specweave 3.1.10 → 3.1.12

package/dist/dashboard/index.html

@@ -5,7 +5,7 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>SpecWeave Dashboard</title>
     <link rel="icon" type="image/svg+xml" href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' width='64' height='64' viewBox='0 0 64 64'%3E%3Ctitle%3ESpecWithCode%3C/title%3E%3Crect width='64' height='64' rx='14.4' fill='%235B6CFF'/%3E%3Csvg x='12.8' y='12.8' width='38.4' height='38.4' viewBox='10 10 80 80'%3E%3Cpath fill='%23FFFFFF' d='M29 10H60L78 28V83Q78 90 71 90H29Q22 90 22 83V17Q22 10 29 10Z'/%3E%3Cpath fill='%23AAACB2' d='M60 10V24Q60 28 64 28H78Z'/%3E%3Cpath fill='%230B1020' d='M38.703 41.051L50.703 52.051A4 4 0 0 1 50.703 57.949L38.703 68.949A4 4 0 0 1 33.297 63.051L42.080 55L33.297 46.949A4 4 0 0 1 38.703 41.051ZM54 62H64A4 4 0 0 1 64 70H54A4 4 0 0 1 54 62Z'/%3E%3C/svg%3E%3C/svg%3E" />
-    <script type="module" crossorigin src="/assets/index-VnHjeVmH.js"></script>
+    <script type="module" crossorigin src="/assets/index-DjwOIk2X.js"></script>
     <link rel="stylesheet" crossorigin href="/assets/index-B4Xv671Q.css">
   </head>
   <body class="antialiased">

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "specweave",
-  "version": "3.1.10",
+  "version": "3.1.12",
   "description": "Keep intent, specifications, and verified progress portable across AI coding tools. A local live work board, append-only task evidence, explicit handoffs, and optional GitHub/Jira/Azure DevOps integrations.",
   "type": "module",
   "bin": {
@@ -103,7 +103,7 @@
     "src/styles/fonts/*-OFL.txt"
   ],
   "dependencies": {
-    "@anthropic-ai/sdk": "^0.133.0",
+    "@anthropic-ai/sdk": "^0.135.0",
     "@inquirer/prompts": "^8.1.0",
     "@octokit/rest": "^22.0.1",
     "@types/handlebars": "^4.0.40",

package/plugins/specweave/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "sw",
   "description": "Portable intent and verified progress across coding tools. Six core workflow skills plus opt-in grill-me, glossary, sync, project and jev, two default lifecycle hooks, and a deterministic CLI and live local dashboard.",
-  "version": "3.1.10",
+  "version": "3.1.12",
   "author": {
     "name": "SpecWeave Team",
     "url": "https://spec-weave.com"

package/src/templates/AGENTS.md.template

@@ -1,21 +1,21 @@
 <!-- SECTION:header required -->
 # {PROJECT_NAME}
 
-This project uses SpecWeave. Plan increments in `.specweave/increments/NNNN-slug/spec.md`: Problem, Scope, Acceptance Criteria, Approach and Tasks. Adjacent `ledger.jsonl` records claims and completions. Start sessions with `specweave pickup`.
+SpecWeave increments live in `.specweave/increments/NNNN-slug/spec.md`: Problem, Scope, Acceptance Criteria, Approach and Tasks. `ledger.jsonl` records claims and completions. Start with `specweave pickup`.
 <!-- /SECTION -->
 
 <!-- SECTION:loop required -->
 ## The loop
 
 1. `specweave pickup`: applies the latest handoff, prints the open increment, next task and ACs, claims, branch, notes and memory.
-2. New work needing ACs or handoff: `specweave create-increment "title"`, then fill spec.md. First ask the user only their critical decisions, one at a time with a recommended answer, and record them under `## Decisions` (sw-increment). If an open increment owns the files, add ACs and tasks there. Recommended for features, not required; to skip one run `specweave small-fix "<why>"`. Close what you open: its plan ends with "Verify and close NNNN".
+2. New work needing ACs or handoff: `specweave create-increment "title"`, then fill spec.md. Ask only critical decisions, one at a time with a recommendation, and record them under `## Decisions` (sw-increment). If an open increment owns the files, add ACs and tasks there. Recommended for features, not required; to skip one run `specweave small-fix "<why>"`. Close what you open: its plan ends with "Verify and close NNNN".
 3. `specweave task claim T-NN`, edit only that task's Files, commit as `NNNN: what changed`, then `specweave task done T-NN --run "<its Test>"`. `--line`/`--link` feed `specweave cards --md`.
 4. When the last task is done or skipped, without asking: `specweave verify`, a fresh-context review (subagent or new session) for anything that ships, `specweave complete NNNN`. PR-shipped work needs `task done` first.
 5. Stopping with tasks left, or switching tools: `specweave handoff --reason "<why>"`.
 
 **Handoff.** When the user says "hand off", "out of tokens" or "switching accounts", or "[Usage limit reached" appears (outside SpecWithCode), run `specweave handoff --reason "<why>"`; tell them to say "pick up" in the other tool. "[Usage limit approaching" or usage heads-ups mean keep working; say so. When the user says "pick up", run `specweave pickup`; continue through step 4, passing any given id/title. Take the newest handoff if several; say which.
 
-Tasks in spec.md: `### T-01 Title`, then `- AC: AC-01 | Files: src/a.ts, tests/e2e/a.test.ts | Test: npm test -- e2e/a`. An AC is met when its tasks are done. Leave notes with `specweave note "<text>"`. Skills: `.agents/skills/sw-*` and `.claude/skills/sw-*`; other tools: `npx vskill install anton-abyzov/specweave/sw-do`.
+Tasks in spec.md: `### T-01 Title`, then `- AC: AC-01 | Files: src/a.ts, tests/e2e/a.test.ts | Test: npm test -- e2e/a`. ACs derive from done tasks. Notes: `specweave note "<text>"`. Skills: `.agents/skills/sw-*` and `.claude/skills/sw-*`; other tools: `npx vskill install anton-abyzov/specweave/sw-do`.
 <!-- /SECTION -->
 
 <!-- SECTION:rules required -->
@@ -24,8 +24,9 @@ Tasks in spec.md: `### T-01 Title`, then `- AC: AC-01 | Files: src/a.ts, tests/e
 - Use headless Chrome/Playwright CLI for browser tests and automation: `headless: true`, `PWDEBUG=0`, `PLAYWRIGHT_HTML_OPEN=never`, HTML reports `open: 'never'`. Save captures to files; propagate to subagents. Before opening an essential visible browser, ask the user and wait for explicit approval. Headless failure is not approval.
 - A task is done when its Test exits 0 and you have seen the real output. A Test checks the AC as users would (CLI, HTTP, UI, API); add unit tests only when asked or when config or conventions require them. Never skip, weaken or delete a test to pass, and never set a status by hand.
 - One agent per branch/worktree: `git worktree add .worktrees/NNNN-<agent> -b inc/NNNN-<agent>` (never `../`). Claims older than 2h are stale. On `ledger.jsonl` conflicts keep both sides' lines.
-- Decisions that must outlive this session go in spec.md Approach, or as one file per fact in `.specweave/memory/` with a line in its `MEMORY.md` index. Memory is committed, so every tool and account sees it.
+- Commit durable decisions in spec.md Approach or one fact per file in `.specweave/memory/`, indexed in `MEMORY.md`, for all tools.
 - Check a secret exists without printing it; never commit `.env*`.
+- Honor project identity and licensing. Keep provenance and required notices; never infer license grants or history rewrites from branding changes.
 - Without the CLI, append ledger lines yourself, one JSON object per line, UTF-8, LF: `{"t":"T-01","e":"claim","by":"<tool>@<host>","at":"<ISO time>"}` (`e` is claim, done, release, skip or block; `done` needs `"evidence":"<commit sha>"`, `skip` needs `"note":"<why>"`).
 <!-- /SECTION -->
 

package/src/templates/CLAUDE.md.template

@@ -8,6 +8,7 @@ Everything shared by every tool is in AGENTS.md, imported above. Only Claude-spe
 - Skills: `/sw-increment "title"`, `/sw-do`, `/sw-auto`, `/sw-review`, `/sw-done`, `/sw-handoff`, from `.claude/skills/`, so they load in cloud sessions too. With the `sw` plugin they are also `/sw:do` and so on.
 - With the plugin, the SessionStart hook prints a short pickup; run `specweave pickup` for the next task's acceptance criteria.
 - Use plan mode before writing a spec for anything bigger than a small fix.
+- Follow AGENTS.md for product identity and licensing; preserve required third-party notices and accurate provenance.
 <!-- /SECTION -->
 
 <!-- SECTION:jev when="jev" -->