zhutao/store_ai_front

Fork 0

Files

zhu c661f4a063 首页

2026-05-07 16:14:31 +08:00

33 KiB

Raw Permalink Blame History

Development Workflow

Core Principles

Plan before code — figure out what to do before you start
Specs injected, not remembered — guidelines are injected via hook/skill, not recalled from memory
Persist everything — research, decisions, and lessons all go to files; conversations get compacted, files don't
Incremental development — one task at a time
Capture learnings — after each task, review and write new knowledge back to spec

Trellis System

Developer Identity

On first use, initialize your identity:

python ./.trellis/scripts/init_developer.py <your-name>

Creates .trellis/.developer (gitignored) + .trellis/workspace/<your-name>/.

Spec System

.trellis/spec/ holds coding guidelines organized by package and layer.

.trellis/spec/<package>/<layer>/index.md — entry point with Pre-Development Checklist + Quality Check. Actual guidelines live in the .md files it points to.
.trellis/spec/guides/index.md — cross-package thinking guides.

python ./.trellis/scripts/get_context.py --mode packages   # list packages / layers

When to update spec: new pattern/convention found · bug-fix prevention to codify · new technical decision.

Task System

Every task has its own directory under .trellis/tasks/{MM-DD-name}/ holding prd.md, implement.jsonl, check.jsonl, task.json, optional research/, info.md.

# Task lifecycle
python ./.trellis/scripts/task.py create "<title>" [--slug <name>] [--parent <dir>]
python ./.trellis/scripts/task.py start <name>          # set active task (session-scoped when available)
python ./.trellis/scripts/task.py current --source      # show active task and source
python ./.trellis/scripts/task.py finish                # clear active task (triggers after_finish hooks)
python ./.trellis/scripts/task.py archive <name>        # move to archive/{year-month}/
python ./.trellis/scripts/task.py list [--mine] [--status <s>]
python ./.trellis/scripts/task.py list-archive

# Code-spec context (injected into implement/check agents via JSONL).
# `implement.jsonl` / `check.jsonl` are seeded on `task create` for sub-agent-capable
# platforms; the AI curates real spec + research entries during Phase 1.3.
python ./.trellis/scripts/task.py add-context <name> <action> <file> <reason>
python ./.trellis/scripts/task.py list-context <name> [action]
python ./.trellis/scripts/task.py validate <name>

# Task metadata
python ./.trellis/scripts/task.py set-branch <name> <branch>
python ./.trellis/scripts/task.py set-base-branch <name> <branch>    # PR target
python ./.trellis/scripts/task.py set-scope <name> <scope>

# Hierarchy (parent/child)
python ./.trellis/scripts/task.py add-subtask <parent> <child>
python ./.trellis/scripts/task.py remove-subtask <parent> <child>

# PR creation
python ./.trellis/scripts/task.py create-pr [name] [--dry-run]

Run python ./.trellis/scripts/task.py --help to see the authoritative, up-to-date list.

Current-task mechanism: task.py create creates the task directory and (when session identity is available) auto-sets the per-session active-task pointer so the planning breadcrumb fires immediately. task.py start writes the same pointer (idempotent if already set) and flips task.json.status from planning to in_progress. State is stored under .trellis/.runtime/sessions/. If no context key is available from hook input, TRELLIS_CONTEXT_ID, or a platform-native session environment variable, there is no active task and task.py start fails with a session identity hint. task.py finish deletes the current session file (status unchanged). task.py archive <task> writes status=completed, moves the directory to archive/, and deletes any runtime session files that still point at the archived task.

Workspace System

Records every AI session for cross-session tracking under .trellis/workspace/<developer>/.

journal-N.md — session log. Max 2000 lines per file; a new journal-(N+1).md is auto-created when exceeded.
index.md — personal index (total sessions, last active).

python ./.trellis/scripts/add_session.py --title "Title" --commit "hash" --summary "Summary"

Context Script

python ./.trellis/scripts/get_context.py                            # full session runtime
python ./.trellis/scripts/get_context.py --mode packages            # available packages + spec layers
python ./.trellis/scripts/get_context.py --mode phase --step <X.Y>  # detailed guide for a workflow step

Phase Index

Phase 1: Plan    → figure out what to do (brainstorm + research → prd.md)
Phase 2: Execute → write code and pass quality checks
Phase 3: Finish  → distill lessons + wrap-up

[workflow-state:no_task] No active task. A Direct answer — pure Q&A / explanation / lookup / chat; no file writes + one-line answer + repo reads ≤ 2 files → AI judges, no override needed. B Create a task — any implementation / code change / build / refactor work. Entry sequence: (1) python ./.trellis/scripts/task.py create "<title>" to create the task (status=planning, breadcrumb switches to [workflow-state:planning] for brainstorm + jsonl phase guidance) → (2) load trellis-brainstorm skill to discuss requirements with the user and iterate on prd.md → (3) once prd is done and jsonl is curated, run task.py start <task-dir> to enter [workflow-state:in_progress] for the implementation skeleton. For research-heavy work, dispatch trellis-research sub-agents — main agent must NOT do 3+ inline WebFetch / WebSearch / gh api calls. "It looks small" is NOT grounds for downgrading B to A or C. C Inline change (per-turn only, escape hatch for B) — the user's CURRENT message MUST contain one of: "skip trellis" / "no task" / "just do it" / "don't create a task" / "跳过 trellis" / "别走流程" / "小修一下" / "直接改" / "先别建任务" → briefly acknowledge ("ok, skipping trellis flow this turn"), then inline. Without seeing one of these phrases you must NOT inline on your own; do not invent an override the user never said. [/workflow-state:no_task]

Phase 1: Plan

1.0 Create task [required · once] (just task.py create; status enters planning)
1.1 Requirement exploration [required · repeatable]
1.2 Research [optional · repeatable]
1.3 Configure context [required · once] — Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi
1.4 Activate task [required · once] (run task.py start; status → in_progress)
1.5 Completion criteria

[workflow-state:planning] Load the trellis-brainstorm skill and iterate on prd.md with the user. Phase 1.3 (required, once): before task.py start, you MUST curate implement.jsonl and check.jsonl — list the spec / research files sub-agents need so they get the right context injected. You may skip only if the jsonl already has agent-curated entries (the seed _example row alone doesn't count). Then run task.py start <task-dir> to flip status to in_progress. Research output must land in {task_dir}/research/*.md, written by trellis-research sub-agents. The main agent should not inline WebFetch / WebSearch — the PRD only links to research files. [/workflow-state:planning]

Phase 2: Execute

2.1 Implement [required · repeatable]
2.2 Quality check [required · repeatable]
2.3 Rollback [on demand]

[workflow-state:in_progress] Flow: trellis-implement → trellis-check → trellis-update-spec → commit (Phase 3.4) → /trellis:finish-work. Main-session default (no override): dispatch the trellis-implement / trellis-check sub-agents — the main agent does NOT edit code by default. Phase 3.4 commit (required, once): after trellis-update-spec, or whenever implementation is verifiably complete, the main agent drives the commit — state the commit plan in user-facing text, then run git commit — BEFORE suggesting /trellis:finish-work. /finish-work refuses to run on a dirty working tree (paths outside .trellis/workspace/ and .trellis/tasks/). Sub-agent self-exemption: if you are already running as trellis-implement, implement directly from the loaded task context and do NOT spawn another trellis-implement; if you are already running as trellis-check, review/fix directly and do NOT spawn another trellis-check. The default dispatch rule applies to the main session only. Sub-agent dispatch protocol (all platforms, all sub-agents EXCEPT trellis-research): When you spawn trellis-implement / trellis-check, your dispatch prompt MUST start with one line: Active task: <task path from \task.py current`>. No exceptions. On class-2 platforms (codex / copilot / gemini / qoder) the sub-agent depends on this line because there is no hook to inject task context. On class-1 platforms (claude / cursor / opencode / kiro / codebuddy / droid) the line is normally redundant — the hook injects context directly — but it serves as a critical fallback when the hook fails (Windows + Claude Code PreToolUse silent skip, --continueresume, fork distribution, hooks disabled, etc.).trellis-research` does not need this line because it operates without a task binding. Inline override (per-turn only, escape hatch for sub-agent dispatch): the user's CURRENT message MUST explicitly contain one of: "do it inline" / "no sub-agent" / "你直接改" / "别派 sub-agent" / "main session 写就行" / "不用 sub-agent". Without seeing one of these phrases you must NOT inline on your own; do not invent an override the user never said. [/workflow-state:in_progress]

Phase 3: Finish

3.1 Quality verification [required · repeatable]
3.2 Debug retrospective [on demand]
3.3 Spec update [required · once]
3.4 Commit changes [required · once]
3.5 Wrap-up reminder

[workflow-state:completed] Code committed via Phase 3.4; run /trellis:finish-work to wrap up (archive the task + record session). If you reach this state with uncommitted code, return to Phase 3.4 first — /finish-work refuses to run on a dirty working tree. task.py archive deletes any runtime session files that still point at the archived task. [/workflow-state:completed]

Rules

Identify which Phase you're in, then continue from the next step there
Run steps in order inside each Phase; [required] steps can't be skipped
Phases can roll back (e.g., Execute reveals a prd defect → return to Plan to fix, then re-enter Execute)
Steps tagged [once] are skipped if the output already exists; don't re-run

Skill Routing

When a user request matches one of these intents, load the corresponding skill (or dispatch the corresponding sub-agent) first — do not skip skills.

[Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

User intent	Route
Wants a new feature / requirement unclear	`trellis-brainstorm`
About to write code / start implementing	Dispatch the `trellis-implement` sub-agent per Phase 2.1
Finished writing / want to verify	Dispatch the `trellis-check` sub-agent per Phase 2.2
Stuck / fixed same bug several times	`trellis-break-loop`
Spec needs update	`trellis-update-spec`

Why trellis-before-dev is NOT in this table: you are not the one writing code — the trellis-implement sub-agent is. Sub-agent platforms get spec context via implement.jsonl injection / prelude, not via the main thread loading trellis-before-dev.

[/Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

[Kilo, Antigravity, Windsurf]

User intent	Skill
Wants a new feature / requirement unclear	`trellis-brainstorm`
About to write code / start implementing	`trellis-before-dev` (then implement directly in the main session)
Finished writing / want to verify	`trellis-check`
Stuck / fixed same bug several times	`trellis-break-loop`
Spec needs update	`trellis-update-spec`

[/Kilo, Antigravity, Windsurf]

DO NOT skip skills

[Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

What you're thinking	Why it's wrong
"This is simple, I'll just code it in the main thread"	Dispatching `trellis-implement` is the cheap path; skipping it tempts you to write code in the main thread and lose spec context — sub-agents get `implement.jsonl` injected, you don't
"I already thought it through in plan mode"	Plan-mode output lives in memory — sub-agents can't see it; must be persisted to prd.md
"I already know the spec"	The spec may have been updated since you last read it; the sub-agent gets the fresh copy, you may not
"Code first, check later"	`trellis-check` surfaces issues you won't notice yourself; earlier is cheaper

[/Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

[Kilo, Antigravity, Windsurf]

What you're thinking	Why it's wrong
"This is simple, just code it"	Simple tasks often grow complex; `trellis-before-dev` takes under a minute and loads the spec context you'll need
"I already thought it through in plan mode"	Plan-mode output lives in memory — must be persisted to prd.md before code
"I already know the spec"	The spec may have been updated since you last read it; read again
"Code first, check later"	`trellis-check` surfaces issues you won't notice yourself; earlier is cheaper

[/Kilo, Antigravity, Windsurf]

Loading Step Detail

At each step, run this to fetch detailed guidance:

python ./.trellis/scripts/get_context.py --mode phase --step <step>
# e.g. python ./.trellis/scripts/get_context.py --mode phase --step 1.1

Phase 1: Plan

Goal: figure out what to build, produce a clear requirements doc and the context needed to implement it.

1.0 Create task `[required · once]`

Create the task directory (status enters planning, the session active-task pointer auto-targets the new task when session identity is available):

python ./.trellis/scripts/task.py create "<task title>" --slug <name>

--slug is the human-readable name only. Do not include the MM-DD- date prefix; task.py create adds that prefix automatically.

After this command succeeds, the per-turn breadcrumb auto-switches to [workflow-state:planning], telling the AI to enter the brainstorm + jsonl curation phase.

⚠️ Run only create here — do not also run start. start flips status to in_progress, which switches the breadcrumb to the implementation phase before brainstorm + jsonl are done — the AI will silently skip them. Save start for step 1.4, after jsonl curation is complete.

Skip when python ./.trellis/scripts/task.py current --source already points to a task.

1.1 Requirement exploration `[required · repeatable]`

Load the trellis-brainstorm skill and explore requirements interactively with the user per the skill's guidance.

The brainstorm skill will guide you to:

Ask one question at a time
Prefer researching over asking the user
Prefer offering options over open-ended questions
Update prd.md immediately after each user answer

Return to this step whenever requirements change and revise prd.md.

1.2 Research `[optional · repeatable]`

Research can happen at any time during requirement exploration. It isn't limited to local code — you can use any available tool (MCP servers, skills, web search, etc.) to look up external information, including third-party library docs, industry practices, API references, etc.

[Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

Spawn the research sub-agent:

Agent type: trellis-research
Task description: Research
Key requirement: Research output MUST be persisted to {TASK_DIR}/research/

[/Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

[Kilo, Antigravity, Windsurf]

Do the research in the main session directly and write findings into {TASK_DIR}/research/.

[/Kilo, Antigravity, Windsurf]

Research artifact conventions:

One file per research topic (e.g. research/auth-library-comparison.md)
Record third-party library usage examples, API references, version constraints in files
Note relevant spec file paths you discovered for later reference

Brainstorm and research can interleave freely — pause to research a technical question, then return to talk with the user.

Key principle: Research output must be written to files, not left only in the chat. Conversations get compacted; files don't.

1.3 Configure context `[required · once]`

[Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

Curate implement.jsonl and check.jsonl so the Phase 2 sub-agents get the right spec context. These files were seeded on task create with a single self-describing _example line; your job here is to fill in real entries.

Location: {TASK_DIR}/implement.jsonl and {TASK_DIR}/check.jsonl (already exist).

Format: one JSON object per line — {"file": "<path>", "reason": "<why>"}. Paths are repo-root relative.

What to put in:

Spec files — .trellis/spec/<package>/<layer>/index.md and any specific guideline files (error-handling.md, conventions.md, etc.) relevant to this task
Research files — {TASK_DIR}/research/*.md that the sub-agent will need to consult

What NOT to put in:

Code files (src/**, packages/**/*.ts, etc.) — those are read by the sub-agent during implementation, not pre-registered here
Files you're about to modify — same reason

Split between the two files:

implement.jsonl → specs + research the implement sub-agent needs to write code correctly
check.jsonl → specs for the check sub-agent (quality guidelines, check conventions, same research if needed)

How to discover relevant specs:

python ./.trellis/scripts/get_context.py --mode packages

Lists every package + its spec layers with paths. Pick the entries that match this task's domain.

How to append entries:

Either edit the jsonl file directly in your editor, or use:

python ./.trellis/scripts/task.py add-context "$TASK_DIR" implement "<path>" "<reason>"
python ./.trellis/scripts/task.py add-context "$TASK_DIR" check "<path>" "<reason>"

Delete the seed _example line once real entries exist (optional — it's skipped automatically by consumers).

Skip when: implement.jsonl has agent-curated entries (the seed row alone doesn't count).

[/Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

[Kilo, Antigravity, Windsurf]

Skip this step. Context is loaded directly by the trellis-before-dev skill in Phase 2.

[/Kilo, Antigravity, Windsurf]

1.4 Activate task `[required · once]`

Once prd.md is complete and 1.3 jsonl curation is done, flip the task status to in_progress:

python ./.trellis/scripts/task.py start <task-dir>

After this command succeeds, the breadcrumb auto-switches to [workflow-state:in_progress], and the rest of Phase 2 / 3 follows.

If task.py start errors with a session-identity message (no context key from hook input, TRELLIS_CONTEXT_ID, or platform-native session env), follow the hint in the error to set up session identity, then retry.

1.5 Completion criteria

Condition	Required
`prd.md` exists	✅
User confirms requirements	✅
`task.py start` has been run (status = in_progress)	✅
`research/` has artifacts (complex tasks)	recommended
`info.md` technical design (complex tasks)	optional

[Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

| implement.jsonl has agent-curated entries (not just the seed row) | ✅ |

[/Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

Phase 2: Execute

Goal: turn the prd into code that passes quality checks.

2.1 Implement `[required · repeatable]`

[Claude Code, Cursor, OpenCode, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

Spawn the implement sub-agent:

Agent type: trellis-implement
Task description: Implement the requirements per prd.md, consulting materials under {TASK_DIR}/research/; finish by running project lint and type-check
Dispatch prompt guard: Tell the spawned agent it is already the trellis-implement sub-agent and must implement directly, not spawn another trellis-implement / trellis-check.

The platform hook/plugin auto-handles:

Reads implement.jsonl and injects the referenced spec files into the agent prompt
Injects prd.md content

[/Claude Code, Cursor, OpenCode, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

[Codex]

Spawn the implement sub-agent:

Agent type: trellis-implement
Task description: Implement the requirements per prd.md, consulting materials under {TASK_DIR}/research/; finish by running project lint and type-check
Dispatch prompt guard: The prompt MUST start with Active task: <task path>, then explicitly say the spawned agent is already trellis-implement and must implement directly without spawning another trellis-implement / trellis-check.

The Codex sub-agent definition auto-handles the context load requirement:

Resolves the active task with task.py current --source, then reads prd.md and info.md if present
Reads implement.jsonl and requires the agent to load each referenced spec file before coding

[/Codex]

[Kiro]

Spawn the implement sub-agent:

Agent type: trellis-implement
Task description: Implement the requirements per prd.md, consulting materials under {TASK_DIR}/research/; finish by running project lint and type-check
Dispatch prompt guard: Tell the spawned agent it is already the trellis-implement sub-agent and must implement directly, not spawn another trellis-implement / trellis-check.

The platform prelude auto-handles the context load requirement:

Reads implement.jsonl and injects the referenced spec files into the agent prompt
Injects prd.md content

[/Kiro]

[Kilo, Antigravity, Windsurf]

Load the trellis-before-dev skill to read project guidelines
Read {TASK_DIR}/prd.md for requirements
Consult materials under {TASK_DIR}/research/
Implement the code per requirements
Run project lint and type-check

[/Kilo, Antigravity, Windsurf]

2.2 Quality check `[required · repeatable]`

[Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

Spawn the check sub-agent:

Agent type: trellis-check
Task description: Review all code changes against spec and prd; fix any findings directly; ensure lint and type-check pass
Dispatch prompt guard: Tell the spawned agent it is already the trellis-check sub-agent and must review/fix directly, not spawn another trellis-check / trellis-implement.

The check agent's job:

Review code changes against specs
Auto-fix issues it finds
Run lint and typecheck to verify

[/Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini, Qoder, CodeBuddy, Copilot, Droid, Pi]

[Kilo, Antigravity, Windsurf]

Load the trellis-check skill and verify the code per its guidance:

Spec compliance
lint / type-check / tests
Cross-layer consistency (when changes span layers)

If issues are found → fix → re-check, until green.

[/Kilo, Antigravity, Windsurf]

2.3 Rollback `[on demand]`

check reveals a prd defect → return to Phase 1, fix prd.md, then redo 2.1
Implementation went wrong → revert code, redo 2.1
Need more research → research (same as Phase 1.2), write findings into research/

Phase 3: Finish

Goal: ensure code quality, capture lessons, record the work.

3.1 Quality verification `[required · repeatable]`

Load the trellis-check skill and do a final verification:

Spec compliance
lint / type-check / tests
Cross-layer consistency (when changes span layers)

If issues are found → fix → re-check, until green.

3.2 Debug retrospective `[on demand]`

If this task involved repeated debugging (the same issue was fixed multiple times), load the trellis-break-loop skill to:

Classify the root cause
Explain why earlier fixes failed
Propose prevention

The goal is to capture debugging lessons so the same class of issue doesn't recur.

3.3 Spec update `[required · once]`

Load the trellis-update-spec skill and review whether this task produced new knowledge worth recording:

Newly discovered patterns or conventions
Pitfalls you hit
New technical decisions

Update the docs under .trellis/spec/ accordingly. Even if the conclusion is "nothing to update", walk through the judgment.

3.4 Commit changes `[required · once]`

The AI drives a batched commit of this task's code changes so /finish-work can run cleanly afterwards. Goal: produce work commits FIRST, then bookkeeping (archive + journal) commits land after — never interleaved.

Step-by-step:

Inspect dirty state:
```
git status --porcelain
```
Snapshot every dirty path. If the working tree is clean, skip to 3.5.
Learn commit style from recent history (so drafted messages blend in):
```
git log --oneline -5
```
Note the prefix convention (feat: / fix: / chore: / docs: ...), language (中文/English), and length style.
Classify dirty files into two groups:
- AI-edited this session — files you wrote/edited via Edit/Write/Bash tool calls in this session. You know what changed and why.
- Unrecognized — dirty files you did NOT touch this session (could be the user's manual edits, leftover WIP from a previous session, or unrelated work). Do NOT silently include these.
Draft a commit plan. Group AI-edited files into logical commits (1 commit per coherent change unit, not 1 commit per file). Each entry: <commit message> + file list. List unrecognized files separately at the bottom.

Present the plan once, ask for one-shot confirmation. Format:

Proposed commits (in order):
  1. <message>
     - <file>
     - <file>
  2. <message>
     - <file>

Unrecognized dirty files (NOT in any commit — confirm include/exclude):
  - <file>
  - <file>

Reply 'ok' / '行' to execute. Reply with edits, or '我自己来' / 'manual' to abort.

On confirmation: run git add <files> + git commit -m "<msg>" for each batch in order. Do not amend. Do not push.
On rejection (user replies "不行" / "我自己来" / "manual" / any pushback on the plan): stop. Do not attempt a second plan. The user will commit by hand; you skip ahead to 3.5 once they confirm.

Rules:

No git commit --amend anywhere — three-stage three-commit flow (work commits → archive commit → journal commit).
Never push to remote in this step.
If the user wants different message wording but accepts the file grouping, edit the message and re-confirm once — but if they reject the grouping, exit to manual mode.
The batched plan is one prompt; do not prompt per commit.

3.5 Wrap-up reminder

After the above, remind the user they can run /finish-work to wrap up (archive the task, record the session).

Customizing Trellis (for forks)

This section is for developers who want to modify the Trellis workflow itself. All customization is done by editing this file; the scripts are parsers only.

Changing what a step means

Edit the corresponding step's walkthrough body in the Phase 1 / 2 / 3 sections above. Critical constraint: if you change a step's [required · once] marker or add a new [required · once] step, you MUST also add a matching enforcement line to that phase's [workflow-state:STATUS] tag block — otherwise the per-turn breadcrumb omits the reinforcement, and the AI silently skips the step. The regression tests assert this.

All 4 tag blocks live in the ## Phase Index section above, immediately after each phase summary:

Scope	Corresponding tag
No active task (before Phase 1)	`[workflow-state:no_task]` (after the Phase Index ASCII art)
All of Phase 1 (task created → ready for implementation)	`[workflow-state:planning]` (after Phase 1 summary)
Phase 2 + Phase 3.1–3.4 (implementation + check + wrap-up)	`[workflow-state:in_progress]` (after Phase 2 summary)
After Phase 3.5 (archived)	`[workflow-state:completed]` (after Phase 3 summary; currently DEAD)

Changing the per-turn prompt text

Directly edit the body of the corresponding [workflow-state:STATUS] block. After editing, run trellis update (if you're a template maintainer) or restart your AI session (if you're customizing your own project) — no script changes required.

Adding a custom status

Add a new block:

[workflow-state:my-status]
your per-turn prompt text
[/workflow-state:my-status]

Constraints:

STATUS charset: [A-Za-z0-9_-]+ (underscores and hyphens allowed, e.g. in-review, blocked-by-team)
A lifecycle hook must write task.json.status to your custom value, otherwise the tag is never read
Lifecycle hooks live in task.json.hooks.after_* and bind to one of after_create / after_start / after_finish / after_archive

Adding a lifecycle hook

Add a hooks field to your task.json:

{
  "hooks": {
    "after_finish": [
      "your-script-or-command-here"
    ]
  }
}

Supported events: after_create / after_start / after_finish / after_archive. Note that after_finish ≠ a status change (it only clears the active-task pointer); use after_archive for "task is done" notifications.

Full contract

For the workflow state machine's runtime contract, the locations of all status writers, pseudo-statuses (no_task / stale_<source_type>), the hook reachability matrix, and other deep details, see:

.trellis/spec/cli/backend/workflow-state-contract.md — runtime contract + writer table + test invariants
.trellis/scripts/inject-workflow-state.py — actual parser (reads workflow.md only, no embedded text)

33 KiB Raw Permalink Blame History Unescape Escape

Development Workflow

Core Principles

Trellis System

Developer Identity

Spec System

Task System

Workspace System

Context Script

Phase Index

Phase 1: Plan

Phase 2: Execute

Phase 3: Finish

Rules

Skill Routing

DO NOT skip skills

Loading Step Detail

Phase 1: Plan

1.0 Create task [required · once]

1.1 Requirement exploration [required · repeatable]

1.2 Research [optional · repeatable]

1.3 Configure context [required · once]

1.4 Activate task [required · once]

1.5 Completion criteria

Phase 2: Execute

2.1 Implement [required · repeatable]

2.2 Quality check [required · repeatable]

2.3 Rollback [on demand]

Phase 3: Finish

3.1 Quality verification [required · repeatable]

3.2 Debug retrospective [on demand]

3.3 Spec update [required · once]

3.4 Commit changes [required · once]

3.5 Wrap-up reminder

Customizing Trellis (for forks)

Changing what a step means

Changing the per-turn prompt text

Adding a custom status

Adding a lifecycle hook

Full contract

33 KiB

Raw Permalink Blame History

1.0 Create task `[required · once]`

1.1 Requirement exploration `[required · repeatable]`

1.2 Research `[optional · repeatable]`

1.3 Configure context `[required · once]`

1.4 Activate task `[required · once]`

2.1 Implement `[required · repeatable]`

2.2 Quality check `[required · repeatable]`

2.3 Rollback `[on demand]`

3.1 Quality verification `[required · repeatable]`

3.2 Debug retrospective `[on demand]`

3.3 Spec update `[required · once]`

3.4 Commit changes `[required · once]`