Omar SobhandClaude Opus 5
5c2c63f8e8
Phase 4 of the plan, plus the PLAN_COMPLETE decision and the gitea_forge
cleanup from Phase 5.
THE REVIEW UI
mission_plan and mission_roster have been complete and reachable by curl
since they shipped, with zero frontend. That matters more than a missing
screen usually would: the decide step is not a convenience, it IS the
safety mechanism. Approving a plan replaces the mission's phases; approving
a roster flips it to the composed engine. A gate nobody can reach is a gate
that is always open or always shut.
MissionProposalDrawer, modelled on LevelUpDrawer which already does
load → review → decide. Reached from a mission's SETUP tab. Verified end to
end against the live backend, not just compiled: a model proposed a roster,
approval flipped the mission to `composed`, and approval on a non-draft
mission was refused.
The plan view shows each phase's done_when, and says plainly when one is
absent — a phase without a completion condition is never judged and reports
completed whatever it did, so its absence is the thing worth seeing.
AND THE DEFECT BUILDING IT FOUND
Every refusal path computed a precise reason — "the mission is running, not
a draft", "no node can boot that backend any more" — logged it to stderr,
and returned a bare {"error":"bad request"}. The person who needed the
sentence was the one clicking Approve; they got two words, and the reason
went to a server log they cannot read.
ApiError::Refused(String) carries it now. Same argument ApiError::Unavailable
was added for ("a 500 with 'internal error' sent them looking for a bug that
was not there"), one status code down. Live: the 400 now reads "this mission
is completed — a roster can only be approved while it is a draft, because
approving one rewrites how the mission will run".
PLAN_COMPLETE, decided
The Skill-Use measurement found that int-xx-marker-protocol documents
PLAN_COMPLETE and task_card_parser never implemented it, so an agent
following the skill exactly was silently ignored. Implemented rather than
removed from the skill: the planner needs a way to say it is done
specifying, and agents already emit it.
Marker ids are now strictly INT-<digits>. `starts_with("INT-")` accepted the
range form `INT-01..02` — observed live — which parsed into an id matching
no real item, so a task card appeared for something that did not exist while
the two items it covered stayed open. Rejecting is right: an ignored marker
is visible, a plausible row is not.
GITEA_FORGE, REMOVED
Named in nine places, defined in none. Harmless while provision_claw ignored
the bundle list; once the list was honoured, an undefined name became a
capability an agent is told it has and does not. Removed from seven team
templates, a workflow recipe, the auto-provision path, and a dropdown a user
could pick it from.
A new test asserts every bundle a template names is defined in the runtime
config — and it immediately found `web_fetch` in two templates I had missed
removing by hand. Same shape as the skill-binding test, one layer up.
Agents reach the forge through git over HTTPS with the ambient GITEA_TOKEN,
which is why nothing ever broke.
Full workspace suite green (106 binaries); frontend builds clean.
Co-Authored-By: Claude Opus 5 <[email protected]>
90 lines
3.1 KiB
TOML
90 lines
3.1 KiB
TOML
key = "backend"
|
|
name = "Backend"
|
|
description = "Rust backend teams — Postgres, DuckDB, graph databases, APIs, wire protocols, middleware."
|
|
stack = ["rust", "postgres", "duckdb", "graph", "api", "middleware"]
|
|
default_topology = "pipeline"
|
|
risk_profile = "coding_readwrite"
|
|
mcp_bundles = ["clawmates_door", "clawmates_skills"]
|
|
version = 1
|
|
|
|
[[roles]]
|
|
slot = "api_designer"
|
|
order_idx = 0
|
|
skills = ["decompose-int-items", "openapi-contract-first", "small-focused-commits", "api-pagination-day-1"]
|
|
system_prompt = """
|
|
You are the API DESIGNER of a Backend team.
|
|
|
|
For each INT item, specify the endpoints, request/response schemas,
|
|
error contract, and pagination behavior BEFORE any code is written.
|
|
Prefer additive changes; call out breaking ones explicitly.
|
|
"""
|
|
brain_seed = """
|
|
# API design memory seed
|
|
|
|
## Wire discipline
|
|
- Every list endpoint paginates from day 1.
|
|
- Every mutation is idempotent (accept a client-supplied key) or
|
|
documents why it can't be.
|
|
- Errors use RFC 7807 problem details.
|
|
"""
|
|
|
|
[[roles]]
|
|
slot = "db_engineer"
|
|
order_idx = 1
|
|
skills = ["postgres-migrations-forward-only", "postgres-index-selection", "postgres-explain-analyze", "write-rust-current-edition", "workspace-repo-commit-protocol"]
|
|
system_prompt = """
|
|
You are the DB ENGINEER of a Backend team.
|
|
|
|
Own migrations, indexes, transaction boundaries, and query plans.
|
|
For any new query, run EXPLAIN ANALYZE mentally (or in the sandbox
|
|
when a DB is available) and rule out seq scans on hot paths.
|
|
"""
|
|
brain_seed = """
|
|
# DB memory seed
|
|
|
|
## Migration protocol
|
|
- Every migration is forward-only + reversible-by-new-migration.
|
|
- Never DROP without a two-release deprecation window.
|
|
- CREATE INDEX CONCURRENTLY on tables > 1M rows.
|
|
|
|
## Index heuristics
|
|
- Every FK gets an index unless it's write-heavy + rarely queried.
|
|
- Partial indexes for high-cardinality boolean filters.
|
|
"""
|
|
|
|
[[roles]]
|
|
slot = "coder"
|
|
order_idx = 2
|
|
skills = ["write-rust-current-edition", "cargo-test-driven-development", "workspace-repo-commit-protocol", "int-xx-marker-protocol", "rust-error-handling", "rust-async-tokio-idioms"]
|
|
system_prompt = """
|
|
You are the CODER of a Backend team.
|
|
|
|
Implement per the API DESIGNER + DB ENGINEER handoffs. Keep the HTTP
|
|
layer thin — validation + auth at the boundary, business logic in a
|
|
service layer that's testable without a Tokio runtime.
|
|
"""
|
|
brain_seed = ""
|
|
|
|
[[roles]]
|
|
slot = "tester"
|
|
order_idx = 3
|
|
skills = ["cargo-test-driven-development", "postgres-integration-testing", "tdd-red-green-refactor"]
|
|
system_prompt = """
|
|
You are the TESTER of a Backend team.
|
|
|
|
Integration tests hit a real Postgres via testcontainers — never mock
|
|
the DB in tests that matter. Contract tests validate the OpenAPI schema
|
|
still matches the shipped handlers.
|
|
"""
|
|
brain_seed = ""
|
|
|
|
[[roles]]
|
|
slot = "committer"
|
|
order_idx = 4
|
|
skills = ["workspace-repo-commit-protocol", "small-focused-commits"]
|
|
system_prompt = """
|
|
You are the COMMITTER. Same protocol as rust_sdlc: only run when tests
|
|
pass and reviewer (implicit here) approved. Emit COMPLETED: INT-<NN>.
|
|
"""
|
|
brain_seed = ""
|