jjbrunton/Sauci
1
0 Fork 0
mirror of https://github.com/jjbrunton/Sauci.git synced 2026-10-31 18:19:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf(app): reduce redundant data fetching

Browse Source 
Share bounded database pools across API repositories, consolidate sync and chat queries, and make mobile refreshes cache-aware and foreground-aware.

Add focused regression coverage, client freshness documentation, and repository agent role configuration.
This commit is contained in:
jjbrunton committed 2026-08-29 21:47:27 +01:00
1 parent 9957fa43f2
commit c7ee8a4851
81 files changed
+4456 -1400
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/agents/routing.md
+53 -16
View File
@@ -1,21 +1,58 @@
# Agent routing and effort
Use one implementation agent by default. Add independent agents only when work is
actually separable or a risk trigger requires independent judgment.
The primary agent owns scope, acceptance criteria, task decomposition, and the
final answer. Use one implementation agent when a bounded handoff will keep noisy
execution out of the primary context. Do not pay the coordination cost for a
trivial one-file edit. Add other agents only for separable work or a risk trigger.
| Role | Default effort | Trigger | Do not use for |
|---|---|---|---|
| `repo-scout` | low | locate ownership, callers, contracts | editing or design decisions |
| `implementation` | medium | bounded product or harness change | broad architecture review |
| `test-writer` | medium | focused regression or missing contract test | rubber-stamping green output |
| `verifier` | medium | independently drive changed behavior | editing implementation |
| `database-reviewer` | medium | migrations, RLS, function/query boundaries | ordinary UI changes |
| `security-reviewer` | high | auth, RLS, crypto, secrets, payments, destructive operations | every routine change |
| `architecture-reviewer` | high | cross-cutting or hard-to-reverse decisions | local refactors |
## Cost ladder
Escalate effort only when uncertainty, blast radius, or irreversibility justifies
it. “Proactively use” is not a trigger. Verification agents return evidence and a
verdict; they do not make changes.
Project Codex defaults live in `.codex/config.toml`; task profiles live in
`.codex/agents/`. An explicit task handoff may raise or lower reasoning effort.
Procedures belong in skills. Agents read the applicable skill and nearest
`AGENTS.md`, then operate within the task's authorization.
| Role | Codex model | Default effort | Trigger | Do not use for |
|---|---|---:|---|---|
| `repo_scout` | Luna | low | locate ownership, callers, contracts | editing or design decisions |
| `implementation` | Terra | medium, overridable | bounded product or harness change | broad architecture review |
| `test_writer` | Terra | medium | focused regression or missing contract test | rubber-stamping green output |
| `verifier` | Terra | medium | independently drive implemented behavior | editing implementation |
| `database_reviewer` | Terra | high | migrations, RLS, function/query boundaries | ordinary UI changes |
| `security_reviewer` | Sol | high | auth, RLS, crypto, secrets, payments, destructive operations | every routine change |
| `architecture_reviewer` | Sol | high | cross-cutting or hard-to-reverse decisions | local refactors |
Claude profiles under `.claude/agents/` provide equivalent roles when Claude is
explicitly requested. They are not part of the normal Codex routing path.
## Implementation effort
Keep `implementation` on Terra and choose effort from the task shape:
- `low`: mechanical, fully specified, narrow change with an obvious check.
- `medium`: normal feature or bug fix with a few files and known contracts.
- `high`: ambiguous behavior, several interacting modules, concurrency, or
difficult debugging.
- `xhigh`: exceptional Terra implementation where high effort has already proved
insufficient or the change has a large but non-security blast radius.
Security and architecture risk are different jobs, not reasons to silently turn
the implementation agent into a premium generalist. Add the matching read-only
Sol reviewer and keep implementation on Terra unless the user explicitly asks for
a different model.
## Handoff contract
Every delegated task includes the objective, owned files or surface, acceptance
criteria, applicable `AGENTS.md` and skill, allowed side effects, required checks,
and the evidence to return. The agent must report changed files, commands and
results, assumptions, and blockers. The primary agent independently reviews the
diff and decides whether acceptance has been met.
Parallel agents are for independent read-heavy work or non-overlapping ownership.
Avoid concurrent edits to the same files, shared database state, fixed local
ports, or one simulator. Subagents consume additional tokens, so parallelism must
buy meaningful time or independent judgment.
Procedures belong in deterministic skills rather than agent prompts. Agents read
the nearest `AGENTS.md` and the applicable repository skill, then operate only
within the task's authorization. Verification agents return evidence and a
verdict; they do not fix implementation.