--- description: "Multi-agent workflow for the current worktree: plan, test, implement, commit" agent: build --- You are executing the multi-agent workflow inside the worktree this opencode session was started from. Run all phases without waiting for user input. The user has walked away. **Prerequisites (the user handles before launching opencode):** - A git worktree is checked out for the issue's feature branch - `opencode` was launched from the root of that worktree - `TODO.md` is committed to the repo and present at `./TODO.md` **Task reference:** $ARGUMENTS If `$ARGUMENTS` is empty, stop immediately: "Usage: `/workflow [base-branch]` (e.g. `/workflow ABC-1`). The ID must exist in `./TODO.md`. Base branch defaults to `main` (then `master`)." Parse `$ARGUMENTS`: the first whitespace-separated token is the issue ID, an optional second token overrides the base branch. --- ## Phase 1: Sanity Check 1. Verify CWD is a non-bare git worktree: `git rev-parse --is-bare-repository 2>/dev/null` must output `false`. If not, stop: "Workflow must be run from a non-bare worktree (the directory opencode was launched in)." 2. Verify `./TODO.md` exists. If not, stop: "TODO.md not found in the current worktree. Commit a TODO.md to the repo first." 3. Verify HEAD is not detached: `git symbolic-ref --short HEAD` must succeed. If it fails, stop: "Cannot run on a detached HEAD. Check out a feature branch first." 4. Capture the current branch: `BRANCH_NAME="$(git symbolic-ref --short HEAD)"`. 5. Resolve the base branch (`BASE_BRANCH`): - If `$ARGUMENTS` provided a second token, use it. - Else if `git rev-parse --verify --quiet main` succeeds, use `main`. - Else if `git rev-parse --verify --quiet master` succeeds, use `master`. - Else stop: "Could not determine base branch (no `main` or `master`). Pass it as the second argument: `/workflow `." 6. Verify the current branch is not the base branch: if `BRANCH_NAME == BASE_BRANCH`, stop: "Cannot run workflow on the base branch (`$BASE_BRANCH`). Switch to a feature branch first." --- ## Phase 2: Issue Context Dispatch `@pm` to read `./TODO.md` (live filesystem mode) and fetch the issue matching the parsed ID: - Issue title, description, acceptance criteria - Labels and priority - Existing status If the issue does not exist or `@pm` fails, stop with error. If the issue's status is `Backlog` or `Todo`, ask `@pm` to set it to `In Progress` (this edit will be staged in Phase 9 alongside other TODO.md updates). --- ## Phase 3: Plan Analyze the codebase. Create a detailed implementation plan addressing the issue's requirements and acceptance criteria. The plan should include: - Problem summary (from issue context) - Proposed approach with rationale - Files to modify (with brief description of changes) - New files to create - Risks and open questions - **Test Design (conditional — include for non-trivial tasks):** - Key behaviors to verify (what tests should assert) - Edge cases and error conditions worth testing - What explicitly should NOT be tested (prevents bloat) - Testability concerns (heavy external deps, GPU-only paths, etc.) **Include Test Design for:** Public API changes, bug fixes with behavioral impact, new features with business logic, multi-module changes. **Skip Test Design for:** Config-only changes, decorator swaps, import reorganization, documentation. When skipped, `@test` derives test cases directly from acceptance criteria. --- ## Phase 4: Review Plan Dispatch `@check` and `@simplify` in parallel to review the plan. Reviewers should evaluate testability: - `@check`: Is the design testable? Are the right behaviors identified? (Review Framework §8) - `@simplify`: Is the test scope appropriate? Over-testing proposed? **Merge rules:** - `@check` safety/correctness findings are hard constraints - If `@simplify` recommends removing something `@check` flags as needed, `@check` wins - Note conflicts explicitly **Review loop (max 3 cycles):** 1. Send plan to both reviewers 2. Merge findings 3. If verdict is ACCEPTABLE from both (or JUSTIFIED COMPLEXITY from `@simplify`): proceed to Phase 5 4. If BLOCK or NEEDS WORK: revise the plan addressing findings, then re-review 5. **Convergence detection:** if reviewers return the same findings as the previous cycle, stop the loop early 6. If still unresolved after 3 cycles: note unresolved blockers and proceed anyway (they will be documented in the workflow summary and commit message) --- ## Phase 5: Split into Tasks Break the approved plan into discrete tasks for `@make`. Each task needs: | Required | Description | |----------|-------------| | **Task** | Clear description of what to implement | | **Acceptance Criteria** | Specific, testable criteria (checkbox format) | | **Code Context** | Actual code snippets from the codebase, not just file paths | | **Files to Modify** | Explicit list, mark new files with "(create)" | | **Test File** | Path for test file. **Pick the pattern that matches the project's language** — see "Test File Path by Language" below. | ### Test File Path by Language The test file path must follow the language's actual test layout. **Do not invent paths that look colocated but aren't valid for the language** (e.g. `src/tests/test_.rs` is *not* a Rust test location — it's a regular `src/` submodule). - **Python** - Colocated: `/tests/test_.py (create)` - Top-level: `tests/test_.py (create)` - **Rust** - Crate-level integration tests: `tests/.rs (create)` (or, in a workspace, `/tests/.rs`). - **If the test references not-yet-existing public API**, the task automatically requires a **stub-first `@make` pre-pass** before `@test` runs (see Phase 6 → "Rust integration TDD: stub-first"). Plan for two `@make` dispatches per such task: stub pass, then body pass. - **Unit-test-only tasks (in-source `#[cfg(test)] mod tests`):** mark the task as `NOT_TESTABLE` with reason `Rust unit-only` — `@test` cannot write inside production source. `@make` writes those inline as part of its production change. - **Polyglot Nix flake** - Match the host language of the code under change (Python or Rust rules above), wrapping commands in `nix develop -c …` per the agents' devshell rule. Include **Integration Contracts** when a task adds/changes function signatures, APIs, config keys, or has dependencies on other tasks. Include **Test Design** from Phase 3 when available, attached to the relevant task(s). **Task size:** ~10-30 minutes each, single coherent change, clear boundaries. ### Split Heuristic — when in doubt, split A task must be **split** if any of the following apply: - It touches more than two distinct concerns (e.g. *constants + new component + sprite spawn + new system + main wiring* is **five** concerns — at least three tasks). - It changes more than ~50 lines across more than 2 files. - It mixes data/structural changes (constants, types, components) with runtime/system changes (new ECS systems, scheduling, render loops). - It mixes pure-logic changes (math helpers) with stateful changes (queries, world mutation). - It mixes new APIs with their first call sites in the same task. When a task fails the heuristic, split into: 1. **Foundations** — new constants, types, components (no behavior change yet). 2. **Implementation** — the actual production logic, calling the foundations. 3. **Wiring** — registration in `main.rs` / `lib.rs` / app-builder. Each split is dispatched separately to `@make` and verified before the next. ### Code Context Anti-patterns The **Code Context** field exists so `@make` can find the seam to modify, not so it can read off a finished answer. Strictly follow: - **Provide:** the existing code being replaced (verbatim), the surrounding ~5–10 lines of context, function signatures of helpers `@make` will need to call, the file's relevant import block. - **Do NOT provide:** a complete drop-in replacement, the new function bodies, the test bodies (those come from `@test` or — for unit-only Rust — from `@make` itself per Phase 6), or any "here is what to write" code block longer than ~5 lines. If the task is so well-specified that you've already written the implementation, the task is too small for `@make` (apply it directly) or you've over-determined the design (revisit Phase 3). ### Finalized-Text Rule Each task spec must be **finalized** before dispatch — single-author text with no contradictions. **Forbidden in dispatch prompts:** - "Actually, that's wrong — let me correct…" - "Wait, let me revise…" - Two versions of the same code block with one labelled "corrected" - Open questions or ambiguities the orchestrator hasn't resolved If you find yourself revising while writing the spec, stop, redo the spec from scratch with the corrected understanding, and only then dispatch. `@make` is a fresh-context implementer; it cannot reliably resolve which of two contradictory drafts is canonical. --- ## Phase 6: Write Tests For each task from Phase 5, dispatch `@test` with: - The task spec (acceptance criteria, code context, files to modify) - The Test Design section from the plan (if provided) - The test file path to create (following colocated pattern) `@test` writes failing tests and verifies RED with structured failure codes. **Post-step file gate (MANDATORY):** Before dispatching `@test`, snapshot the current changed files: ```bash git diff --name-only > /tmp/pre_test_baseline.txt ``` After `@test` completes, validate only NEW changes: ```bash git diff --name-only | comm -23 - /tmp/pre_test_baseline.txt > /tmp/test_new_files.txt ``` All new files must match the project's test patterns: - Python: `**/test_*.py`, `**/*_test.py`, `**/conftest.py` (new only), `**/test_data/**`, `**/test_fixtures/**` - Rust: `tests/**/*.rs`, `**/tests/**/*.rs` (workspace-style `/tests/...`), `**/test_data/**`, `**/test_fixtures/**` **Anti-patterns — discard the output even if the glob matches:** - Anything under `src/` for Rust (e.g. `src/tests/foo.rs`, `src/**/tests/...`). `src/tests/` is a regular module path under `src/`, not a Rust test location, and `@test` cannot wire it up via `mod` declarations in production source. Such paths indicate the task spec gave a wrong test path — escalate, don't accept the file. If any non-matching file appears, or any anti-pattern matches: discard `@test` output, report violation. **Decision table — handling `@test` results:** | Condition | Action | |-----------|--------| | `TESTS_READY` + `escalate_to_check: false` | Proceed to Phase 7 | | `TESTS_READY` + `escalate_to_check: true` | Route tests to `@check` for light review. `@check` diagnoses, caller routes fixes to `@test`. Then proceed. | | `NOT_TESTABLE` (general reasons) | Route to `@check` for sign-off on justification. If approved, task goes to `@make` without tests. | | `NOT_TESTABLE` reason `Rust unit-only` | See "Rust unit-only routing" below. **Do not** include test code in the `@make` spec; pass test specs only. | | `BLOCKED` | Investigate. May need to revise task spec or plan. | | Test passes immediately | Investigate — behavior may already exist. Task spec may be wrong. | ### Rust unit-only routing When `@test` returns `NOT_TESTABLE: Rust unit-only` (the implementation needs in-source `#[cfg(test)] mod tests` blocks that `@test` is forbidden from writing), the orchestrator must: 1. Get `@check`'s sign-off on the justification (no integration-test seam exists). 2. Build the `@make` spec with **test specifications**, not test code: - "Add `#[cfg(test)] mod foo_tests` at the bottom of `` exercising:" - For each behavior, a one-line description: input → expected output, edge case to cover, error path to assert. - Where applicable, name the function under test and the assertion type (`assert_eq!`, `assert!`, panic on invalid input). 3. **Forbidden in the `@make` spec:** complete `#[test] fn …` bodies, full module blocks, or any `@test`-style RED-verified test code. `@make` writes the inline tests itself based on the spec. 4. After `@make` completes, the orchestrator runs the test suite once to confirm RED→GREEN evidence and includes it in the workflow summary. This keeps the agents in their lanes: `@test` never writes inside `src/`, `@make` writes both the tests and the production code in a single coherent change, and the orchestrator sees explicit test pass evidence. ### Rust integration TDD: stub-first (mandatory) Rust integration tests live in a separate test crate (`tests/.rs`) that imports from `lib.rs`. Any test referencing not-yet-existing public API can only RED at *build* time, which masks assertion diagnostics. To avoid this, **for every Rust task whose `@test` step writes an integration test against public API that does not yet exist**, dispatch a stub-first `@make` pass *before* `@test` runs: **Stub pass (split from Phase 7's body pass):** 1. Dispatch `@make` in **standard mode** (no tests exist yet) with this exact scope: - **Goal:** add the planned public API as `todo!()`-bodied stubs so the integration test will compile. - **Files to modify:** `src/lib.rs` (add `pub mod …;` declarations) plus any new `src/.rs` files containing the stub functions/structs. - **Stubs only:** every function body is exactly `todo!()`. Every method body is exactly `todo!()`. Public structs may use `pub struct Foo;` or `pub struct Foo { /* fields TBD */ }` — but no logic. - **Signatures must match the planned final API exactly** (return types, lifetimes, generics) — otherwise the integration test will mismatch later. Lift signatures from the Phase 3 plan / Phase 5 task spec. - **Acceptance criteria:** `cargo check` (wrapped in `nix develop -c …` if the project has a devshell) passes; no test command is run. - **Code Context Anti-patterns still apply:** the stub pass is small and finalized — no draft bodies, no contradictory signatures. 2. Verify `cargo check` passed in `@make`'s output. If not, fix and re-dispatch the stub pass before continuing. 3. Dispatch `@test` as normal. The integration test now compiles; running it panics on `todo!()` at runtime, which is a clean `MISSING_BEHAVIOR` RED with a stack trace — far better than the build-error-RED form. 4. Continue to Phase 7's body pass (`@make` in TDD mode), where the same files are revisited and the `todo!()` bodies are replaced. **This routing is mandatory** for new public API in Rust. It is **not** required when the integration test exercises an existing public API (e.g. a behavior fix where the function already exists) — in that case `@test` runs directly and `@make` modifies the body in Phase 7. The stub pass and the body pass each produce their own atomic commit (per Phase 9 rules): `feat(): scaffold with todo!() stubs` followed by `feat(): implement ` (or whichever conventional type fits). **Parallelism:** Independent tasks can have tests written in parallel. **Constraint:** `@test` must not modify existing conftest.py files (prevents collision during parallel execution). --- ## Phase 7: Implement Execute each task by dispatching `@make` with: - The task spec (from Phase 5, finalized — see Finalized-Text Rule) - Relevant code context (seam-revealing snippets only — see Code Context Anti-patterns) - **Pre-written failing tests and handoff from `@test` (if TESTS_READY)** ### Pre-Dispatch Validation (MANDATORY) Before sending the spec to `@make`, scan it and reject (revise, then retry) if any of the following are present: | Check | Why it matters | |---|---| | `bash -c`, `sh -c`, `zsh -c`, `fish -c` (anywhere, including inside `nix develop --command bash -c …`) | `@make`'s sandbox denies all `*-c` shell invocations and any nested `bash` would bypass the per-command allowlist. Replace with one direct command per line: `nix develop -c cargo check`, `nix develop -c cargo test`, etc. | | `nix develop --command bash` / `nix develop -c bash` / `nix develop -c sh` | Same — the inner shell escapes the sandbox. Wrap each toolchain command directly. | | Any `cd && …` | `@make` cannot `cd`. Rewrite to use absolute paths or `git -C ` for git operations (and `@make` doesn't run git anyway). | | Code blocks longer than ~5 lines under "Code Context" or labelled as the answer | Violates Code Context Anti-patterns. Trim to the seam. | | Two versions of the same code, "actually let me correct…", or open questions | Violates the Finalized-Text Rule. Redo the spec. | | Test bodies inside the `@make` spec when tests are coming from `@test` | The TDD handoff already provides them; duplicating creates conflict. | If any check trips, **do not dispatch.** Fix the spec and re-validate. Repeated trips on the same task signal a Phase 5 split problem — go back and split. `@make` runs in TDD mode when tests are provided: 1. Entry validation: run tests, verify RED, check failure codes match handoff 2. Implement minimal code to make tests pass (GREEN) 3. Regression check on broader area 4. Refactor while keeping green 5. Report RED→GREEN evidence **Escalation:** If `@make` flags test quality concerns during entry validation: 1. `@make` reports the issue to caller 2. Caller routes to `@check` for diagnosis 3. `@check` reports findings 4. Caller routes to `@test` for fixes 5. Fixed tests return to `@make` For NOT_TESTABLE tasks, `@make` runs in standard mode. After all tasks complete, verify overall integration: - Run the project's test suite if available - Run linting/type checking if configured - Fix any integration issues between tasks --- ## Phase 8: Final Review Dispatch `@check` and `@simplify` in parallel to review the full implementation (all changes across all files). Provide reviewers with: - The original plan - The full diff (`git diff "$BASE_BRANCH"...HEAD`) - Any decisions or deviations from the plan **Review loop (max 3 cycles):** 1. Send implementation to both reviewers 2. Merge findings (same precedence rules as Phase 4) 3. If ACCEPTABLE: proceed to Phase 9 4. If issues found: fix them directly (no need to re-dispatch `@make` for small fixes), then re-review 5. **Convergence detection:** same findings twice = stop loop early 6. If unresolved after 3 cycles: document blockers, proceed to commit anyway --- ## Phase 9: Commit and Wrap Up The workflow is forge-agnostic. It commits locally and stops. **Do not push, and do not open a pull/merge request** — the user chooses their forge and review workflow manually. ### Commit Code Changes - Stage code changes only. **Do not stage `TODO.md`** (committed separately below) and **do not stage `.opencode/workflow-summary.md`** (intentionally never committed — see Local Summary). - Write a conventional commit message summarizing the implementation. Reference the TODO.md issue ID in the body (e.g. `Refs: ABC-1`). - If changes are large/varied, use multiple atomic commits (one per logical unit) ### TODO Update - Dispatch `@pm` against `./TODO.md` (live filesystem mode). Ask it to: - Set **Branch** to `$BRANCH_NAME` - Set **Status** to `In Review` - Add a comment with the branch name, latest commit SHA, and a one-line summary - If acceptance-criteria checkboxes were addressed by the implementation, ask `@pm` to check them off - Commit the TODO.md change as a separate atomic commit: `chore(todo): update status and progress` ### Local Summary - Write `.opencode/workflow-summary.md` in the worktree with: - **Run timestamp** — capture it from the shell at write time: `date -Iseconds` (e.g. `2026-05-07T11:24:13+02:00`). **Do not** use a placeholder like `???:???:??` or "session date" — if you cannot get a real timestamp, omit the field entirely rather than fabricating one. - Issue reference and title - Branch name and final commit SHA(s) - Summary of implementation - TDD evidence (RED→GREEN per task, NOT_TESTABLE justifications) - Review outcomes (plan review + final review verdicts) - Unresolved items (if any) - Files changed - **Do not commit this file.** It is a per-run, per-branch artifact; committing it would create merge conflicts whenever multiple workflow branches are merged. Leave it untracked. Recommend the user add `.opencode/` to `.gitignore` if not already. --- ## Failure Handling At any phase, if an unrecoverable error occurs: 1. Write `.opencode/workflow-summary.md` with what was completed and what failed. Do **not** stage or commit this file. 2. If any code was written, commit it with message `wip: incomplete workflow run for `. Stage code only — exclude `.opencode/workflow-summary.md`. 3. Leave the branch and worktree intact for the user to inspect — do not push, do not delete. 4. Dispatch `@pm` against `./TODO.md` to add a comment on the issue summarising what failed. 5. Stop execution. **Never hang on interactive prompts.** If any command appears to require input, treat it as a failure and follow the above procedure.