tegwick
4ee612140b
Implements T01-T04: - tools.py: green-commit-only-equivalent tool surface (read/write/edit/ glob/grep + git status/diff/log/add+commit), path-traversal guarded. - openrouter_client.py: own minimal chat-completions client — llm-connect's OpenRouterAdapter takes a single prompt string and never surfaces tool_calls, so it can't drive a multi-turn tool-calling loop without a breaking change to its frozen Core ABC. llm-connect stays an optional dependency (pyproject.toml), not load-bearing. - loop.py: plan -> tool call -> observe -> repeat, budget- and turn-bounded, tool errors reported back to the model instead of crashing the loop. - credentials.py: own OpenBao AppRole/ambient-token acquisition, per glas-harness ADR-002 (Option B) — glas-harness does not broker this. - runner.py/hub.py: commit-verified success criterion + State Hub progress/token reporting, mirroring rein-aharness's model. 26 tests, all mocked at the httpx/subprocess boundary — no real OpenRouter or OpenBao calls made. T05 (Forgejo repo creation) stays open, deferred to the operator. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
95 lines
3.4 KiB
Markdown
95 lines
3.4 KiB
Markdown
---
|
|
id: REIN-OW-WP-0001
|
|
title: "Bootstrap: minimal open-weight agentic loop"
|
|
status: proposed
|
|
---
|
|
|
|
First working milestone for rein-openweights: prove an agentic tool-use
|
|
loop against a current open-weight model via OpenRouter/llm-connect,
|
|
comparable in scope to rein-aharness's `green-commit-only` profile, ready
|
|
to implement the glas-harness rein contract once
|
|
`glas-harness/GLAS-WP-0001-T01` defines it.
|
|
|
|
## Task: Pick the starter open-weight model + OpenRouter path
|
|
|
|
Checked `llm-connect`'s existing OpenRouter integration
|
|
(`OpenRouterAdapter.execute_prompt`): it takes a single prompt string,
|
|
builds a fixed `[system, user]` message pair itself, and never surfaces
|
|
`message.tool_calls` in its response — it cannot drive a multi-turn
|
|
tool-calling loop without a breaking change to llm-connect's frozen
|
|
Core `LLMAdapter` ABC. Decision: rein-openweights uses its own minimal
|
|
OpenRouter client (`openrouter_client.py`) for the agentic loop instead;
|
|
`tools`/`tool_choice` already pass through llm-connect's own
|
|
`OPENAI_CHAT_PASSTHROUGH_FIELDS` allow-list, confirming the request
|
|
shape is standard OpenAI-compatible function-calling, just not
|
|
round-tripped by that adapter today. Starter model is a `--model`-configurable
|
|
default (`meta-llama/llama-3.1-70b-instruct`), not hardcoded.
|
|
|
|
```task
|
|
id: REIN-OW-WP-0001-T01
|
|
status: done
|
|
priority: high
|
|
```
|
|
|
|
## Task: Minimal agentic loop
|
|
|
|
Implemented in `loop.py` + `tools.py`: plan → tool call → observe →
|
|
repeat with a hard tool allow-list matching rein-aharness's
|
|
`green-commit-only` (`read_file`/`write_file`/`edit_file`/`glob_files`/
|
|
`grep_files` + `git_status`/`git_diff`/`git_log`/`git_add_commit`, no
|
|
push/network/shell), bounded by `max_turns` and a token budget. Budget
|
|
tracker is vendored locally (`budget.py`), not `llm-connect`'s —
|
|
consistent with T01/ADR-002 keeping llm-connect optional. Path-traversal
|
|
guarded (`_resolve`); tool errors are reported back to the model as a
|
|
`role: tool` message rather than crashing the loop. 26 tests, all
|
|
mocked at the `httpx`/subprocess boundary.
|
|
|
|
```task
|
|
id: REIN-OW-WP-0001-T02
|
|
status: done
|
|
priority: high
|
|
```
|
|
|
|
## Task: Success criterion + reporting
|
|
|
|
Implemented in `runner.py`/`hub.py`: a local git commit is the sole
|
|
success signal (`RunResult.ok == committed`), State Hub progress event
|
|
(`executor_run`) and token event posted on completion via a hub module
|
|
mirroring rein-aharness's, `--no-hub` to skip. Not yet exercised against
|
|
a live State Hub call in this pass (mocked in tests) — same caveat as
|
|
rein-aharness/glas-harness's own not-yet-live-run notes elsewhere in
|
|
this rein family.
|
|
|
|
```task
|
|
id: REIN-OW-WP-0001-T03
|
|
status: done
|
|
priority: medium
|
|
```
|
|
|
|
## Task: Credential brokering
|
|
|
|
Resolved by glas-harness `docs/adr/ADR-002-credential-brokering-and-composable-reins.md`
|
|
(Option B): rein-openweights acquires its own OpenRouter credential.
|
|
Implemented in `credentials.py`, mirroring rein-aharness's mailscan.py
|
|
OpenBao AppRole/ambient-token pattern (explicit env var → AppRole
|
|
exchange → ambient token → single `kv get`). glas-harness does not
|
|
broker this.
|
|
|
|
```task
|
|
id: REIN-OW-WP-0001-T04
|
|
status: done
|
|
priority: medium
|
|
```
|
|
|
|
## Task: Forgejo repo creation
|
|
|
|
This repo is local-only. Create `coulomb/rein-openweights.git` on
|
|
Forgejo and wire the remote once T02 has something worth pushing —
|
|
coordinate with the operator (repo creation is not something this
|
|
session can do unattended).
|
|
|
|
```task
|
|
id: REIN-OW-WP-0001-T05
|
|
status: todo
|
|
priority: low
|
|
```
|