@pennixrv/trellis 0.7.0-beta.9 → 0.7.1

package/dist/templates/copilot/prompts/record-session.prompt.md

@@ -2,28 +2,21 @@
 description: "Trellis Copilot prompt: Method 1: Simple parameters"
 ---
 
-[!] **Prerequisite**: This command should only be used AFTER the human has tested and committed the code.
+[!] **Prerequisite**: Record verified progress and the actual commit references for this session. Do not imply that the task is complete merely because work was committed.
 
-**Do NOT run `git commit` directly** — the scripts below handle their own commits for `.trellis/` metadata. You only need to read git history (`git log`, `git status`, `git diff`) and run the Python scripts.
+Task status and phase state are changed only through Trellis CLI. This prompt records the developer session journal; it does not archive, complete, or cancel tasks.
 
 ---
 
 ## Record Work Progress
 
-### Step 1: Get Context & Check Tasks
+### Step 1: Get Context
 
 ```bash
 python3 ./.trellis/scripts/get_context.py --mode record
 ```
 
-[!] Archive tasks whose work is **actually done** — judge by work status, not the `status` field in task.json:
-- Code committed? → Archive it (don't wait for PR)
-- All acceptance criteria met? → Archive it
-- Don't skip archiving just because `status` still says `planning` or `in_progress`
-
-```bash
-python3 ./.trellis/scripts/task.py archive <task-name>
-```
+Review the current phase, changed files, recent commits, remaining work, and blockers. Use the Delivery Review and On-Site Closeout Phase Skill with the Trellis CLI to complete or cancel a task when its acceptance conditions are met.
 
 ### Step 2: One-Click Add Session
 
@@ -62,5 +55,4 @@ EOF
 |---------|---------|
 | `python3 ./.trellis/scripts/get_context.py --mode record` | Get context for record-session |
 | `python3 ./.trellis/scripts/add_session.py --title "..." --commit "..."` | **One-click add session (recommended, branch auto-complete)** |
-| `python3 ./.trellis/scripts/task.py archive <name>` | Archive completed task (auto-commits) |
 | `python3 ./.trellis/scripts/task.py list` | List active tasks |

package/dist/templates/copilot/prompts/start.prompt.md

@@ -4,7 +4,7 @@ description: "Trellis Copilot prompt: Start Session"
 
 # Start Session
 
-Initialize a Trellis-managed development session. This platform has no session-start hook, so manually load the equivalent context by following these steps (each one mirrors a section the hook would otherwise inject).
+Use this prompt to inspect or refresh Trellis context. Copilot also supplies SessionStart context and a per-turn workflow-state breadcrumb through its hooks.
 
 ---
 
@@ -38,15 +38,13 @@ cat .trellis/spec/<package>/<layer>/index.md   # for each relevant layer
 Index files list the specific guideline docs to read when you actually start coding.
 
 ## Step 4: Decide next action
-From Step 1 you know the current task and status. Check the task directory:
+Use the current `<workflow-state>` breadcrumb to identify the business phase; task lifecycle status (`planning` or `in_progress`) and artifact presence do not identify that phase. If the breadcrumb is missing or stale, inspect the task with `task.py phase show <task>` and follow the matching phase Skill in `.trellis/workflow.md`.
 
-- **Active task status `planning` + no `prd.md`** → Phase 1.1. Load the `trellis-brainstorm` skill.
-- **Active task status `planning` + `prd.md` exists** → stay in Phase 1. Lightweight tasks can be PRD-only; complex tasks need `design.md` + `implement.md`. Load the relevant Phase 1 step detail before `task.py start`.
-- **Active task status `in_progress`** → Phase 2 step 2.1. Load the step detail:
-  ```bash
-  {{PYTHON_CMD}} ./.trellis/scripts/get_context.py --mode phase --step 2.1 --platform {{CLI_FLAG}}
-  ```
-- **No active task** → classify first. For simple conversation / small task, ask only whether this turn should create a Trellis task. For complex work, ask whether you may create a Trellis task and enter planning. If the user says no, skip Trellis for this session.
+- **An active phase is recorded** → continue that phase and load its matching Skill.
+- **The task has no initialized phase route** → load `trellis-goal-exploration-and-requirements`, align and obtain the user's confirmation of the current requirements baseline, then initialize the applicable ordered route with `task.py phase init`.
+- **No active task** → classify first. Handle a clear, low-risk, reversible, authorized, immediately verifiable request directly; otherwise ask for task-creation consent and begin with `trellis-goal-exploration-and-requirements`.
+
+`task.py start` enters implementation only after an accepted implementation contract from Solution Design and Convergence Phase and separate implementation authorization.
 
 ---
 
@@ -54,7 +52,11 @@ From Step 1 you know the current task and status. Check the task directory:
 
 | User intent | Skill |
 |---|---|
-| New feature / unclear requirements | `trellis-brainstorm` |
+| Goal and requirements | `trellis-goal-exploration-and-requirements` |
+| Decision alternatives | `trellis-decision-space-construction-and-merging` |
+| Solution design | `trellis-solution-design-and-convergence` |
+| Implementation | `trellis-task-implementation` |
+| Delivery review | `trellis-delivery-review-and-closeout` |
 | About to write code | `trellis-before-dev` |
 | Done coding / quality check | `trellis-check` |
 | Stuck / fixed same bug multiple times | `trellis-break-loop` |

package/dist/templates/dsh/DSH.md

@@ -27,8 +27,8 @@ In dsh:
 2. The main session dispatches `trellis-agent-research`,
    `trellis-agent-implement`, and `trellis-agent-check` through DSH's native
    `subagent` tool. Each child loads exactly one matching role skill.
-3. Finish through `trellis-finish-work`, which preserves the required order:
-   commit, archive, then journal.
+3. Use Delivery Review and On-Site Closeout Phase to review and close the task. `trellis-finish-work` records
+   session progress separately and does not change task lifecycle state.
 
 ## Companion plugin fallback contract
 

package/dist/templates/kiro/agents/trellis.json

@@ -1,7 +1,7 @@
 {
   "name": "trellis",
-  "description": "Trellis workflow main agent. Drives the Trellis development workflow: reads .trellis/workflow.md, classifies each turn, and routes work through plan / implement / check phases. Use as the default Kiro agent for projects that run Trellis.",
-  "prompt": "# Trellis Workflow Agent\n\nYou are the main session agent for a project that uses the Trellis workflow.\n\n## On Every Turn\n\nA `userPromptSubmit` hook injects a `<workflow-state>` breadcrumb each turn telling you the active task and its current phase. An `agentSpawn` hook injects a `<session-context>` overview when this agent starts. Trust those injections to orient yourself — do not re-derive context from scratch.\n\n## How to Work\n\n1. **Follow the workflow.** `.trellis/workflow.md` is the single source of truth for phases and steps. It is also attached as a resource for this agent. Read it (or the injected Phase Index) and follow the matching phase.\n2. **Resolve the active task** with `python3 ./.trellis/scripts/task.py current --source` when the breadcrumb is missing or stale.\n3. **Classify the turn** before acting: simple conversation, small edit, or a complex task that needs a Trellis task directory + planning. Do not create a task for trivial turns.\n4. **Plan before implementing.** For complex work, write `prd.md` (and `design.md` / `implement.md` when warranted) and get the user's confirmation before entering implementation.\n5. **Load task context in order** for implementation/check: jsonl entries -> `prd.md` -> `design.md` (if present) -> `implement.md` (if present).\n6. **Verify** with the project's lint / type-check / test commands before declaring work done.\n\n## Constraints\n\n- Do NOT run `git commit` / `git push` / `git merge` unless the user explicitly asks.\n- Keep changes surgical and scoped to the request.\n- Discover guidelines on demand: `python3 ./.trellis/scripts/get_context.py --mode packages`.\n",
+  "description": "Trellis workflow main agent. Follows the current task route and matching Skills, or uses the taskless route when eligible.",
+  "prompt": "# Trellis Workflow Agent\n\nYou are the main session agent for a project that uses the Trellis workflow.\n\n## On Every Turn\n\nA `userPromptSubmit` hook injects a `<workflow-state>` breadcrumb each turn with the active task and its current phase. An `agentSpawn` hook injects a `<session-context>` overview when this agent starts. Use these to orient yourself; resolve missing or stale state through Trellis CLI.\n\n## How to Work\n\n1. Follow `.trellis/workflow.md` and the matching phase Skill. The workflow and its task route define the business phase; task lifecycle status and artifact presence do not.\n2. If the breadcrumb is missing or stale, inspect the active task with `python3 ./.trellis/scripts/task.py current --json` and `python3 ./.trellis/scripts/task.py phase show <task>`.\n3. With no active task, use the taskless route only when `.trellis/workflow.md` permits it; otherwise create the task and establish its baseline through Goal Exploration and Requirements Confirmation Phase.\n4. The Goal Exploration and Requirements Confirmation Phase requires the user's confirmation of the current requirements revision. Before Task Implementation and Test Verification Phase, both an accepted `implementation_contract` from Solution Design and Convergence Phase and separate implementation authorization are required. Delivery Review and On-Site Closeout Phase governs delivery acceptance, task completion, and cancellation.\n5. Use task artifacts and context manifests as required by the current route and any dispatched agent; do not require a fixed set of planning documents based only on task complexity.\n6. Verify with project checks appropriate to the changes before reporting completion.\n\n## Constraints\n\n- Do NOT run `git commit` / `git push` / `git merge` unless the user explicitly asks.\n- Keep changes scoped to the request.\n- Discover guidelines on demand: `python3 ./.trellis/scripts/get_context.py --mode packages`.\n",
   "tools": [
     "read",
     "write",

package/dist/templates/markdown/agents.md

@@ -1,9 +1,20 @@
 <!-- TRELLIS:START -->
-# Trellis
+# Trellis Instructions
 
-Follow `.trellis/workflow.md`; read the applicable `.trellis/spec/` guidance before editing code, and keep task facts in `.trellis/tasks/`. Project-scoped helpers live in `.agents/skills/`.
+These instructions are for AI assistants working in this project.
 
-When a live Trellis Channel wait returns a host continuation, resume only that continuation until it resolves, times out, or errors. Do not run another host action meanwhile, including another wait, shell command, or status/message query; use diagnostics only on demand after it returns.
+This project is managed by Trellis. The working knowledge you need lives under `.trellis/`:
+
+- `.trellis/workflow.md` — development phases, when to create tasks, skill routing
+- `.trellis/spec/` — package- and layer-scoped coding guidelines (read before writing code in a given layer)
+- `.trellis/workspace/` — per-developer journals and session traces
+- `.trellis/tasks/` — task records and their planning, implementation, and review artifacts
+
+If a Trellis command is available on your platform (e.g. `/trellis:finish-work`, `/trellis:continue`), prefer it over manual steps. Not every platform exposes every command.
+
+If you're using Codex or another agent-capable tool, additional project-scoped helpers may live in:
+- `.agents/skills/` — reusable Trellis skills
+- `.codex/agents/` — optional custom subagents
 
 Managed by Trellis. Edits outside this block are preserved; edits inside may be overwritten by a future `trellis update`.
 

package/dist/templates/markdown/spec/guides/cross-layer-thinking-guide.md.txt

@@ -216,7 +216,7 @@ When a CLI auto-detects a mode by probing a remote resource (e.g., checking if `
 
 **Real-world example**: Custom registry flow had 8 bugs across 3 review rounds: (1) probe only ran in interactive mode, (2) transient errors fell through to wrong mode, (3) giget URI had `#ref` in wrong position, (4) prefetched templates leaked across source switches, (5) `--template` shortcut bypassed probe but `downloadTemplateById` internally used catch-all `fetchTemplateIndex`, turning timeouts into "Template not found".
 
-**Real-world example**: Agent-session update hints fetched npm `latest` metadata with `response.read(4096)` and then parsed it as complete JSON. The `@pennixrv/trellis` package metadata exceeded 4 KB, so the JSON was truncated, parse failed silently, and the first session injection showed no update hint. Fix: read the complete response before parsing, and add a regression where `version` is followed by an 8 KB metadata tail.
+**Real-world example**: Agent-session update hints fetched npm `latest` metadata with `response.read(4096)` and then parsed it as complete JSON. The `@mindfoldhq/trellis` package metadata exceeded 4 KB, so the JSON was truncated, parse failed silently, and the first session injection showed no update hint. Fix: read the complete response before parsing, and add a regression where `version` is followed by an 8 KB metadata tail.
 
 ---
 
@@ -284,7 +284,7 @@ When a CLI auto-detects a mode by probing a remote resource (e.g., checking if `
 
 **Real-world example**: Custom registry flow had 8 bugs across 3 review rounds: (1) probe only ran in interactive mode, (2) transient errors fell through to wrong mode, (3) giget URI had `#ref` in wrong position, (4) prefetched templates leaked across source switches, (5) `--template` shortcut bypassed probe but `downloadTemplateById` internally used catch-all `fetchTemplateIndex`, turning timeouts into "Template not found".
 
-**Real-world example**: Agent-session update hints fetched npm `latest` metadata with `response.read(4096)` and then parsed it as complete JSON. The `@pennixrv/trellis` package metadata exceeded 4 KB, so the JSON was truncated, parse failed silently, and the first session injection showed no update hint. Fix: read the complete response before parsing, and add a regression where `version` is followed by an 8 KB metadata tail.
+**Real-world example**: Agent-session update hints fetched npm `latest` metadata with `response.read(4096)` and then parsed it as complete JSON. The `@mindfoldhq/trellis` package metadata exceeded 4 KB, so the JSON was truncated, parse failed silently, and the first session injection showed no update hint. Fix: read the complete response before parsing, and add a regression where `version` is followed by an 8 KB metadata tail.
 
 ---
 
@@ -319,9 +319,10 @@ CLI input → event writer → events.jsonl → reader → filter → reducer
 - [ ] Add at least one regression that proves history replay and live filtering
       use the same filter model
 
-**Real-world example**: Thread channels added `kind: "thread"`, `description`,
-`context`, labels, and `lastSeq`. The first implementation replayed thread
-state correctly, but several commands still re-parsed event payload fields with
-local casts. The fix was to make the core event layer own `ThreadChannelEvent`
-and `isThreadEvent`, make `reduceChannelMetadata` the only channel metadata
-projection, and make `reduceThreads` the only thread replay reducer.
+**Real-world example**: Forum Teamwork Sessions added thread events with
+`description`, `context`, labels, and sequence tracking. The first
+implementation replayed thread state correctly, but several commands still
+re-parsed event payload fields with local casts. The fix was to make Core own
+`ThreadTeamworkEvent` and `isThreadEvent`, use
+`reduceTeamworkSessionMetadata` for session metadata, and use `reduceThreads`
+for thread replay.

package/dist/templates/markdown/spec/guides/cross-platform-thinking-guide.md.txt

@@ -600,7 +600,7 @@ When release notes or docs claim an asset is bundled, installed automatically, o
 included with Trellis, verify the whole distribution path:
 
 - [ ] Source file exists in the branch being tagged, not only in another branch,
-  docs submodule, or marketplace tree.
+  docs submodule, or external Marketplace repository.
 - [ ] `pnpm build` copies the asset into `dist/templates/**`.
 - [ ] `npm pack --dry-run --json` includes the expected `dist/**` path.
 - [ ] The built binary installs the asset in a fresh temp repository.

package/dist/templates/markdown/workspace-index.md

@@ -17,7 +17,6 @@ workspace/
     |-- index.md          # Personal index with session history
     |-- tasks/         # Task files
     |   |-- *.json        # Active tasks
-    |   +-- archive/      # Archived tasks by month
     +-- journal-N.md     # Journal files (sequential: 1, 2, 3...)
 ```
 

package/dist/templates/omp/extensions/trellis/index.ts.txt

@@ -59,7 +59,7 @@ function isInsideRoot(root: string, candidate: string): boolean {
 }
 
 // ---------------------------------------------------------------------------
-// Trusted context roots (mirrors packages/cli/src/commands/channel/context-trust.ts;
+// Trusted context roots (mirrors packages/cli/src/commands/teamwork/context-trust.ts;
 // standalone copy since templates don't import from the CLI package).
 // ---------------------------------------------------------------------------
 
@@ -69,7 +69,7 @@ function stripTrustValue(s: string): string {
    return s.trim().replace(/\s*#.*$/, "").trim().replace(/^['"]|['"]$/g, "");
 }
 
-function parseChannelTrustSection(content: string): { trustedDirs: string[]; autoTrustSymlinks?: boolean } {
+function parseTeamworkTrustSection(content: string): { trustedDirs: string[]; autoTrustSymlinks?: boolean } {
    const lines = content.split("\n");
    const trustedDirs: string[] = [];
    let autoTrustSymlinks: boolean | undefined;
@@ -115,7 +115,7 @@ function parseChannelTrustSection(content: string): { trustedDirs: string[]; aut
          const val = stripTrustValue(boolMatch[1]!).toLowerCase();
          if (val === "false") autoTrustSymlinks = false;
          else if (val === "true") autoTrustSymlinks = true;
-         else process.stderr.write(`[channel] channel.auto_trust_trellis_symlinks: invalid value '${val}', ignoring\n`);
+         else process.stderr.write(`[teamwork] teamwork.auto_trust_trellis_symlinks: invalid value '${val}', ignoring\n`);
          continue;
       }
    }
@@ -128,7 +128,7 @@ function resolveTrustedRoots(projectRoot: string): string[] {
    let config: { trustedDirs: string[]; autoTrustSymlinks?: boolean } = { trustedDirs: [] };
    if (existsSync(configPath)) {
       try {
-         config = parseChannelTrustSection(readFileSync(configPath, "utf-8"));
+         config = parseTeamworkTrustSection(readFileSync(configPath, "utf-8"));
       } catch {
          // ignore
       }
@@ -202,9 +202,9 @@ function displayProjectPath(projectRoot: string, filePath: string, taskDir?: str
 function resolveActiveTaskStatus(
    projectRoot: string,
    contextKey: string | null,
-): { status: string; taskDir: string | null; taskTitle: string | null } {
+): { status: string; phaseStatus: string | null; taskDir: string | null; taskTitle: string | null } {
    const sessionsDir = join(projectRoot, ".trellis", ".runtime", "sessions");
-   if (!existsSync(sessionsDir)) return { status: "no_task", taskDir: null, taskTitle: null };
+   if (!existsSync(sessionsDir)) return { status: "no_task", phaseStatus: null, taskDir: null, taskTitle: null };
 
    // --- 通过 context key 解析 session 文件 ---
    let sessionFilePath: string | null = null;
@@ -214,7 +214,7 @@ function resolveActiveTaskStatus(
       if (existsSync(candidate)) {
          sessionFilePath = candidate;
       } else {
-         return { status: "no_task", taskDir: null, taskTitle: null };
+         return { status: "no_task", phaseStatus: null, taskDir: null, taskTitle: null };
       }
    } else {
       // No identity: use single-session fallback only when there is exactly one session file.
@@ -222,12 +222,12 @@ function resolveActiveTaskStatus(
       try {
          sessionFiles = readdirSync(sessionsDir).filter((f) => f.endsWith(".json"));
       } catch {
-         return { status: "no_task", taskDir: null, taskTitle: null };
+         return { status: "no_task", phaseStatus: null, taskDir: null, taskTitle: null };
       }
       if (sessionFiles.length === 1) {
          sessionFilePath = join(sessionsDir, sessionFiles[0]);
       } else {
-         return { status: "no_task", taskDir: null, taskTitle: null };
+         return { status: "no_task", phaseStatus: null, taskDir: null, taskTitle: null };
       }
    }
 
@@ -236,12 +236,12 @@ function resolveActiveTaskStatus(
    try {
       sessionData = JSON.parse(readFileSync(sessionFilePath, "utf-8"));
    } catch {
-      return { status: "no_task", taskDir: null, taskTitle: null };
+      return { status: "no_task", phaseStatus: null, taskDir: null, taskTitle: null };
    }
 
    const currentTask = sessionData.current_task;
    if (typeof currentTask !== "string" || !currentTask)
-      return { status: "no_task", taskDir: null, taskTitle: null };
+      return { status: "no_task", phaseStatus: null, taskDir: null, taskTitle: null };
 
    // Same jail the jsonl-referenced files already go through below. `task.py`
    // now refuses to store a ref that leaves the project, but a session file
@@ -249,19 +249,30 @@ function resolveActiveTaskStatus(
    // rewrite session files — so a poisoned pointer outlives the upgrade that
    // closed the writer.
    const taskDir = resolveProjectFile(projectRoot, currentTask, resolveTrustedRoots(projectRoot));
-   if (!taskDir) return { status: "no_task", taskDir: null, taskTitle: null };
+   if (!taskDir) return { status: "no_task", phaseStatus: null, taskDir: null, taskTitle: null };
    const taskJsonPath = join(taskDir, "task.json");
-   if (!existsSync(taskJsonPath)) return { status: "no_task", taskDir: null, taskTitle: null };
+   if (!existsSync(taskJsonPath)) return { status: "no_task", phaseStatus: null, taskDir: null, taskTitle: null };
 
    let taskData: Record<string, unknown>;
    try {
       taskData = JSON.parse(readFileSync(taskJsonPath, "utf-8"));
    } catch {
-      return { status: "no_task", taskDir: null, taskTitle: null };
+      return { status: "no_task", phaseStatus: null, taskDir: null, taskTitle: null };
    }
 
+   const taskMeta = taskData.meta;
+   const phaseWorkflow = taskMeta && typeof taskMeta === "object" && !Array.isArray(taskMeta)
+      ? (taskMeta as Record<string, unknown>).task_workflow as Record<string, unknown> | undefined
+      : undefined;
+   const route = phaseWorkflow?.phase_ids;
+   const phaseId = phaseWorkflow?.current_phase_id || (Array.isArray(route) ? route[route.length - 1] : undefined);
+   const phaseMap = phaseWorkflow?.phases;
+   const phase = typeof phaseId === "string" && phaseMap && typeof phaseMap === "object" && !Array.isArray(phaseMap)
+      ? (phaseMap as Record<string, Record<string, unknown>>)[phaseId]
+      : null;
    return {
-      status: typeof taskData.status === "string" ? taskData.status : "planning",
+      status: typeof phaseId === "string" && phase ? phaseId : (typeof taskData.status === "string" ? taskData.status : "planning"),
+      phaseStatus: typeof phase?.status === "string" ? phase.status : null,
       taskDir,
       taskTitle: typeof taskData.title === "string" ? taskData.title : null,
    };
@@ -818,7 +829,7 @@ class TurnContextCache {
          return { workflowMsg: this.workflowMsg };
       }
 
-      const { status } = resolveActiveTaskStatus(projectRoot, contextKey);
+      const { status, phaseStatus } = resolveActiveTaskStatus(projectRoot, contextKey);
 
       const workflowPath = join(projectRoot, ".trellis", "workflow.md");
       let workflowMd = "";
@@ -839,7 +850,7 @@ class TurnContextCache {
       // When skip keyword is present, skip workflow state injection this turn
       this.workflowMsg = this.skipThisTurn
          ? ""
-         : `<workflow-state>\n${workflowBody}\n</workflow-state>\n\n<session-overview>\n${SESSION_OVERVIEW_TEXT}\n</session-overview>`;
+         : `<workflow-state>\n${phaseStatus ? `Phase: ${status} (${phaseStatus})\n` : ""}${workflowBody}\n</workflow-state>\n\n<session-overview>\n${SESSION_OVERVIEW_TEXT}\n</session-overview>`;
 
       this.key = cacheKey;
       this.timestamp = now;

package/dist/templates/opencode/lib/session-utils.js

@@ -71,12 +71,9 @@ function getTaskStatus(ctx, platformInput = null) {
   const taskStatus = taskData.status || "unknown"
 
   if (taskStatus === "completed") {
-    return `Status: COMPLETED\nTask: ${taskTitle}\nNext-Action: Run /trellis:finish-work. If the working tree is dirty, return to Phase 3.4 first.`
+    return `Status: COMPLETED\nTask: ${taskTitle}\nNext-Action: Start another task or end the session; finish-work only records the session journal.`
   }
 
-  const hasPrd = existsSync(join(taskDir, "prd.md"))
-  const hasDesign = existsSync(join(taskDir, "design.md"))
-  const hasImplementPlan = existsSync(join(taskDir, "implement.md"))
   const artifactNames = ["prd.md", "design.md", "implement.md", "implement.jsonl", "check.jsonl"]
   const present = artifactNames.filter(name => existsSync(join(taskDir, name)))
   if (existsSync(join(taskDir, "research"))) present.push("research/")
@@ -87,24 +84,13 @@ function getTaskStatus(ctx, platformInput = null) {
     (!existsSync(implementJsonl) || hasCuratedJsonlEntry(implementJsonl)) &&
     (!existsSync(checkJsonl) || hasCuratedJsonlEntry(checkJsonl))
 
-  if (taskStatus === "planning" && !hasPrd) {
-    return `Status: PLANNING\nTask: ${taskTitle}\nPresent: ${presentLine}\nNext-Action: Load trellis-brainstorm and write prd.md. Stay in planning.`
-  }
-
   if (taskStatus === "planning") {
-    const missingComplex = []
-    if (!hasDesign) missingComplex.push("design.md")
-    if (!hasImplementPlan) missingComplex.push("implement.md")
-    const nextBits = []
-    if (missingComplex.length > 0) {
-      nextBits.push(
-        `Lightweight task can request start review with PRD-only; complex task must add ${missingComplex.join(", ")} before start`,
-      )
-    } else {
-      nextBits.push("Planning artifacts are present; ask for review before `task.py start`")
-    }
+    const nextBits = [
+      "Follow the current per-turn workflow-state; task lifecycle status and artifact presence do not identify the business phase",
+      "If no phase route is initialized, load `trellis-goal-exploration-and-requirements` and confirm the requirements baseline before initializing the route",
+    ]
     if (!jsonlReady) {
-      nextBits.push("curate `implement.jsonl` and `check.jsonl` before sub-agent mode start")
+      nextBits.push("curate task context manifests only when a dispatched agent needs them")
     }
     return `Status: PLANNING\nTask: ${taskTitle}\nPresent: ${presentLine}\nNext-Action: ${nextBits.join("; ")}. Do not enter implementation until the user confirms start.`
   }
@@ -112,7 +98,7 @@ function getTaskStatus(ctx, platformInput = null) {
   return (
     `Status: ${String(taskStatus).toUpperCase()}\nTask: ${taskTitle}\n` +
     `Present: ${presentLine}\n` +
-    "Next-Action: Follow the matching per-turn workflow-state. " +
+    "Next-Action: Follow the matching per-turn workflow-state; task lifecycle status does not identify the business phase. " +
     "Implementation/check context order is jsonl entries -> `prd.md` -> `design.md if present` -> `implement.md if present`."
   )
 }
@@ -393,8 +379,8 @@ Trellis compact SessionStart context. Use it to orient the session; load details
   if (workflowContent) {
     const allLines = workflowContent.split("\n")
     const overviewLines = [
-      "# Development Workflow - Session Summary",
-      "Full guide: .trellis/workflow.md. Step detail: `python3 ./.trellis/scripts/get_context.py --mode phase --step <X.Y>`.",
+      "# 工作流会话摘要",
+      "完整说明：.trellis/workflow.md。阶段详情：读取当前阶段提示指定的 Skill。",
       "",
     ]
 
@@ -402,9 +388,18 @@ Trellis compact SessionStart context. Use it to orient the session; load details
     let rangeEnd = allLines.length
     for (let i = 0; i < allLines.length; i++) {
       const stripped = allLines[i].trim()
-      if (rangeStart === -1 && stripped === "## Phase Index") {
+      const heading = stripped.replace(/^#{2,3}\s+/, "")
+      const isPhaseHeading =
+        /^#{2,3}\s+/.test(stripped) &&
+        ["目标探索与需求核对阶段", "Goal Exploration and Requirements Confirmation Phase"].some(
+          (title) =>
+            heading === title ||
+            heading.endsWith(`：${title}`) ||
+            heading.endsWith(`: ${title}`),
+        )
+      if (rangeStart === -1 && ["## 阶段索引", "## Phase Index"].includes(stripped)) {
         rangeStart = i
-      } else if (rangeStart !== -1 && stripped === "## Phase 1: Plan") {
+      } else if (rangeStart !== -1 && isPhaseHeading) {
         rangeEnd = i
         break
       }

package/dist/templates/opencode/lib/trellis-context.js

@@ -372,14 +372,10 @@ export class TrellisContext {
    * Get active task from session runtime context.
    *
    * Resolution order (mirrors Python `active_task.resolve_active_task`):
-   *   1. Lookup the runtime file for the input-derived context key. A known
-   *      key is authoritative when it contains a task; a missing or empty
-   *      context may use the guarded unbound-task projection.
-   *   2. If no context key is available and exactly one session runtime file
-   *      exists locally, use it (`_resolveSingleSessionFallback`). Refuses to
-   *      guess when 0 or ≥2 files exist so multi-window isolation holds.
-   *   3. If no session file exists, expose one resumable task assigned to the
-   *      current developer as a read-only unbound projection.
+   *   1. Lookup the runtime file for the input-derived context key.
+   *   2. If that misses and exactly one session runtime file exists locally,
+   *      use it (`_resolveSingleSessionFallback`). Refuses to guess when 0 or
+   *      ≥2 files exist so multi-window isolation holds.
    */
   getActiveTask(platformInput = null) {
     const contextKey = this.getContextKey(platformInput)
@@ -394,11 +390,6 @@ export class TrellisContext {
           stale: !taskDir || !existsSync(taskDir),
         }
       }
-      const unbound = this._resolveUnboundTask()
-      if (unbound) {
-        return unbound
-      }
-      return { taskPath: null, source: "none", stale: false }
     }
 
     const fallback = this._resolveSingleSessionFallback()
@@ -406,11 +397,6 @@ export class TrellisContext {
       return fallback
     }
 
-    const unbound = this._resolveUnboundTask()
-    if (unbound) {
-      return unbound
-    }
-
     return { taskPath: null, source: "none", stale: false }
   }
 
@@ -452,64 +438,6 @@ export class TrellisContext {
     }
   }
 
-  _resolveUnboundTask() {
-    const sessionsDir = join(this.directory, ".trellis", ".runtime", "sessions")
-    if (existsSync(sessionsDir)) {
-      let sessionFiles
-      try {
-        sessionFiles = readdirSync(sessionsDir).filter(name => name.endsWith(".json"))
-      } catch {
-        return null
-      }
-      if (sessionFiles.some(file => {
-        try {
-          const context = JSON.parse(readFileSync(join(sessionsDir, file), "utf-8"))
-          return Boolean(this.normalizeTaskRef(context?.current_task || ""))
-        } catch {
-          return false
-        }
-      })) return null
-    }
-
-    const developer = (process.env.TRELLIS_DEVELOPER || "").trim() || (() => {
-      try {
-        const content = readFileSync(join(this.directory, ".trellis", ".developer"), "utf-8")
-        return content.split(/\r?\n/).find(line => line.startsWith("name="))?.slice(5).trim() || ""
-      } catch {
-        return ""
-      }
-    })()
-    if (!developer) return null
-
-    const tasksDir = join(this.directory, ".trellis", "tasks")
-    let taskNames
-    try {
-      taskNames = readdirSync(tasksDir).filter(name => name !== "archive")
-    } catch {
-      return null
-    }
-
-    const candidates = taskNames.flatMap(name => {
-      try {
-        const data = JSON.parse(readFileSync(join(tasksDir, name, "task.json"), "utf-8"))
-        if (data.assignee !== developer || !["planning", "in_progress", "review"].includes(data.status)) return []
-        return [`.trellis/tasks/${name}`]
-      } catch {
-        return []
-      }
-    })
-    if (candidates.length === 0) return null
-    if (candidates.length === 1) {
-      return { taskPath: candidates[0], source: "unbound", stale: false }
-    }
-    return {
-      taskPath: null,
-      source: "unbound_ambiguous",
-      stale: false,
-      candidatePaths: candidates.sort(),
-    }
-  }
-
   getCurrentTask(platformInput = null) {
     return this.getActiveTask(platformInput).taskPath
   }

package/dist/templates/opencode/plugins/inject-subagent-context.js

@@ -471,9 +471,10 @@ export default async ({ directory, platform: hostPlatform = process.platform, en
           // run when earlier ones miss):
           //   1. Exact session runtime context lookup for input.sessionID
           //   2. `Active task: <path>` hint in the dispatch prompt
-          //      (explicit per-dispatch override)
-          //   3. Single-session fallback only when the input has no session
-          //      identity and exactly 1 runtime file exists locally
+          //      (explicit per-dispatch override — beats single-session
+          //      inference so multi-window users can disambiguate)
+          //   3. Single-session fallback — only when exactly 1 session
+          //      runtime file exists locally
           let taskDir = null
           let taskSource = null
 
@@ -502,7 +503,7 @@ export default async ({ directory, platform: hostPlatform = process.platform, en
             }
           }
 
-          if (!taskDir && !contextKey) {
+          if (!taskDir) {
             const fallback = ctx._resolveSingleSessionFallback()
             if (fallback?.taskPath) {
               const fallbackDir = ctx.resolveTaskDir(fallback.taskPath)

package/dist/templates/opencode/plugins/inject-workflow-state.js

@@ -244,14 +244,6 @@ function loadBreadcrumbs(workflowPath) {
  */
 function getActiveTask(ctx, platformInput = null) {
   const active = ctx.getActiveTask(platformInput)
-  if (active.source === "unbound_ambiguous") {
-    return {
-      id: null,
-      status: "unbound_ambiguous",
-      source: active.source,
-      candidates: active.candidatePaths || [],
-    }
-  }
   const taskRef = active.taskPath
   if (!taskRef) return null
   const taskDir = ctx.resolveTaskDir(taskRef)
@@ -264,8 +256,14 @@ function getActiveTask(ctx, platformInput = null) {
     const data = JSON.parse(readFileSync(taskJsonPath, "utf-8"))
     const status = typeof data.status === "string" ? data.status : ""
     if (!status) return null
+    const phaseWorkflow = data.meta?.task_workflow
+    const phases = phaseWorkflow?.phases
+    const phaseId = phaseWorkflow?.current_phase_id || phaseWorkflow?.phase_ids?.at(-1)
+    const phase = typeof phaseId === "string" ? phases?.[phaseId] : null
     const id = data.id || taskRef.split("/").pop()
-    if (active.source === "unbound") return { id, status: "unbound_task", source: active.source }
+    if (typeof phaseId === "string" && phase && typeof phase.status === "string") {
+      return { id, status: phaseId, phaseStatus: phase.status, source: active.source }
+    }
     return { id, status, source: active.source }
   } catch {
     return null
@@ -279,17 +277,16 @@ function getActiveTask(ctx, platformInput = null) {
  *   "Refer to workflow.md for current step." line
  * - no_task pseudo-status (id === null) → header omits task info
  */
-function buildBreadcrumb(id, status, templates, candidates = []) {
+function buildBreadcrumb(id, status, templates, phaseStatus = null) {
   let body = templates[status]
   if (body === undefined) {
     body = "Refer to workflow.md for current step."
   }
-  let header
-  if (status === "unbound_ambiguous") {
-    header = `Status: ${status}\nCandidates: ${candidates.join(", ")}`
-  } else {
-    header = id === null ? `Status: ${status}` : `Task: ${id} (${status})`
-  }
+  const header = id === null
+    ? `Status: ${status}`
+    : phaseStatus
+      ? `Task: ${id}\nPhase: ${status} (${phaseStatus})`
+      : `Task: ${id} (${status})`
   return `<workflow-state>\n${header}\n${body}\n</workflow-state>`
 }
 
@@ -332,7 +329,7 @@ export default async ({ directory }) => {
           const templates = loadBreadcrumbs(resolveWorkflowMd(ctx, directory, platformInput))
           const task = getActiveTask(ctx, platformInput)
           const breadcrumb = task
-            ? buildBreadcrumb(task.id, task.status, templates, task.candidates)
+            ? buildBreadcrumb(task.id, task.status, templates, task.phaseStatus)
             : buildBreadcrumb(null, "no_task", templates)
 
           prependEphemeralText(messages, breadcrumb)