Chemenu 2.1.0 - deterministischer Wissenskompiler
Chemenu kompiliert Rohnotizen zu einem verlinkten, quellengebundenen Wiki: raw/ -> types/ + tools/ -> kb/ -> reports/. Was mechanisch ist, macht tools/wikitool; was Urteil braucht, macht ein Agent unter Contracts, deren Grenzen in Code durchgesetzt sind statt im Prompt. Dieser Commit ist der Startpunkt der oeffentlichen Historie. Die vorherige Entwicklung fand in einer privaten Instanz statt und ist nicht Teil dieses Repositorys; ihre Erzaehlung steht vollstaendig in CHANGES.md, das mit 44 Eintraegen von 0.1.0 bis 2.1.0 erhalten geblieben ist. Der mitgelieferte Korpus ist ein Testbett und eine Demo: 170 Seiten ueber den Stack selbst - Gates, Lint, Versionierung, Suche, das Wiki-Muster. Er dokumentiert das Werkzeug mit den eigenen Mitteln des Werkzeugs. Lizenz: AGPL-3.0 fuer den Stack (tools/, types/), CC-BY-4.0 fuer die Inhalte. Die Grenze zwischen beiden ist der Dateiplan, den dist export berechnet - siehe NOTICE.
This commit is contained in:
@@ -0,0 +1,77 @@
|
||||
---
|
||||
type: types/instruction.md
|
||||
name: claude-code-model-selection
|
||||
description: Which Claude model and effort level to run a Claude Code session, a spawned subagent, or a /code-review pass at for a given task in this repo.
|
||||
---
|
||||
|
||||
# Pick the Claude model and effort level for the task at hand
|
||||
|
||||
Scale the model and effort to how much judgment the task actually needs. Running everything at
|
||||
the most capable model and highest effort is safe but wasteful: the gates in [gates.md](gates.md)
|
||||
are enforced in code, not by model judgment, so a weaker model cannot bypass them - it can only
|
||||
do a worse job of the calls the gates don't cover.
|
||||
|
||||
Claude-Code-only, and imported by CLAUDE.md rather than linked from AGENTS.md: the model names,
|
||||
the `/code-review` effort dial and the `Agent` tool's `model:` override have no equivalent in the
|
||||
other harnesses this repo supports (Codex CLI, GitHub Copilot CLI, Mistral Vibe). See
|
||||
[instructions/CONTRACT.md](CONTRACT.md) for that split.
|
||||
|
||||
## When to run
|
||||
|
||||
Before spawning a subagent with an explicit `model:` override, before picking a `/code-review`
|
||||
effort level, and when the user asks which model to use - or when the session's current model is
|
||||
clearly mismatched to the task that just started.
|
||||
|
||||
Two of the three choices are the agent's to make; the session's own model is not. An agent cannot
|
||||
switch the model it is running as - that is the user's `/model` - so step 1 is a recommendation
|
||||
to *make*, not a setting to apply.
|
||||
|
||||
## Steps
|
||||
|
||||
1. **Recommend the session's model and effort by the skill in use**, when asked or when the
|
||||
mismatch is worth one sentence. Say it once and continue working either way - a session that
|
||||
argues about its own model instead of doing the task has already cost more than the model
|
||||
difference:
|
||||
|
||||
| Skill / task | Model | Effort |
|
||||
|---|---|---|
|
||||
| `wiki-status`, simple `wiki-query` lookups | Sonnet | default |
|
||||
| `wiki-lint` | Sonnet | default |
|
||||
| `wiki-ingest`, `wiki-manage`, judgment-heavy `wiki-query` | Sonnet | high |
|
||||
| Stack development: `tools/`, `types/`, `instructions/` as code | Opus | high |
|
||||
|
||||
2. **Pick a spawned subagent's model by what it does**, via the `Agent` tool's `model:`
|
||||
parameter - the values are `haiku`, `sonnet`, `opus`, `fable`:
|
||||
|
||||
- Read-only search/lookup (an `Explore` agent, or a `general-purpose` agent doing pure
|
||||
retrieval): `model: "haiku"`. No judgment call is being delegated, only retrieval.
|
||||
- A subagent that writes pages, reviews code, or decides something: leave `model:` off so it
|
||||
inherits the session's model, chosen per step 1.
|
||||
- A fork (`subagent_type: "fork"`) always inherits the parent session's model; a `model:`
|
||||
override on a fork is ignored.
|
||||
|
||||
3. **Pick a `/code-review` effort level by blast radius, not by habit.** The levels are `low`,
|
||||
`medium`, `high`, `xhigh`, `max` and `ultra` (multi-agent, in the cloud):
|
||||
|
||||
- A routine diff (a skill wording fix, an ordinary ingest's tool output): `low` or `medium` -
|
||||
fewer, high-confidence findings are enough.
|
||||
- Gate code (`run_budget.py`, `git_publish.py`, anything implementing the Mass-Update or
|
||||
Iteration gates), the compiler, or a change about to ship in a version bump: `high` and up -
|
||||
broader coverage is worth the cost when the blast radius of a missed bug is a safety gate.
|
||||
- `ultra` is user-triggered and billed separately; recommend it, never assume it.
|
||||
|
||||
## Decision points
|
||||
|
||||
- **Task spans both a mechanical step and a judgment call?** Pick by the judgment call, not the
|
||||
mechanical one - `wikitool` carries the mechanical part regardless of which model is
|
||||
supervising it.
|
||||
- **Unsure which row applies?** Default to Sonnet at high effort, not the most capable model at
|
||||
the highest effort. Under-provisioning costs one worse answer in one session; reflexively
|
||||
over-provisioning is a standing cost paid every session.
|
||||
|
||||
## Scope
|
||||
|
||||
Does not apply to non-Claude-Code harnesses - see the note above; a follow-up issue tracks
|
||||
whether and how they should decide this differently. Does not set the classifier model behind
|
||||
Claude Code's own `auto` permission mode - that is a harness internal, not a per-task choice
|
||||
this repo controls.
|
||||
Reference in New Issue
Block a user