption that had web search outside the MCP channel; `signal-community` and `/multi-agent:refactor` band E (modes, recency and academic filters, follow-up threads, arXiv). Denied in unattended runs and autonomous research |
 | Media | 1 (`media_frames`) | Phase 2 visual evidence: turns a screen recording into frames a reviewer and a model can both look at |
 | Security | 2 (`security_cvss_score`, `security_dep_inventory`) | the Phase 3 Step 2.7 security audit (`security-auditor`) and `/multi-agent:security-review`; offline, no egress |
+| Travel Document Fixtures | 2 (`document_mrz_build`, `document_generate`) | the `e2e-testing` skill's MRZ and document-scan recipes |
+| Voice | 6 | none in the pipeline; a local voice host outside it |
+| Store APIs | 30 | `/multi-agent:store-ready`, `/multi-agent:setup` credential onboarding |
+| Virtual iPhone | 10 | none in the pipeline yet; available outside it |
 
 ---
 

package/docs/facts.json

@@ -1,7 +1,7 @@
 {
   "$comment": "Generated by pipeline/scripts/gen-facts.mjs. Do not hand-edit: the site reads this, and a number edited here instead of at its source is the drift this file removes.",
-  "generatedAt": "2026-10-09",
-  "version": "20.18.0",
+  "generatedAt": "2026-10-11",
+  "version": "20.20.0",
   "phaseSchema": 2,
   "phases": [
     {
@@ -40,18 +40,18 @@
   "skillCountAll": 228,
   "agentCount": 10,
   "hosts": ["Claude Code", "Codex CLI", "Copilot CLI"],
-  "toolCount": 174,
+  "toolCount": 189,
   "toolCategories": {
     "ios": 42,
+    "web": 35,
     "android": 33,
     "store": 30,
-    "web": 21,
     "vphone": 10,
     "code": 8,
     "design": 7,
     "voice": 6,
+    "context": 4,
     "pass": 4,
-    "context": 3,
     "agent": 2,
     "document": 2,
     "research": 2,
@@ -60,5 +60,5 @@
     "ui": 1
   },
   "pluginSkillCount": 252,
-  "toolkitVersion": "3.19.1"
+  "toolkitVersion": "3.20.0"
 }

package/docs/features.md

@@ -54,7 +54,7 @@ The install is not only useful while `/multi-agent` is running. `rules/outside-t
 
 - **Onboarded service credentials.** Resolve the logical name through `credential-store.sh` and read the issue, page or log. Writes route through the pipeline commands, which carry the rules that make them safe - issues are never auto-closed, PR bodies use `Ref:`, outward prose goes through the humanizer.
 - **The stack skills enabled for this repo.** Each toolkit's own `index` skill routes. The pipeline reads the effective `enabledPlugins` rather than keeping a stack table, so a seventh toolkit needs no code change.
-- **The `multi-agent-toolkit` MCP.** 118 tools for a running app.
+- **The `multi-agent-toolkit` MCP.** 180+ tools for a running app.
 
 Uninstall preserves the whole layer - tokens, the reader that opens them, the mapping that names them, the MCP registration. It is 1.5 kB of always-loaded text; the detail lives in a ref that loads on demand, and a gate keeps both under a ceiling because every byte there is paid by every session.