feat(wrap): add omp target (Oh My Pi) with models.yml override and unwrap (#1811)
## Description
Adds `headroom wrap omp` / `headroom unwrap omp` — a one-command wrap
for [Oh My Pi](https://www.npmjs.com/package/@oh-my-pi/pi-coding-agent)
(`omp`), the pi-mono-lineage coding agent, as proposed in #1149.
One honest correction to the issue: #1149 proposed reusing the
`ANTHROPIC_BASE_URL` redirect from `wrap claude`. During implementation
I probed that empirically and it turned out to be wrong — omp only reads
`ANTHROPIC_BASE_URL` in its web-search helper; its **chat** endpoint
comes from the model registry (`providers.anthropic.baseUrl` in
`~/.omp/agent/models.yml`). With the env var pointed at a local probe
server, omp's chat traffic still went straight to the real endpoint (0
probe hits); with a `models.yml` same-ID override, every request arrived
at the probe (9/9 hits on `/v1/messages`). A same-ID override keeps
omp's bundled Anthropic model catalog and stored credentials (both keyed
by provider id `anthropic`), so only the endpoint moves.
The wrap therefore injects a marker-fenced `providers.anthropic.baseUrl`
override into `models.yml`, snapshotting the pre-wrap file
**byte-for-byte** first, and `headroom unwrap omp` restores it exactly
(or removes the file when the wrap created it) — the same durable-wrap +
backup + unwrap contract `wrap codex` uses for `config.toml`.
Closes #1149
## Type of Change
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- `headroom/providers/omp/` (new provider slice): `models_yml_path()`
(honors `PI_CODING_AGENT_DIR`), `inject_models_override()` (yaml-merge
preserving user providers; pristine byte-for-byte backup, never
re-snapshotted while managed), `restore_models_override()` (`restored` /
`removed` / `noop`; never touches an unmanaged file),
`build_launch_env()`
- `headroom/cli/wrap.py`: `wrap omp` (mirrors the aider/vibe
`_launch_tool` shape; rtk instructions into the project's `AGENTS.md`,
which omp reads natively) and `unwrap omp` (restore models.yml + scrub
rtk block + stop proxy)
- `headroom/telemetry/context.py`: `omp` added to `_KNOWN_WRAP_AGENTS`
so the stack slug reports `wrap_omp` instead of `unknown`
- `README.md` (agent matrix row + unwrap list), `llms.txt`,
`CHANGELOG.md`
- `tests/test_cli/test_wrap_omp.py`: 16 tests (injection
fresh/merge/re-inject, restore statuses incl. unmanaged-file safety, env
passthrough, CLI wiring, unwrap flows)
## Testing
- [ ] Unit tests pass (`pytest`) — all new + `test_cli` tests pass; the
full suite carries **3 pre-existing failures** that reproduce
identically on unmodified `origin/main` (same set, same asserts — see
Test Output and the rebase-validation comment)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ uv run pytest -q # post-rebase, base 4f22cbb0
3 failed, 7723 passed, 515 skipped in 262.64s
FAILED tests/test_cli/test_wrap_claude_base_url.py::test_wrap_marker_is_stale_when_pid_reused
FAILED tests/test_rtk_session_savings.py::test_rtk_reader_returns_none_on_nonzero_exit
FAILED tests/test_rtk_session_savings.py::test_lean_ctx_reader_returns_none_on_failure_and_logs
→ all three reproduce identically on unmodified origin/main (4f22cbb0), run the
same way (same worktree + venv, sources switched): 3 failed, 7707 passed —
this branch = baseline + the 16 new tests, nothing else changes.
(The pre-rebase run against e8151f05 showed the same shape: one order-dependent
flake that also reproduced on its baseline; these are env/order-dependent.)
$ uv run pytest tests/test_cli/ -q # post-rebase
542 passed + 1 of the pre-existing failures above # includes the 16 new test_wrap_omp.py tests
$ uv run ruff check . ; echo ruff-check-exit:$?
All checks passed!
ruff-check-exit:0
$ uv run ruff format --check . # post-rebase
1 pre-existing violation: headroom/proxy/handlers/anthropic.py — flagged identically
on unmodified origin/main (not touched by this PR); every file this PR touches is clean
$ uv run mypy headroom # post-rebase; output redirected to file; exit captured
Success: no issues found in 409 source files
mypy-exit:0
```
## Real Behavior Proof
- Environment: macOS 15 (arm64, M1 Pro), Python 3.12.13 (uv venv,
editable install incl. Rust `_core`), headroom @ this branch, base
extras only (no `[ml]`), Anthropic account signed into omp. Initial
proof ran on base e8151f05 with omp 16.3.6 (`@oh-my-pi/pi-coding-agent`
via bun); re-validated after the rebase onto 4f22cbb0 with omp 16.3.11 —
fresh numbers in the rebase-validation comment.
- Exact command / steps: four scenarios, run in this order —
1. Mechanism probe (why models.yml, not env): local HTTP probe server on
`127.0.0.1:18999`; ran `omp -p "say ok" --model claude-fable-5
--no-session --no-tools` once with
`ANTHROPIC_BASE_URL=http://127.0.0.1:18999`, once with
`~/.omp/agent/models.yml` containing `providers.anthropic.baseUrl:
http://127.0.0.1:18999`.
2. One-command path: `headroom wrap omp --no-rtk --port 8790 -- -p "Read
CHANGELOG.md and count how many '### Fixed' headings it contains. Answer
with just the number." --model claude-fable-5 --no-session --max-time
180`
3. Routing stats: separate proxy on :8788, wrap with `--no-proxy`, then
`GET /stats`.
4. Restore: `headroom unwrap omp`, plus an isolated
`PI_CODING_AGENT_DIR=/tmp/omp-agent-test` run with a pre-existing user
`models.yml`, then `cmp` against the original.
- Observed result: end-to-end routing through the proxy proven for every
scenario —
- Probe: env-var run → **0 probe hits**, omp answered normally
(bypassed). models.yml run → **9 hits on `/v1/messages?beta=true`** with
real Messages bodies. This is the routing mechanism the wrap uses.
- One-command run: wrap started the proxy ("Proxy ready on
http://127.0.0.1:8790"), wrote the override (`models.yml:
providers.anthropic.baseUrl=http://127.0.0.1:8790/p/headroom-wrap-omp`),
launched omp, and omp answered **"7"** (correct — real `read` tool work
through the proxy). Proxy log for the session (3 requests,
`anthropic_messages` path):
```
PERF model=claude-fable-5 msgs=1 tok_before=36 cache_read=0
cache_write=61939 cache_hit_pct=0
PERF model=claude-fable-5 msgs=3 tok_before=796 cache_read=0
cache_write=63308 cache_hit_pct=0
PERF model=claude-fable-5 msgs=5 tok_before=935 cache_read=63308
cache_write=215 cache_hit_pct=100
```
Prompt caching survives the proxy (100% hit on the follow-up turn).
- Routing stats (:8788 session): `requests.total: 2, by_provider:
{"anthropic": 2}, by_model: {"claude-fable-5": 2}`, per-project prefix
`/p/headroom-wrap-omp` attributed.
- Unwrap: `Removed wrap-created models.yml` (file gone); isolated
pre-existing-file run: backup created, user's `my-gw` provider preserved
in the managed file, and after `unwrap omp` the restored file is
**byte-identical** (`cmp` clean).
- Compression: **not observed in this environment** — `tok_saved=0`,
`transforms=router:noop` / `too_small`. Honest reading: omp minimizes
its own tool outputs client-side (a 300-item JSON tool result reached
the proxy at only ~657 tokens) and the `[ml]` text compressor wasn't
installed; small print-mode payloads sit below crush thresholds, and
passthrough-by-default is the documented safety contract. The wrap's
value here is proven at the routing/lifecycle/cache layer; compression
numbers will match whatever the proxy does for a given content mix.
- Not tested: Windows / Linux; lean-ctx mode with omp
(`HEADROOM_CONTEXT_TOOL=lean-ctx` — `lean-ctx init --agent omp` depends
on lean-ctx recognizing the agent; failure degrades with a warning by
design); long interactive (non `-p`) sessions; `--memory` / `--learn` /
`--code-graph` flags combined with omp; OAuth-vs-API-key matrix beyond
my local account.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes — all
except the 3 documented pre-existing failures, which fail identically on
unmodified origin/main
- [x] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
N/A — terminal evidence inline above.
## Additional Notes
- The models.yml override is regenerated from the pristine backup on
every wrap, so re-running with a different `--port` updates the endpoint
idempotently and the backup is never clobbered.
- Scope note from #1149 stands: this routes omp's **Anthropic** provider
family. omp's other providers (OpenAI-direct, Gemini, ...) resolve their
endpoints from their own registry entries; users can already point those
at Headroom with their own custom provider in `models.yml`.
- `headroom/providers/omp/` deliberately contains no install-time / MCP
pieces — this is the thin wrap + unwrap slice only.
---------
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
Co-authored-by: Tejas Chopra <chopratejas@gmail.com>
2026-07-16 04:30:19 +09:00
|
|
|
"""Tests for `headroom wrap omp` / `headroom unwrap omp`.
|
|
|
|
|
|
|
|
|
|
Covers the omp runtime override contract (fresh-create vs merge-preserving
|
|
|
|
|
injection, pristine backups, re-injection idempotency, restore statuses) and
|
|
|
|
|
the CLI wiring that drives it. Every test isolates omp's agent directory via
|
|
|
|
|
``PI_CODING_AGENT_DIR`` and runs from a tmp cwd so the real ``~/.omp`` is
|
|
|
|
|
never touched.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
|
|
|
|
from pathlib import Path
|
|
|
|
|
from unittest.mock import patch
|
|
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
import yaml
|
|
|
|
|
from click.testing import CliRunner
|
|
|
|
|
|
|
|
|
|
from headroom.cli.main import main
|
|
|
|
|
from headroom.providers.omp import (
|
|
|
|
|
MANAGED_MARKER,
|
|
|
|
|
backup_path,
|
|
|
|
|
build_launch_env,
|
|
|
|
|
inject_models_override,
|
|
|
|
|
models_yml_path,
|
|
|
|
|
restore_models_override,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture
|
|
|
|
|
def runner() -> CliRunner:
|
|
|
|
|
return CliRunner()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture
|
|
|
|
|
def omp_home(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> Path:
|
|
|
|
|
"""Isolate omp's agent dir under tmp_path and run from a tmp cwd.
|
|
|
|
|
|
|
|
|
|
Returns the ``models.yml`` path the runtime resolves to.
|
|
|
|
|
"""
|
|
|
|
|
agent_dir = tmp_path / "omp-agent"
|
|
|
|
|
agent_dir.mkdir()
|
|
|
|
|
monkeypatch.setenv("PI_CODING_AGENT_DIR", str(agent_dir))
|
|
|
|
|
monkeypatch.chdir(tmp_path)
|
|
|
|
|
return agent_dir / "models.yml"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# runtime: path resolution
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_models_yml_path_honors_pi_coding_agent_dir(
|
|
|
|
|
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
|
|
|
|
|
) -> None:
|
|
|
|
|
custom = tmp_path / "relocated-agent"
|
|
|
|
|
monkeypatch.setenv("PI_CODING_AGENT_DIR", str(custom))
|
|
|
|
|
monkeypatch.chdir(tmp_path)
|
|
|
|
|
assert models_yml_path() == custom / "models.yml"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# runtime: injection
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_inject_fresh_create_writes_managed_marker_and_no_backup(omp_home: Path) -> None:
|
|
|
|
|
models_file, base_url = inject_models_override(8787, "proj")
|
|
|
|
|
|
|
|
|
|
assert models_file == omp_home
|
|
|
|
|
assert base_url == "http://127.0.0.1:8787/p/proj"
|
|
|
|
|
|
|
|
|
|
text = models_file.read_text(encoding="utf-8")
|
|
|
|
|
assert MANAGED_MARKER in text
|
|
|
|
|
assert yaml.safe_load(text)["providers"]["anthropic"]["baseUrl"] == base_url
|
|
|
|
|
|
|
|
|
|
# Nothing pre-existed, so there is nothing to snapshot.
|
|
|
|
|
assert not backup_path(models_file).exists()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_inject_over_existing_backs_up_pristine_and_merges(omp_home: Path) -> None:
|
|
|
|
|
original = (
|
|
|
|
|
"providers:\n"
|
|
|
|
|
" anthropic:\n"
|
|
|
|
|
" apiKey: sk-user-secret\n"
|
|
|
|
|
" openai:\n"
|
|
|
|
|
" baseUrl: https://api.openai.com/v1\n"
|
|
|
|
|
"models:\n"
|
|
|
|
|
" - id: my-custom-model\n"
|
|
|
|
|
)
|
|
|
|
|
omp_home.write_bytes(original.encode("utf-8"))
|
|
|
|
|
|
|
|
|
|
_, base_url = inject_models_override(8787, "proj")
|
|
|
|
|
|
|
|
|
|
# Pre-wrap file is snapshotted byte-for-byte.
|
|
|
|
|
assert backup_path(omp_home).read_bytes() == original.encode("utf-8")
|
|
|
|
|
|
|
|
|
|
merged = yaml.safe_load(omp_home.read_text(encoding="utf-8"))
|
|
|
|
|
assert merged["providers"]["anthropic"]["baseUrl"] == base_url
|
|
|
|
|
# Only anthropic.baseUrl is set; every other user key survives the merge.
|
|
|
|
|
assert merged["providers"]["anthropic"]["apiKey"] == "sk-user-secret"
|
|
|
|
|
assert merged["providers"]["openai"]["baseUrl"] == "https://api.openai.com/v1"
|
|
|
|
|
assert merged["models"] == [{"id": "my-custom-model"}]
|
|
|
|
|
assert MANAGED_MARKER in omp_home.read_text(encoding="utf-8")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_reinject_new_port_regenerates_from_pristine_backup(omp_home: Path) -> None:
|
|
|
|
|
original = "providers:\n anthropic:\n apiKey: sk-user-secret\n"
|
|
|
|
|
omp_home.write_bytes(original.encode("utf-8"))
|
|
|
|
|
backup = backup_path(omp_home)
|
|
|
|
|
|
|
|
|
|
inject_models_override(8787, "proj")
|
|
|
|
|
assert backup.read_bytes() == original.encode("utf-8")
|
|
|
|
|
|
|
|
|
|
_, base_url_9999 = inject_models_override(9999, "proj")
|
|
|
|
|
|
|
|
|
|
# Re-injection never clobbers the pristine pre-wrap backup.
|
|
|
|
|
assert backup.read_bytes() == original.encode("utf-8")
|
|
|
|
|
|
|
|
|
|
merged = yaml.safe_load(omp_home.read_text(encoding="utf-8"))
|
|
|
|
|
assert base_url_9999 == "http://127.0.0.1:9999/p/proj"
|
|
|
|
|
assert merged["providers"]["anthropic"]["baseUrl"] == base_url_9999
|
|
|
|
|
# Regenerated from the backup, so user creds still survive the new port.
|
|
|
|
|
assert merged["providers"]["anthropic"]["apiKey"] == "sk-user-secret"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# runtime: restore
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_restore_restores_pristine_and_removes_backup(omp_home: Path) -> None:
|
|
|
|
|
original = "providers:\n anthropic:\n apiKey: sk-user-secret\n"
|
|
|
|
|
omp_home.write_bytes(original.encode("utf-8"))
|
|
|
|
|
inject_models_override(8787, "proj")
|
|
|
|
|
|
|
|
|
|
assert restore_models_override() == "restored"
|
|
|
|
|
assert omp_home.read_bytes() == original.encode("utf-8")
|
|
|
|
|
assert not backup_path(omp_home).exists()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_restore_removes_wrap_created_file(omp_home: Path) -> None:
|
|
|
|
|
inject_models_override(8787, "proj") # fresh create → no backup
|
|
|
|
|
assert omp_home.exists()
|
|
|
|
|
|
|
|
|
|
assert restore_models_override() == "removed"
|
|
|
|
|
assert not omp_home.exists()
|
|
|
|
|
assert not backup_path(omp_home).exists()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_restore_noop_when_nothing_managed(omp_home: Path) -> None:
|
|
|
|
|
assert restore_models_override() == "noop"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_restore_leaves_unmanaged_file_untouched(omp_home: Path) -> None:
|
|
|
|
|
user_content = "providers:\n anthropic:\n apiKey: sk-user-secret\n"
|
|
|
|
|
omp_home.write_bytes(user_content.encode("utf-8"))
|
|
|
|
|
|
|
|
|
|
assert restore_models_override() == "noop"
|
|
|
|
|
# A models.yml the wrap does not manage is never modified or deleted.
|
|
|
|
|
assert omp_home.read_bytes() == user_content.encode("utf-8")
|
|
|
|
|
assert not backup_path(omp_home).exists()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# runtime: launch env
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_build_launch_env_passes_env_through_and_emits_display(omp_home: Path) -> None:
|
|
|
|
|
source = {"PATH": "/usr/bin", "ANTHROPIC_BASE_URL": "https://api.anthropic.com"}
|
|
|
|
|
env, display = build_launch_env(8787, source, project="proj")
|
|
|
|
|
|
|
|
|
|
# The redirect lives in models.yml, so env is a verbatim copy — notably
|
|
|
|
|
# ANTHROPIC_BASE_URL is NOT rewritten to the proxy.
|
|
|
|
|
assert env == source
|
|
|
|
|
assert env is not source # a copy, so caller's environ can't be mutated
|
|
|
|
|
assert display == ["models.yml: providers.anthropic.baseUrl=http://127.0.0.1:8787/p/proj"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# CLI: wrap omp
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_wrap_omp_missing_binary_exits_with_install_hint(runner: CliRunner, omp_home: Path) -> None:
|
|
|
|
|
with patch("headroom.cli.wrap.shutil.which", return_value=None):
|
fix: remove rtk and lean-ctx CLI context tools (#2677)
## Description
Removes both third-party CLI context tools — **rtk** and **lean-ctx** —
and with them the context-tool selector itself. Headroom no longer
downloads, installs or configures either one, and there is no
replacement.
The previous pass (#2344) gated only three entry points inside
`headroom/cli/wrap.py`. That left the feature reachable in practice:
| Gap | Effect |
|---|---|
| `scripts/install.sh:1544`, `install.ps1:1681` | Ran `rtk init --global
--auto-patch` from bash/PowerShell, **bypassing the Python gate
entirely** — `curl \| sh` still wrote a Claude Code `PreToolUse` hook
regardless of `HEADROOM_RTK` |
| `wrap.py` `_setup_context_tool_for_agent` | **`wrap openhands` was
broken by default**: `rtk_required=True` met a gate returning `None` →
`SystemExit(1)`. Invisible because all 8 openhands tests patched
`_ensure_rtk_binary` to a fake path |
| `proxy/helpers.py`, `subscription/tracker.py` | Proxy shelled out to
`rtk gain` from `/stats`, the dashboard and `headroom perf`; the tracker
polled it per contribution (`_RTK_WIRING_DEFAULT = "enabled"`) |
| No cleanup path | Nothing removed artifacts an earlier default had
installed, so a machine that once ran the old default kept rtk in the
loop forever (#1669, #1955) |
Also worth noting: the rtk binary download had **no SHA or signature
verification** — only `rtk --version` as a smoke test.
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [x] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [x] Code refactoring (no functional changes)
## Changes Made
**Removed** — `headroom/rtk/` and `headroom/lean_ctx/` packages,
`headroom/cli/wrap_rtk_metrics.py`, `_selected_context_tool` /
`_setup_context_tool_for_agent` / `_VALID_CONTEXT_TOOLS`, the `--rtk` /
`--no-rtk` / `--no-project-rtk` / `--keep-rtk` flags across all 18 wrap
subcommands, `HEADROOM_RTK*`, the proxy-side `rtk gain` polling, the
dashboard CLI-filtering panel (rows + all 8 `cliFiltering*` Alpine
getters), `paths.rtk_path()` / `lean_ctx_path()`, the SDK path helpers,
`benchmarks/rtk_loop_learn_eval.py`, and the `headroom/rtk/**` CI path
filters.
**Fails loudly, not silently** — `--context-tool` / `--no-context-tool`
/ `HEADROOM_CONTEXT_TOOL` are kept solely to error out. They live in
shell profiles, aliases and CI jobs, and accepting them as a no-op would
read as Headroom having quietly stopped working. The installers reject
them too, which matters more than it looks: their arg parsers forward
the first unknown flag **and everything after it** to the wrapped tool,
so a leftover `--no-rtk` would have silently swallowed a following
`--port` and then been ignored downstream.
**New `headroom/context_tool_cleanup.py`** — deleting the code cannot
help a machine that already ran the old default, since the hooks,
binaries and injected guidance are durable on disk.
`purge_context_tool_artifacts()` runs once per `wrap`/`unwrap` and
removes the registered hook entries, the generated hook scripts, the
Headroom-managed `~/.local/bin` symlinks, the vendored
`~/.headroom/bin/{rtk,lean-ctx}` binaries, the `lean-ctx` MCP server
entry and the marker-fenced instruction blocks. Deliberately
conservative: idempotent, **skips** a malformed config rather than
overwriting it, and only unlinks a symlink resolving inside Headroom's
own bin dir so a user's own build is untouched. It reports on
**stderr**, because `wrap/unwrap openclaw --prepare-only` emit
machine-readable JSON on stdout as their entire contract. Skipped for
`wrap selfheal` (runs from a SessionStart hook; must not race Claude
Code's writer for `~/.claude.json`) and for `--help`, which must stay
read-only.
**Client-config hardening** (discovered while investigating a "corrupted
Serena settings file" report) — `wrap.py` reset a settings file to `{}`
when an existing file would not parse, then wrote that back. One
hand-edited typo or a transient `EACCES`/`EINTR` on a valid file
destroyed the user's `permissions`, `env` and `hooks`, on **every
`headroom wrap claude`**. It now refuses to write. Separately,
`fsutil.write_text` is now atomic (temp file + `fsync` + `os.replace`),
fixing all 14 non-atomic client-config writes at once; it follows
symlinks rather than replacing them (dotfile managers) and preserves an
existing file's mode.
**Deliberately kept** — `rtk` stays in the wrapper-peel list in
`transforms/content_router.py`. It sits beside `sudo`/`env`/`timeout` as
shell-command grammar, so `rtk cat f` is still classified as a file read
for anyone running their own rtk install, which the purge intentionally
leaves alone.
## Testing
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ ruff check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
All checks passed!
$ ruff format --check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
1255 files already formatted
$ mypy headroom/
Success: no issues found in 508 source files
$ pytest tests/test_context_tool_cleanup.py -q
11 passed
$ pytest tests/test_fsutil.py -q
12 passed
$ pytest tests/test_cli/test_wrap_codex.py -q # 89 tests
89 passed in 431.68s
$ pytest tests/test_cli/test_wrap_opencode.py -q
39 passed in 257.46s
$ pytest tests/test_cli/test_wrap_helpers.py -q
45 passed
$ pytest tests/test_paths.py -q
75 passed
$ pytest tests/test_cli/test_unwrap_claude.py -q
14 passed
$ pytest tests/test_proxy_savings_history.py -q
39 passed
$ pytest tests/test_cli/test_wrap_copilot.py -q
27 passed
$ pytest tests/test_cli/test_wrap_zcode.py -q
20 passed
$ pytest tests/test_subscription_tracker.py -q
9 passed
$ pytest tests/test_proxy_dashboard_stats_cache.py -q
5 passed, 1 skipped
```
Repo-wide grep for 14 removed symbols (`headroom.rtk`,
`headroom.lean_ctx`, `_ensure_rtk_binary`, `_selected_context_tool`,
`_get_context_tool_stats`, `rtk_path`, `lean_ctx_path`,
`wrap_rtk_metrics`, `HEADROOM_RTK`, `cli_tokens_avoided`,
`tokens_saved_rtk`, …) across `*.py`, `*.ts`, `*.sh`, `*.ps1`, `*.yml`,
`*.html`: **zero hits**.
Notable test changes: `test_wrap_openhands.py` no longer patches
`_ensure_rtk_binary` and asserts `wrap openhands --prepare-only` exits 0
unpatched — the regression that was previously masked.
`test_wrap_continue.py` and `test_wrap_hintfile_agents.py` were removed
(every test drove RTK instruction injection). A new
`test_subscription_tracker.py::test_load_state_written_before_cli_context_tools_were_removed`
proves a pre-removal `subscription_state.json` still loads.
## Real Behavior Proof
- **Environment:** macOS 15.4 (darwin 25.4.0), Python 3.12.6, Headroom @
this branch, real `~/.headroom` and `~/.claude` on the dev machine.
- **Exact command / steps and observed result:**
```text
# 1. Retired flag fails loudly instead of silently no-op'ing
$ headroom wrap codex --prepare-only --context-tool rtk
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: they
rewrote shell commands through a third-party binary Headroom no longer manages.
Drop --context-tool / --no-context-tool and unset HEADROOM_CONTEXT_TOOL;
`headroom wrap` uninstalls what they left behind on first run.
$ HEADROOM_CONTEXT_TOOL=lean-ctx headroom wrap codex --prepare-only
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: ...
# 2. install.sh rejects the retired flags (extracted parse_wrap_args harness)
['--no-rtk', '--port', '9999'] rc=1 ERROR: CLI context tools ... Drop --no-rtk
['--context-tool=rtk'] rc=1 ERROR: CLI context tools ... Drop --context-tool
$ bash -n scripts/install.sh # syntax OK
# 3. Purge ran against the real machine, which had all the orphaned artifacts
$ python -c "from headroom.context_tool_cleanup import purge_context_tool_artifacts; ..."
removed ~/.headroom/bin/lean-ctx (51 MB)
removed ~/.headroom/bin/rtk (7.7 MB)
removed ~/.local/bin/rtk (symlink into ~/.headroom/bin)
removed ~/.claude/hooks/rtk-rewrite.sh
removed 8 lean-ctx-* hook scripts
# ~/.claude.json afterwards: 90 top-level keys, 19 projects, mcpServers unchanged
# → ~59 MB reclaimed, no unrelated key touched
# 4. stdout stays machine-readable while the purge reports (planted a fake artifact)
$ headroom wrap openclaw --prepare-only --gateway-provider-id codex >out 2>err
$ cat out
{"enabled":true,"config":{"proxyPort":8787,...}} # parses as JSON
$ cat err
Retired CLI context tool cleanup: removed /Users/tcms/.headroom/bin/rtk
# 5. --help is inert (planted artifact survives), a real run purges
$ headroom wrap codex --help → artifact survived: CORRECT
$ headroom wrap openclaw --prepare-only → purged: CORRECT
# 6. MCP purge dry-run against a copy of the real 82 KB ~/.claude.json
top-level keys 90 -> 90; projects 19 -> 19; LOST keys: none
all content outside mcpServers byte-identical: True
```
Dashboard rendered via the Playwright test after the panel removal:
"Token Savings" shows only `Proxy 0 (0.0%)` / `Of total wire: 36.86%`,
and "Token Usage" reads Before Compression → Proxy Removed → After
Compression with no "Filtered (this session)" row. Nothing below the
removed panel broke.
- **Not tested:** Windows and Linux (macOS only) — `install.ps1` is
verified by brace-balance and inspection, not executed, since no `pwsh`
is available locally. The wrap e2e suite (`e2e/wrap/run.py`) was updated
but not run; it needs the Docker e2e image. `serena project index`
interaction is exercised in the stacked base PR.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I did **not** edit `CHANGELOG.md` — it is generated by
release-please from my Conventional Commit PR title (a CI guard enforces
this)
## Additional Notes
**Stacked on #2676** (`tejas/serena-config-bootstrap`) — please merge
that first; this PR's base should then be retargeted to `main`, or it
will read as containing that fix too.
**Breaking-change migration for users:**
- Drop `--rtk`, `--no-rtk`, `--no-project-rtk`, `--keep-rtk`,
`--context-tool`, `--no-context-tool` from any alias, script or CI job,
and unset `HEADROOM_RTK*` / `HEADROOM_CONTEXT_TOOL`. They now error
rather than being ignored, so the failure is immediate and
self-explaining.
- Previously-installed artifacts are purged automatically on the next
`wrap`/`unwrap`; no manual cleanup needed.
- `headroom perf --json` no longer carries a `cli_filtering` key, and
`/stats` no longer returns a `context_tool` section.
**Docs:** `docs/rtk-architecture.md` deleted; RTK/lean-ctx removed from
`README.md`,
`docs/content/docs/{configuration,opencode,grok-build,docker-install,filesystem-contract}.mdx`,
`docs/observability.md` and the matching `wiki/` pages.
`REALIGNMENT/09-phase-G-rtk-observability.md` is marked SUPERSEDED
rather than deleted, to keep the planning record.
**Follow-ups not in scope:** `_emit_wrap_interrupted` was deleted as
dead code — its only caller was the `except KeyboardInterrupt` guarding
the binary download, so with no download there is nothing slow left to
interrupt.
2026-07-30 22:59:41 -07:00
|
|
|
result = runner.invoke(main, ["wrap", "omp"])
|
feat(wrap): add omp target (Oh My Pi) with models.yml override and unwrap (#1811)
## Description
Adds `headroom wrap omp` / `headroom unwrap omp` — a one-command wrap
for [Oh My Pi](https://www.npmjs.com/package/@oh-my-pi/pi-coding-agent)
(`omp`), the pi-mono-lineage coding agent, as proposed in #1149.
One honest correction to the issue: #1149 proposed reusing the
`ANTHROPIC_BASE_URL` redirect from `wrap claude`. During implementation
I probed that empirically and it turned out to be wrong — omp only reads
`ANTHROPIC_BASE_URL` in its web-search helper; its **chat** endpoint
comes from the model registry (`providers.anthropic.baseUrl` in
`~/.omp/agent/models.yml`). With the env var pointed at a local probe
server, omp's chat traffic still went straight to the real endpoint (0
probe hits); with a `models.yml` same-ID override, every request arrived
at the probe (9/9 hits on `/v1/messages`). A same-ID override keeps
omp's bundled Anthropic model catalog and stored credentials (both keyed
by provider id `anthropic`), so only the endpoint moves.
The wrap therefore injects a marker-fenced `providers.anthropic.baseUrl`
override into `models.yml`, snapshotting the pre-wrap file
**byte-for-byte** first, and `headroom unwrap omp` restores it exactly
(or removes the file when the wrap created it) — the same durable-wrap +
backup + unwrap contract `wrap codex` uses for `config.toml`.
Closes #1149
## Type of Change
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- `headroom/providers/omp/` (new provider slice): `models_yml_path()`
(honors `PI_CODING_AGENT_DIR`), `inject_models_override()` (yaml-merge
preserving user providers; pristine byte-for-byte backup, never
re-snapshotted while managed), `restore_models_override()` (`restored` /
`removed` / `noop`; never touches an unmanaged file),
`build_launch_env()`
- `headroom/cli/wrap.py`: `wrap omp` (mirrors the aider/vibe
`_launch_tool` shape; rtk instructions into the project's `AGENTS.md`,
which omp reads natively) and `unwrap omp` (restore models.yml + scrub
rtk block + stop proxy)
- `headroom/telemetry/context.py`: `omp` added to `_KNOWN_WRAP_AGENTS`
so the stack slug reports `wrap_omp` instead of `unknown`
- `README.md` (agent matrix row + unwrap list), `llms.txt`,
`CHANGELOG.md`
- `tests/test_cli/test_wrap_omp.py`: 16 tests (injection
fresh/merge/re-inject, restore statuses incl. unmanaged-file safety, env
passthrough, CLI wiring, unwrap flows)
## Testing
- [ ] Unit tests pass (`pytest`) — all new + `test_cli` tests pass; the
full suite carries **3 pre-existing failures** that reproduce
identically on unmodified `origin/main` (same set, same asserts — see
Test Output and the rebase-validation comment)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ uv run pytest -q # post-rebase, base 4f22cbb0
3 failed, 7723 passed, 515 skipped in 262.64s
FAILED tests/test_cli/test_wrap_claude_base_url.py::test_wrap_marker_is_stale_when_pid_reused
FAILED tests/test_rtk_session_savings.py::test_rtk_reader_returns_none_on_nonzero_exit
FAILED tests/test_rtk_session_savings.py::test_lean_ctx_reader_returns_none_on_failure_and_logs
→ all three reproduce identically on unmodified origin/main (4f22cbb0), run the
same way (same worktree + venv, sources switched): 3 failed, 7707 passed —
this branch = baseline + the 16 new tests, nothing else changes.
(The pre-rebase run against e8151f05 showed the same shape: one order-dependent
flake that also reproduced on its baseline; these are env/order-dependent.)
$ uv run pytest tests/test_cli/ -q # post-rebase
542 passed + 1 of the pre-existing failures above # includes the 16 new test_wrap_omp.py tests
$ uv run ruff check . ; echo ruff-check-exit:$?
All checks passed!
ruff-check-exit:0
$ uv run ruff format --check . # post-rebase
1 pre-existing violation: headroom/proxy/handlers/anthropic.py — flagged identically
on unmodified origin/main (not touched by this PR); every file this PR touches is clean
$ uv run mypy headroom # post-rebase; output redirected to file; exit captured
Success: no issues found in 409 source files
mypy-exit:0
```
## Real Behavior Proof
- Environment: macOS 15 (arm64, M1 Pro), Python 3.12.13 (uv venv,
editable install incl. Rust `_core`), headroom @ this branch, base
extras only (no `[ml]`), Anthropic account signed into omp. Initial
proof ran on base e8151f05 with omp 16.3.6 (`@oh-my-pi/pi-coding-agent`
via bun); re-validated after the rebase onto 4f22cbb0 with omp 16.3.11 —
fresh numbers in the rebase-validation comment.
- Exact command / steps: four scenarios, run in this order —
1. Mechanism probe (why models.yml, not env): local HTTP probe server on
`127.0.0.1:18999`; ran `omp -p "say ok" --model claude-fable-5
--no-session --no-tools` once with
`ANTHROPIC_BASE_URL=http://127.0.0.1:18999`, once with
`~/.omp/agent/models.yml` containing `providers.anthropic.baseUrl:
http://127.0.0.1:18999`.
2. One-command path: `headroom wrap omp --no-rtk --port 8790 -- -p "Read
CHANGELOG.md and count how many '### Fixed' headings it contains. Answer
with just the number." --model claude-fable-5 --no-session --max-time
180`
3. Routing stats: separate proxy on :8788, wrap with `--no-proxy`, then
`GET /stats`.
4. Restore: `headroom unwrap omp`, plus an isolated
`PI_CODING_AGENT_DIR=/tmp/omp-agent-test` run with a pre-existing user
`models.yml`, then `cmp` against the original.
- Observed result: end-to-end routing through the proxy proven for every
scenario —
- Probe: env-var run → **0 probe hits**, omp answered normally
(bypassed). models.yml run → **9 hits on `/v1/messages?beta=true`** with
real Messages bodies. This is the routing mechanism the wrap uses.
- One-command run: wrap started the proxy ("Proxy ready on
http://127.0.0.1:8790"), wrote the override (`models.yml:
providers.anthropic.baseUrl=http://127.0.0.1:8790/p/headroom-wrap-omp`),
launched omp, and omp answered **"7"** (correct — real `read` tool work
through the proxy). Proxy log for the session (3 requests,
`anthropic_messages` path):
```
PERF model=claude-fable-5 msgs=1 tok_before=36 cache_read=0
cache_write=61939 cache_hit_pct=0
PERF model=claude-fable-5 msgs=3 tok_before=796 cache_read=0
cache_write=63308 cache_hit_pct=0
PERF model=claude-fable-5 msgs=5 tok_before=935 cache_read=63308
cache_write=215 cache_hit_pct=100
```
Prompt caching survives the proxy (100% hit on the follow-up turn).
- Routing stats (:8788 session): `requests.total: 2, by_provider:
{"anthropic": 2}, by_model: {"claude-fable-5": 2}`, per-project prefix
`/p/headroom-wrap-omp` attributed.
- Unwrap: `Removed wrap-created models.yml` (file gone); isolated
pre-existing-file run: backup created, user's `my-gw` provider preserved
in the managed file, and after `unwrap omp` the restored file is
**byte-identical** (`cmp` clean).
- Compression: **not observed in this environment** — `tok_saved=0`,
`transforms=router:noop` / `too_small`. Honest reading: omp minimizes
its own tool outputs client-side (a 300-item JSON tool result reached
the proxy at only ~657 tokens) and the `[ml]` text compressor wasn't
installed; small print-mode payloads sit below crush thresholds, and
passthrough-by-default is the documented safety contract. The wrap's
value here is proven at the routing/lifecycle/cache layer; compression
numbers will match whatever the proxy does for a given content mix.
- Not tested: Windows / Linux; lean-ctx mode with omp
(`HEADROOM_CONTEXT_TOOL=lean-ctx` — `lean-ctx init --agent omp` depends
on lean-ctx recognizing the agent; failure degrades with a warning by
design); long interactive (non `-p`) sessions; `--memory` / `--learn` /
`--code-graph` flags combined with omp; OAuth-vs-API-key matrix beyond
my local account.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes — all
except the 3 documented pre-existing failures, which fail identically on
unmodified origin/main
- [x] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
N/A — terminal evidence inline above.
## Additional Notes
- The models.yml override is regenerated from the pristine backup on
every wrap, so re-running with a different `--port` updates the endpoint
idempotently and the backup is never clobbered.
- Scope note from #1149 stands: this routes omp's **Anthropic** provider
family. omp's other providers (OpenAI-direct, Gemini, ...) resolve their
endpoints from their own registry entries; users can already point those
at Headroom with their own custom provider in `models.yml`.
- `headroom/providers/omp/` deliberately contains no install-time / MCP
pieces — this is the thin wrap + unwrap slice only.
---------
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
Co-authored-by: Tejas Chopra <chopratejas@gmail.com>
2026-07-16 04:30:19 +09:00
|
|
|
|
|
|
|
|
assert result.exit_code == 1
|
|
|
|
|
assert "npm install -g @oh-my-pi/pi-coding-agent" in result.output
|
|
|
|
|
# Fail fast before mutating omp's config.
|
|
|
|
|
assert not omp_home.exists()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_wrap_omp_happy_path_injects_before_launch(runner: CliRunner, omp_home: Path) -> None:
|
|
|
|
|
captured: dict[str, object] = {}
|
|
|
|
|
|
|
|
|
|
def fake_launch_tool(**kwargs: object) -> None:
|
|
|
|
|
captured.update(kwargs)
|
|
|
|
|
# Prove models.yml is on disk BEFORE omp is launched.
|
|
|
|
|
captured["models_text_at_launch"] = (
|
|
|
|
|
omp_home.read_text(encoding="utf-8") if omp_home.exists() else None
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
with (
|
|
|
|
|
patch("headroom.cli.wrap.shutil.which", return_value="omp"),
|
|
|
|
|
patch("headroom.cli.wrap._launch_tool", side_effect=fake_launch_tool),
|
|
|
|
|
):
|
fix: remove rtk and lean-ctx CLI context tools (#2677)
## Description
Removes both third-party CLI context tools — **rtk** and **lean-ctx** —
and with them the context-tool selector itself. Headroom no longer
downloads, installs or configures either one, and there is no
replacement.
The previous pass (#2344) gated only three entry points inside
`headroom/cli/wrap.py`. That left the feature reachable in practice:
| Gap | Effect |
|---|---|
| `scripts/install.sh:1544`, `install.ps1:1681` | Ran `rtk init --global
--auto-patch` from bash/PowerShell, **bypassing the Python gate
entirely** — `curl \| sh` still wrote a Claude Code `PreToolUse` hook
regardless of `HEADROOM_RTK` |
| `wrap.py` `_setup_context_tool_for_agent` | **`wrap openhands` was
broken by default**: `rtk_required=True` met a gate returning `None` →
`SystemExit(1)`. Invisible because all 8 openhands tests patched
`_ensure_rtk_binary` to a fake path |
| `proxy/helpers.py`, `subscription/tracker.py` | Proxy shelled out to
`rtk gain` from `/stats`, the dashboard and `headroom perf`; the tracker
polled it per contribution (`_RTK_WIRING_DEFAULT = "enabled"`) |
| No cleanup path | Nothing removed artifacts an earlier default had
installed, so a machine that once ran the old default kept rtk in the
loop forever (#1669, #1955) |
Also worth noting: the rtk binary download had **no SHA or signature
verification** — only `rtk --version` as a smoke test.
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [x] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [x] Code refactoring (no functional changes)
## Changes Made
**Removed** — `headroom/rtk/` and `headroom/lean_ctx/` packages,
`headroom/cli/wrap_rtk_metrics.py`, `_selected_context_tool` /
`_setup_context_tool_for_agent` / `_VALID_CONTEXT_TOOLS`, the `--rtk` /
`--no-rtk` / `--no-project-rtk` / `--keep-rtk` flags across all 18 wrap
subcommands, `HEADROOM_RTK*`, the proxy-side `rtk gain` polling, the
dashboard CLI-filtering panel (rows + all 8 `cliFiltering*` Alpine
getters), `paths.rtk_path()` / `lean_ctx_path()`, the SDK path helpers,
`benchmarks/rtk_loop_learn_eval.py`, and the `headroom/rtk/**` CI path
filters.
**Fails loudly, not silently** — `--context-tool` / `--no-context-tool`
/ `HEADROOM_CONTEXT_TOOL` are kept solely to error out. They live in
shell profiles, aliases and CI jobs, and accepting them as a no-op would
read as Headroom having quietly stopped working. The installers reject
them too, which matters more than it looks: their arg parsers forward
the first unknown flag **and everything after it** to the wrapped tool,
so a leftover `--no-rtk` would have silently swallowed a following
`--port` and then been ignored downstream.
**New `headroom/context_tool_cleanup.py`** — deleting the code cannot
help a machine that already ran the old default, since the hooks,
binaries and injected guidance are durable on disk.
`purge_context_tool_artifacts()` runs once per `wrap`/`unwrap` and
removes the registered hook entries, the generated hook scripts, the
Headroom-managed `~/.local/bin` symlinks, the vendored
`~/.headroom/bin/{rtk,lean-ctx}` binaries, the `lean-ctx` MCP server
entry and the marker-fenced instruction blocks. Deliberately
conservative: idempotent, **skips** a malformed config rather than
overwriting it, and only unlinks a symlink resolving inside Headroom's
own bin dir so a user's own build is untouched. It reports on
**stderr**, because `wrap/unwrap openclaw --prepare-only` emit
machine-readable JSON on stdout as their entire contract. Skipped for
`wrap selfheal` (runs from a SessionStart hook; must not race Claude
Code's writer for `~/.claude.json`) and for `--help`, which must stay
read-only.
**Client-config hardening** (discovered while investigating a "corrupted
Serena settings file" report) — `wrap.py` reset a settings file to `{}`
when an existing file would not parse, then wrote that back. One
hand-edited typo or a transient `EACCES`/`EINTR` on a valid file
destroyed the user's `permissions`, `env` and `hooks`, on **every
`headroom wrap claude`**. It now refuses to write. Separately,
`fsutil.write_text` is now atomic (temp file + `fsync` + `os.replace`),
fixing all 14 non-atomic client-config writes at once; it follows
symlinks rather than replacing them (dotfile managers) and preserves an
existing file's mode.
**Deliberately kept** — `rtk` stays in the wrapper-peel list in
`transforms/content_router.py`. It sits beside `sudo`/`env`/`timeout` as
shell-command grammar, so `rtk cat f` is still classified as a file read
for anyone running their own rtk install, which the purge intentionally
leaves alone.
## Testing
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ ruff check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
All checks passed!
$ ruff format --check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
1255 files already formatted
$ mypy headroom/
Success: no issues found in 508 source files
$ pytest tests/test_context_tool_cleanup.py -q
11 passed
$ pytest tests/test_fsutil.py -q
12 passed
$ pytest tests/test_cli/test_wrap_codex.py -q # 89 tests
89 passed in 431.68s
$ pytest tests/test_cli/test_wrap_opencode.py -q
39 passed in 257.46s
$ pytest tests/test_cli/test_wrap_helpers.py -q
45 passed
$ pytest tests/test_paths.py -q
75 passed
$ pytest tests/test_cli/test_unwrap_claude.py -q
14 passed
$ pytest tests/test_proxy_savings_history.py -q
39 passed
$ pytest tests/test_cli/test_wrap_copilot.py -q
27 passed
$ pytest tests/test_cli/test_wrap_zcode.py -q
20 passed
$ pytest tests/test_subscription_tracker.py -q
9 passed
$ pytest tests/test_proxy_dashboard_stats_cache.py -q
5 passed, 1 skipped
```
Repo-wide grep for 14 removed symbols (`headroom.rtk`,
`headroom.lean_ctx`, `_ensure_rtk_binary`, `_selected_context_tool`,
`_get_context_tool_stats`, `rtk_path`, `lean_ctx_path`,
`wrap_rtk_metrics`, `HEADROOM_RTK`, `cli_tokens_avoided`,
`tokens_saved_rtk`, …) across `*.py`, `*.ts`, `*.sh`, `*.ps1`, `*.yml`,
`*.html`: **zero hits**.
Notable test changes: `test_wrap_openhands.py` no longer patches
`_ensure_rtk_binary` and asserts `wrap openhands --prepare-only` exits 0
unpatched — the regression that was previously masked.
`test_wrap_continue.py` and `test_wrap_hintfile_agents.py` were removed
(every test drove RTK instruction injection). A new
`test_subscription_tracker.py::test_load_state_written_before_cli_context_tools_were_removed`
proves a pre-removal `subscription_state.json` still loads.
## Real Behavior Proof
- **Environment:** macOS 15.4 (darwin 25.4.0), Python 3.12.6, Headroom @
this branch, real `~/.headroom` and `~/.claude` on the dev machine.
- **Exact command / steps and observed result:**
```text
# 1. Retired flag fails loudly instead of silently no-op'ing
$ headroom wrap codex --prepare-only --context-tool rtk
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: they
rewrote shell commands through a third-party binary Headroom no longer manages.
Drop --context-tool / --no-context-tool and unset HEADROOM_CONTEXT_TOOL;
`headroom wrap` uninstalls what they left behind on first run.
$ HEADROOM_CONTEXT_TOOL=lean-ctx headroom wrap codex --prepare-only
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: ...
# 2. install.sh rejects the retired flags (extracted parse_wrap_args harness)
['--no-rtk', '--port', '9999'] rc=1 ERROR: CLI context tools ... Drop --no-rtk
['--context-tool=rtk'] rc=1 ERROR: CLI context tools ... Drop --context-tool
$ bash -n scripts/install.sh # syntax OK
# 3. Purge ran against the real machine, which had all the orphaned artifacts
$ python -c "from headroom.context_tool_cleanup import purge_context_tool_artifacts; ..."
removed ~/.headroom/bin/lean-ctx (51 MB)
removed ~/.headroom/bin/rtk (7.7 MB)
removed ~/.local/bin/rtk (symlink into ~/.headroom/bin)
removed ~/.claude/hooks/rtk-rewrite.sh
removed 8 lean-ctx-* hook scripts
# ~/.claude.json afterwards: 90 top-level keys, 19 projects, mcpServers unchanged
# → ~59 MB reclaimed, no unrelated key touched
# 4. stdout stays machine-readable while the purge reports (planted a fake artifact)
$ headroom wrap openclaw --prepare-only --gateway-provider-id codex >out 2>err
$ cat out
{"enabled":true,"config":{"proxyPort":8787,...}} # parses as JSON
$ cat err
Retired CLI context tool cleanup: removed /Users/tcms/.headroom/bin/rtk
# 5. --help is inert (planted artifact survives), a real run purges
$ headroom wrap codex --help → artifact survived: CORRECT
$ headroom wrap openclaw --prepare-only → purged: CORRECT
# 6. MCP purge dry-run against a copy of the real 82 KB ~/.claude.json
top-level keys 90 -> 90; projects 19 -> 19; LOST keys: none
all content outside mcpServers byte-identical: True
```
Dashboard rendered via the Playwright test after the panel removal:
"Token Savings" shows only `Proxy 0 (0.0%)` / `Of total wire: 36.86%`,
and "Token Usage" reads Before Compression → Proxy Removed → After
Compression with no "Filtered (this session)" row. Nothing below the
removed panel broke.
- **Not tested:** Windows and Linux (macOS only) — `install.ps1` is
verified by brace-balance and inspection, not executed, since no `pwsh`
is available locally. The wrap e2e suite (`e2e/wrap/run.py`) was updated
but not run; it needs the Docker e2e image. `serena project index`
interaction is exercised in the stacked base PR.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I did **not** edit `CHANGELOG.md` — it is generated by
release-please from my Conventional Commit PR title (a CI guard enforces
this)
## Additional Notes
**Stacked on #2676** (`tejas/serena-config-bootstrap`) — please merge
that first; this PR's base should then be retargeted to `main`, or it
will read as containing that fix too.
**Breaking-change migration for users:**
- Drop `--rtk`, `--no-rtk`, `--no-project-rtk`, `--keep-rtk`,
`--context-tool`, `--no-context-tool` from any alias, script or CI job,
and unset `HEADROOM_RTK*` / `HEADROOM_CONTEXT_TOOL`. They now error
rather than being ignored, so the failure is immediate and
self-explaining.
- Previously-installed artifacts are purged automatically on the next
`wrap`/`unwrap`; no manual cleanup needed.
- `headroom perf --json` no longer carries a `cli_filtering` key, and
`/stats` no longer returns a `context_tool` section.
**Docs:** `docs/rtk-architecture.md` deleted; RTK/lean-ctx removed from
`README.md`,
`docs/content/docs/{configuration,opencode,grok-build,docker-install,filesystem-contract}.mdx`,
`docs/observability.md` and the matching `wiki/` pages.
`REALIGNMENT/09-phase-G-rtk-observability.md` is marked SUPERSEDED
rather than deleted, to keep the planning record.
**Follow-ups not in scope:** `_emit_wrap_interrupted` was deleted as
dead code — its only caller was the `except KeyboardInterrupt` guarding
the binary download, so with no download there is nothing slow left to
interrupt.
2026-07-30 22:59:41 -07:00
|
|
|
result = runner.invoke(main, ["wrap", "omp", "--", "-p", "fix the bug"])
|
feat(wrap): add omp target (Oh My Pi) with models.yml override and unwrap (#1811)
## Description
Adds `headroom wrap omp` / `headroom unwrap omp` — a one-command wrap
for [Oh My Pi](https://www.npmjs.com/package/@oh-my-pi/pi-coding-agent)
(`omp`), the pi-mono-lineage coding agent, as proposed in #1149.
One honest correction to the issue: #1149 proposed reusing the
`ANTHROPIC_BASE_URL` redirect from `wrap claude`. During implementation
I probed that empirically and it turned out to be wrong — omp only reads
`ANTHROPIC_BASE_URL` in its web-search helper; its **chat** endpoint
comes from the model registry (`providers.anthropic.baseUrl` in
`~/.omp/agent/models.yml`). With the env var pointed at a local probe
server, omp's chat traffic still went straight to the real endpoint (0
probe hits); with a `models.yml` same-ID override, every request arrived
at the probe (9/9 hits on `/v1/messages`). A same-ID override keeps
omp's bundled Anthropic model catalog and stored credentials (both keyed
by provider id `anthropic`), so only the endpoint moves.
The wrap therefore injects a marker-fenced `providers.anthropic.baseUrl`
override into `models.yml`, snapshotting the pre-wrap file
**byte-for-byte** first, and `headroom unwrap omp` restores it exactly
(or removes the file when the wrap created it) — the same durable-wrap +
backup + unwrap contract `wrap codex` uses for `config.toml`.
Closes #1149
## Type of Change
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- `headroom/providers/omp/` (new provider slice): `models_yml_path()`
(honors `PI_CODING_AGENT_DIR`), `inject_models_override()` (yaml-merge
preserving user providers; pristine byte-for-byte backup, never
re-snapshotted while managed), `restore_models_override()` (`restored` /
`removed` / `noop`; never touches an unmanaged file),
`build_launch_env()`
- `headroom/cli/wrap.py`: `wrap omp` (mirrors the aider/vibe
`_launch_tool` shape; rtk instructions into the project's `AGENTS.md`,
which omp reads natively) and `unwrap omp` (restore models.yml + scrub
rtk block + stop proxy)
- `headroom/telemetry/context.py`: `omp` added to `_KNOWN_WRAP_AGENTS`
so the stack slug reports `wrap_omp` instead of `unknown`
- `README.md` (agent matrix row + unwrap list), `llms.txt`,
`CHANGELOG.md`
- `tests/test_cli/test_wrap_omp.py`: 16 tests (injection
fresh/merge/re-inject, restore statuses incl. unmanaged-file safety, env
passthrough, CLI wiring, unwrap flows)
## Testing
- [ ] Unit tests pass (`pytest`) — all new + `test_cli` tests pass; the
full suite carries **3 pre-existing failures** that reproduce
identically on unmodified `origin/main` (same set, same asserts — see
Test Output and the rebase-validation comment)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ uv run pytest -q # post-rebase, base 4f22cbb0
3 failed, 7723 passed, 515 skipped in 262.64s
FAILED tests/test_cli/test_wrap_claude_base_url.py::test_wrap_marker_is_stale_when_pid_reused
FAILED tests/test_rtk_session_savings.py::test_rtk_reader_returns_none_on_nonzero_exit
FAILED tests/test_rtk_session_savings.py::test_lean_ctx_reader_returns_none_on_failure_and_logs
→ all three reproduce identically on unmodified origin/main (4f22cbb0), run the
same way (same worktree + venv, sources switched): 3 failed, 7707 passed —
this branch = baseline + the 16 new tests, nothing else changes.
(The pre-rebase run against e8151f05 showed the same shape: one order-dependent
flake that also reproduced on its baseline; these are env/order-dependent.)
$ uv run pytest tests/test_cli/ -q # post-rebase
542 passed + 1 of the pre-existing failures above # includes the 16 new test_wrap_omp.py tests
$ uv run ruff check . ; echo ruff-check-exit:$?
All checks passed!
ruff-check-exit:0
$ uv run ruff format --check . # post-rebase
1 pre-existing violation: headroom/proxy/handlers/anthropic.py — flagged identically
on unmodified origin/main (not touched by this PR); every file this PR touches is clean
$ uv run mypy headroom # post-rebase; output redirected to file; exit captured
Success: no issues found in 409 source files
mypy-exit:0
```
## Real Behavior Proof
- Environment: macOS 15 (arm64, M1 Pro), Python 3.12.13 (uv venv,
editable install incl. Rust `_core`), headroom @ this branch, base
extras only (no `[ml]`), Anthropic account signed into omp. Initial
proof ran on base e8151f05 with omp 16.3.6 (`@oh-my-pi/pi-coding-agent`
via bun); re-validated after the rebase onto 4f22cbb0 with omp 16.3.11 —
fresh numbers in the rebase-validation comment.
- Exact command / steps: four scenarios, run in this order —
1. Mechanism probe (why models.yml, not env): local HTTP probe server on
`127.0.0.1:18999`; ran `omp -p "say ok" --model claude-fable-5
--no-session --no-tools` once with
`ANTHROPIC_BASE_URL=http://127.0.0.1:18999`, once with
`~/.omp/agent/models.yml` containing `providers.anthropic.baseUrl:
http://127.0.0.1:18999`.
2. One-command path: `headroom wrap omp --no-rtk --port 8790 -- -p "Read
CHANGELOG.md and count how many '### Fixed' headings it contains. Answer
with just the number." --model claude-fable-5 --no-session --max-time
180`
3. Routing stats: separate proxy on :8788, wrap with `--no-proxy`, then
`GET /stats`.
4. Restore: `headroom unwrap omp`, plus an isolated
`PI_CODING_AGENT_DIR=/tmp/omp-agent-test` run with a pre-existing user
`models.yml`, then `cmp` against the original.
- Observed result: end-to-end routing through the proxy proven for every
scenario —
- Probe: env-var run → **0 probe hits**, omp answered normally
(bypassed). models.yml run → **9 hits on `/v1/messages?beta=true`** with
real Messages bodies. This is the routing mechanism the wrap uses.
- One-command run: wrap started the proxy ("Proxy ready on
http://127.0.0.1:8790"), wrote the override (`models.yml:
providers.anthropic.baseUrl=http://127.0.0.1:8790/p/headroom-wrap-omp`),
launched omp, and omp answered **"7"** (correct — real `read` tool work
through the proxy). Proxy log for the session (3 requests,
`anthropic_messages` path):
```
PERF model=claude-fable-5 msgs=1 tok_before=36 cache_read=0
cache_write=61939 cache_hit_pct=0
PERF model=claude-fable-5 msgs=3 tok_before=796 cache_read=0
cache_write=63308 cache_hit_pct=0
PERF model=claude-fable-5 msgs=5 tok_before=935 cache_read=63308
cache_write=215 cache_hit_pct=100
```
Prompt caching survives the proxy (100% hit on the follow-up turn).
- Routing stats (:8788 session): `requests.total: 2, by_provider:
{"anthropic": 2}, by_model: {"claude-fable-5": 2}`, per-project prefix
`/p/headroom-wrap-omp` attributed.
- Unwrap: `Removed wrap-created models.yml` (file gone); isolated
pre-existing-file run: backup created, user's `my-gw` provider preserved
in the managed file, and after `unwrap omp` the restored file is
**byte-identical** (`cmp` clean).
- Compression: **not observed in this environment** — `tok_saved=0`,
`transforms=router:noop` / `too_small`. Honest reading: omp minimizes
its own tool outputs client-side (a 300-item JSON tool result reached
the proxy at only ~657 tokens) and the `[ml]` text compressor wasn't
installed; small print-mode payloads sit below crush thresholds, and
passthrough-by-default is the documented safety contract. The wrap's
value here is proven at the routing/lifecycle/cache layer; compression
numbers will match whatever the proxy does for a given content mix.
- Not tested: Windows / Linux; lean-ctx mode with omp
(`HEADROOM_CONTEXT_TOOL=lean-ctx` — `lean-ctx init --agent omp` depends
on lean-ctx recognizing the agent; failure degrades with a warning by
design); long interactive (non `-p`) sessions; `--memory` / `--learn` /
`--code-graph` flags combined with omp; OAuth-vs-API-key matrix beyond
my local account.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes — all
except the 3 documented pre-existing failures, which fail identically on
unmodified origin/main
- [x] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
N/A — terminal evidence inline above.
## Additional Notes
- The models.yml override is regenerated from the pristine backup on
every wrap, so re-running with a different `--port` updates the endpoint
idempotently and the backup is never clobbered.
- Scope note from #1149 stands: this routes omp's **Anthropic** provider
family. omp's other providers (OpenAI-direct, Gemini, ...) resolve their
endpoints from their own registry entries; users can already point those
at Headroom with their own custom provider in `models.yml`.
- `headroom/providers/omp/` deliberately contains no install-time / MCP
pieces — this is the thin wrap + unwrap slice only.
---------
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
Co-authored-by: Tejas Chopra <chopratejas@gmail.com>
2026-07-16 04:30:19 +09:00
|
|
|
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert captured["tool_label"] == "OMP"
|
|
|
|
|
assert captured["agent_type"] == "omp"
|
|
|
|
|
assert captured["args"] == ("-p", "fix the bug")
|
|
|
|
|
|
|
|
|
|
text_at_launch = captured["models_text_at_launch"]
|
|
|
|
|
assert isinstance(text_at_launch, str)
|
|
|
|
|
assert MANAGED_MARKER in text_at_launch
|
|
|
|
|
base_url = yaml.safe_load(text_at_launch)["providers"]["anthropic"]["baseUrl"]
|
|
|
|
|
assert base_url.startswith("http://127.0.0.1:8787/p/")
|
|
|
|
|
|
|
|
|
|
display = captured["env_vars_display"]
|
|
|
|
|
assert isinstance(display, list)
|
|
|
|
|
assert f"models.yml: providers.anthropic.baseUrl={base_url}" in display
|
|
|
|
|
|
|
|
|
|
|
fix: remove rtk and lean-ctx CLI context tools (#2677)
## Description
Removes both third-party CLI context tools — **rtk** and **lean-ctx** —
and with them the context-tool selector itself. Headroom no longer
downloads, installs or configures either one, and there is no
replacement.
The previous pass (#2344) gated only three entry points inside
`headroom/cli/wrap.py`. That left the feature reachable in practice:
| Gap | Effect |
|---|---|
| `scripts/install.sh:1544`, `install.ps1:1681` | Ran `rtk init --global
--auto-patch` from bash/PowerShell, **bypassing the Python gate
entirely** — `curl \| sh` still wrote a Claude Code `PreToolUse` hook
regardless of `HEADROOM_RTK` |
| `wrap.py` `_setup_context_tool_for_agent` | **`wrap openhands` was
broken by default**: `rtk_required=True` met a gate returning `None` →
`SystemExit(1)`. Invisible because all 8 openhands tests patched
`_ensure_rtk_binary` to a fake path |
| `proxy/helpers.py`, `subscription/tracker.py` | Proxy shelled out to
`rtk gain` from `/stats`, the dashboard and `headroom perf`; the tracker
polled it per contribution (`_RTK_WIRING_DEFAULT = "enabled"`) |
| No cleanup path | Nothing removed artifacts an earlier default had
installed, so a machine that once ran the old default kept rtk in the
loop forever (#1669, #1955) |
Also worth noting: the rtk binary download had **no SHA or signature
verification** — only `rtk --version` as a smoke test.
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [x] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [x] Code refactoring (no functional changes)
## Changes Made
**Removed** — `headroom/rtk/` and `headroom/lean_ctx/` packages,
`headroom/cli/wrap_rtk_metrics.py`, `_selected_context_tool` /
`_setup_context_tool_for_agent` / `_VALID_CONTEXT_TOOLS`, the `--rtk` /
`--no-rtk` / `--no-project-rtk` / `--keep-rtk` flags across all 18 wrap
subcommands, `HEADROOM_RTK*`, the proxy-side `rtk gain` polling, the
dashboard CLI-filtering panel (rows + all 8 `cliFiltering*` Alpine
getters), `paths.rtk_path()` / `lean_ctx_path()`, the SDK path helpers,
`benchmarks/rtk_loop_learn_eval.py`, and the `headroom/rtk/**` CI path
filters.
**Fails loudly, not silently** — `--context-tool` / `--no-context-tool`
/ `HEADROOM_CONTEXT_TOOL` are kept solely to error out. They live in
shell profiles, aliases and CI jobs, and accepting them as a no-op would
read as Headroom having quietly stopped working. The installers reject
them too, which matters more than it looks: their arg parsers forward
the first unknown flag **and everything after it** to the wrapped tool,
so a leftover `--no-rtk` would have silently swallowed a following
`--port` and then been ignored downstream.
**New `headroom/context_tool_cleanup.py`** — deleting the code cannot
help a machine that already ran the old default, since the hooks,
binaries and injected guidance are durable on disk.
`purge_context_tool_artifacts()` runs once per `wrap`/`unwrap` and
removes the registered hook entries, the generated hook scripts, the
Headroom-managed `~/.local/bin` symlinks, the vendored
`~/.headroom/bin/{rtk,lean-ctx}` binaries, the `lean-ctx` MCP server
entry and the marker-fenced instruction blocks. Deliberately
conservative: idempotent, **skips** a malformed config rather than
overwriting it, and only unlinks a symlink resolving inside Headroom's
own bin dir so a user's own build is untouched. It reports on
**stderr**, because `wrap/unwrap openclaw --prepare-only` emit
machine-readable JSON on stdout as their entire contract. Skipped for
`wrap selfheal` (runs from a SessionStart hook; must not race Claude
Code's writer for `~/.claude.json`) and for `--help`, which must stay
read-only.
**Client-config hardening** (discovered while investigating a "corrupted
Serena settings file" report) — `wrap.py` reset a settings file to `{}`
when an existing file would not parse, then wrote that back. One
hand-edited typo or a transient `EACCES`/`EINTR` on a valid file
destroyed the user's `permissions`, `env` and `hooks`, on **every
`headroom wrap claude`**. It now refuses to write. Separately,
`fsutil.write_text` is now atomic (temp file + `fsync` + `os.replace`),
fixing all 14 non-atomic client-config writes at once; it follows
symlinks rather than replacing them (dotfile managers) and preserves an
existing file's mode.
**Deliberately kept** — `rtk` stays in the wrapper-peel list in
`transforms/content_router.py`. It sits beside `sudo`/`env`/`timeout` as
shell-command grammar, so `rtk cat f` is still classified as a file read
for anyone running their own rtk install, which the purge intentionally
leaves alone.
## Testing
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ ruff check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
All checks passed!
$ ruff format --check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
1255 files already formatted
$ mypy headroom/
Success: no issues found in 508 source files
$ pytest tests/test_context_tool_cleanup.py -q
11 passed
$ pytest tests/test_fsutil.py -q
12 passed
$ pytest tests/test_cli/test_wrap_codex.py -q # 89 tests
89 passed in 431.68s
$ pytest tests/test_cli/test_wrap_opencode.py -q
39 passed in 257.46s
$ pytest tests/test_cli/test_wrap_helpers.py -q
45 passed
$ pytest tests/test_paths.py -q
75 passed
$ pytest tests/test_cli/test_unwrap_claude.py -q
14 passed
$ pytest tests/test_proxy_savings_history.py -q
39 passed
$ pytest tests/test_cli/test_wrap_copilot.py -q
27 passed
$ pytest tests/test_cli/test_wrap_zcode.py -q
20 passed
$ pytest tests/test_subscription_tracker.py -q
9 passed
$ pytest tests/test_proxy_dashboard_stats_cache.py -q
5 passed, 1 skipped
```
Repo-wide grep for 14 removed symbols (`headroom.rtk`,
`headroom.lean_ctx`, `_ensure_rtk_binary`, `_selected_context_tool`,
`_get_context_tool_stats`, `rtk_path`, `lean_ctx_path`,
`wrap_rtk_metrics`, `HEADROOM_RTK`, `cli_tokens_avoided`,
`tokens_saved_rtk`, …) across `*.py`, `*.ts`, `*.sh`, `*.ps1`, `*.yml`,
`*.html`: **zero hits**.
Notable test changes: `test_wrap_openhands.py` no longer patches
`_ensure_rtk_binary` and asserts `wrap openhands --prepare-only` exits 0
unpatched — the regression that was previously masked.
`test_wrap_continue.py` and `test_wrap_hintfile_agents.py` were removed
(every test drove RTK instruction injection). A new
`test_subscription_tracker.py::test_load_state_written_before_cli_context_tools_were_removed`
proves a pre-removal `subscription_state.json` still loads.
## Real Behavior Proof
- **Environment:** macOS 15.4 (darwin 25.4.0), Python 3.12.6, Headroom @
this branch, real `~/.headroom` and `~/.claude` on the dev machine.
- **Exact command / steps and observed result:**
```text
# 1. Retired flag fails loudly instead of silently no-op'ing
$ headroom wrap codex --prepare-only --context-tool rtk
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: they
rewrote shell commands through a third-party binary Headroom no longer manages.
Drop --context-tool / --no-context-tool and unset HEADROOM_CONTEXT_TOOL;
`headroom wrap` uninstalls what they left behind on first run.
$ HEADROOM_CONTEXT_TOOL=lean-ctx headroom wrap codex --prepare-only
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: ...
# 2. install.sh rejects the retired flags (extracted parse_wrap_args harness)
['--no-rtk', '--port', '9999'] rc=1 ERROR: CLI context tools ... Drop --no-rtk
['--context-tool=rtk'] rc=1 ERROR: CLI context tools ... Drop --context-tool
$ bash -n scripts/install.sh # syntax OK
# 3. Purge ran against the real machine, which had all the orphaned artifacts
$ python -c "from headroom.context_tool_cleanup import purge_context_tool_artifacts; ..."
removed ~/.headroom/bin/lean-ctx (51 MB)
removed ~/.headroom/bin/rtk (7.7 MB)
removed ~/.local/bin/rtk (symlink into ~/.headroom/bin)
removed ~/.claude/hooks/rtk-rewrite.sh
removed 8 lean-ctx-* hook scripts
# ~/.claude.json afterwards: 90 top-level keys, 19 projects, mcpServers unchanged
# → ~59 MB reclaimed, no unrelated key touched
# 4. stdout stays machine-readable while the purge reports (planted a fake artifact)
$ headroom wrap openclaw --prepare-only --gateway-provider-id codex >out 2>err
$ cat out
{"enabled":true,"config":{"proxyPort":8787,...}} # parses as JSON
$ cat err
Retired CLI context tool cleanup: removed /Users/tcms/.headroom/bin/rtk
# 5. --help is inert (planted artifact survives), a real run purges
$ headroom wrap codex --help → artifact survived: CORRECT
$ headroom wrap openclaw --prepare-only → purged: CORRECT
# 6. MCP purge dry-run against a copy of the real 82 KB ~/.claude.json
top-level keys 90 -> 90; projects 19 -> 19; LOST keys: none
all content outside mcpServers byte-identical: True
```
Dashboard rendered via the Playwright test after the panel removal:
"Token Savings" shows only `Proxy 0 (0.0%)` / `Of total wire: 36.86%`,
and "Token Usage" reads Before Compression → Proxy Removed → After
Compression with no "Filtered (this session)" row. Nothing below the
removed panel broke.
- **Not tested:** Windows and Linux (macOS only) — `install.ps1` is
verified by brace-balance and inspection, not executed, since no `pwsh`
is available locally. The wrap e2e suite (`e2e/wrap/run.py`) was updated
but not run; it needs the Docker e2e image. `serena project index`
interaction is exercised in the stacked base PR.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I did **not** edit `CHANGELOG.md` — it is generated by
release-please from my Conventional Commit PR title (a CI guard enforces
this)
## Additional Notes
**Stacked on #2676** (`tejas/serena-config-bootstrap`) — please merge
that first; this PR's base should then be retargeted to `main`, or it
will read as containing that fix too.
**Breaking-change migration for users:**
- Drop `--rtk`, `--no-rtk`, `--no-project-rtk`, `--keep-rtk`,
`--context-tool`, `--no-context-tool` from any alias, script or CI job,
and unset `HEADROOM_RTK*` / `HEADROOM_CONTEXT_TOOL`. They now error
rather than being ignored, so the failure is immediate and
self-explaining.
- Previously-installed artifacts are purged automatically on the next
`wrap`/`unwrap`; no manual cleanup needed.
- `headroom perf --json` no longer carries a `cli_filtering` key, and
`/stats` no longer returns a `context_tool` section.
**Docs:** `docs/rtk-architecture.md` deleted; RTK/lean-ctx removed from
`README.md`,
`docs/content/docs/{configuration,opencode,grok-build,docker-install,filesystem-contract}.mdx`,
`docs/observability.md` and the matching `wiki/` pages.
`REALIGNMENT/09-phase-G-rtk-observability.md` is marked SUPERSEDED
rather than deleted, to keep the planning record.
**Follow-ups not in scope:** `_emit_wrap_interrupted` was deleted as
dead code — its only caller was the `except KeyboardInterrupt` guarding
the binary download, so with no download there is nothing slow left to
interrupt.
2026-07-30 22:59:41 -07:00
|
|
|
def test_wrap_omp_does_not_write_agents_md(
|
|
|
|
|
runner: CliRunner, omp_home: Path, tmp_path: Path
|
feat(wrap): add omp target (Oh My Pi) with models.yml override and unwrap (#1811)
## Description
Adds `headroom wrap omp` / `headroom unwrap omp` — a one-command wrap
for [Oh My Pi](https://www.npmjs.com/package/@oh-my-pi/pi-coding-agent)
(`omp`), the pi-mono-lineage coding agent, as proposed in #1149.
One honest correction to the issue: #1149 proposed reusing the
`ANTHROPIC_BASE_URL` redirect from `wrap claude`. During implementation
I probed that empirically and it turned out to be wrong — omp only reads
`ANTHROPIC_BASE_URL` in its web-search helper; its **chat** endpoint
comes from the model registry (`providers.anthropic.baseUrl` in
`~/.omp/agent/models.yml`). With the env var pointed at a local probe
server, omp's chat traffic still went straight to the real endpoint (0
probe hits); with a `models.yml` same-ID override, every request arrived
at the probe (9/9 hits on `/v1/messages`). A same-ID override keeps
omp's bundled Anthropic model catalog and stored credentials (both keyed
by provider id `anthropic`), so only the endpoint moves.
The wrap therefore injects a marker-fenced `providers.anthropic.baseUrl`
override into `models.yml`, snapshotting the pre-wrap file
**byte-for-byte** first, and `headroom unwrap omp` restores it exactly
(or removes the file when the wrap created it) — the same durable-wrap +
backup + unwrap contract `wrap codex` uses for `config.toml`.
Closes #1149
## Type of Change
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- `headroom/providers/omp/` (new provider slice): `models_yml_path()`
(honors `PI_CODING_AGENT_DIR`), `inject_models_override()` (yaml-merge
preserving user providers; pristine byte-for-byte backup, never
re-snapshotted while managed), `restore_models_override()` (`restored` /
`removed` / `noop`; never touches an unmanaged file),
`build_launch_env()`
- `headroom/cli/wrap.py`: `wrap omp` (mirrors the aider/vibe
`_launch_tool` shape; rtk instructions into the project's `AGENTS.md`,
which omp reads natively) and `unwrap omp` (restore models.yml + scrub
rtk block + stop proxy)
- `headroom/telemetry/context.py`: `omp` added to `_KNOWN_WRAP_AGENTS`
so the stack slug reports `wrap_omp` instead of `unknown`
- `README.md` (agent matrix row + unwrap list), `llms.txt`,
`CHANGELOG.md`
- `tests/test_cli/test_wrap_omp.py`: 16 tests (injection
fresh/merge/re-inject, restore statuses incl. unmanaged-file safety, env
passthrough, CLI wiring, unwrap flows)
## Testing
- [ ] Unit tests pass (`pytest`) — all new + `test_cli` tests pass; the
full suite carries **3 pre-existing failures** that reproduce
identically on unmodified `origin/main` (same set, same asserts — see
Test Output and the rebase-validation comment)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ uv run pytest -q # post-rebase, base 4f22cbb0
3 failed, 7723 passed, 515 skipped in 262.64s
FAILED tests/test_cli/test_wrap_claude_base_url.py::test_wrap_marker_is_stale_when_pid_reused
FAILED tests/test_rtk_session_savings.py::test_rtk_reader_returns_none_on_nonzero_exit
FAILED tests/test_rtk_session_savings.py::test_lean_ctx_reader_returns_none_on_failure_and_logs
→ all three reproduce identically on unmodified origin/main (4f22cbb0), run the
same way (same worktree + venv, sources switched): 3 failed, 7707 passed —
this branch = baseline + the 16 new tests, nothing else changes.
(The pre-rebase run against e8151f05 showed the same shape: one order-dependent
flake that also reproduced on its baseline; these are env/order-dependent.)
$ uv run pytest tests/test_cli/ -q # post-rebase
542 passed + 1 of the pre-existing failures above # includes the 16 new test_wrap_omp.py tests
$ uv run ruff check . ; echo ruff-check-exit:$?
All checks passed!
ruff-check-exit:0
$ uv run ruff format --check . # post-rebase
1 pre-existing violation: headroom/proxy/handlers/anthropic.py — flagged identically
on unmodified origin/main (not touched by this PR); every file this PR touches is clean
$ uv run mypy headroom # post-rebase; output redirected to file; exit captured
Success: no issues found in 409 source files
mypy-exit:0
```
## Real Behavior Proof
- Environment: macOS 15 (arm64, M1 Pro), Python 3.12.13 (uv venv,
editable install incl. Rust `_core`), headroom @ this branch, base
extras only (no `[ml]`), Anthropic account signed into omp. Initial
proof ran on base e8151f05 with omp 16.3.6 (`@oh-my-pi/pi-coding-agent`
via bun); re-validated after the rebase onto 4f22cbb0 with omp 16.3.11 —
fresh numbers in the rebase-validation comment.
- Exact command / steps: four scenarios, run in this order —
1. Mechanism probe (why models.yml, not env): local HTTP probe server on
`127.0.0.1:18999`; ran `omp -p "say ok" --model claude-fable-5
--no-session --no-tools` once with
`ANTHROPIC_BASE_URL=http://127.0.0.1:18999`, once with
`~/.omp/agent/models.yml` containing `providers.anthropic.baseUrl:
http://127.0.0.1:18999`.
2. One-command path: `headroom wrap omp --no-rtk --port 8790 -- -p "Read
CHANGELOG.md and count how many '### Fixed' headings it contains. Answer
with just the number." --model claude-fable-5 --no-session --max-time
180`
3. Routing stats: separate proxy on :8788, wrap with `--no-proxy`, then
`GET /stats`.
4. Restore: `headroom unwrap omp`, plus an isolated
`PI_CODING_AGENT_DIR=/tmp/omp-agent-test` run with a pre-existing user
`models.yml`, then `cmp` against the original.
- Observed result: end-to-end routing through the proxy proven for every
scenario —
- Probe: env-var run → **0 probe hits**, omp answered normally
(bypassed). models.yml run → **9 hits on `/v1/messages?beta=true`** with
real Messages bodies. This is the routing mechanism the wrap uses.
- One-command run: wrap started the proxy ("Proxy ready on
http://127.0.0.1:8790"), wrote the override (`models.yml:
providers.anthropic.baseUrl=http://127.0.0.1:8790/p/headroom-wrap-omp`),
launched omp, and omp answered **"7"** (correct — real `read` tool work
through the proxy). Proxy log for the session (3 requests,
`anthropic_messages` path):
```
PERF model=claude-fable-5 msgs=1 tok_before=36 cache_read=0
cache_write=61939 cache_hit_pct=0
PERF model=claude-fable-5 msgs=3 tok_before=796 cache_read=0
cache_write=63308 cache_hit_pct=0
PERF model=claude-fable-5 msgs=5 tok_before=935 cache_read=63308
cache_write=215 cache_hit_pct=100
```
Prompt caching survives the proxy (100% hit on the follow-up turn).
- Routing stats (:8788 session): `requests.total: 2, by_provider:
{"anthropic": 2}, by_model: {"claude-fable-5": 2}`, per-project prefix
`/p/headroom-wrap-omp` attributed.
- Unwrap: `Removed wrap-created models.yml` (file gone); isolated
pre-existing-file run: backup created, user's `my-gw` provider preserved
in the managed file, and after `unwrap omp` the restored file is
**byte-identical** (`cmp` clean).
- Compression: **not observed in this environment** — `tok_saved=0`,
`transforms=router:noop` / `too_small`. Honest reading: omp minimizes
its own tool outputs client-side (a 300-item JSON tool result reached
the proxy at only ~657 tokens) and the `[ml]` text compressor wasn't
installed; small print-mode payloads sit below crush thresholds, and
passthrough-by-default is the documented safety contract. The wrap's
value here is proven at the routing/lifecycle/cache layer; compression
numbers will match whatever the proxy does for a given content mix.
- Not tested: Windows / Linux; lean-ctx mode with omp
(`HEADROOM_CONTEXT_TOOL=lean-ctx` — `lean-ctx init --agent omp` depends
on lean-ctx recognizing the agent; failure degrades with a warning by
design); long interactive (non `-p`) sessions; `--memory` / `--learn` /
`--code-graph` flags combined with omp; OAuth-vs-API-key matrix beyond
my local account.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes — all
except the 3 documented pre-existing failures, which fail identically on
unmodified origin/main
- [x] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
N/A — terminal evidence inline above.
## Additional Notes
- The models.yml override is regenerated from the pristine backup on
every wrap, so re-running with a different `--port` updates the endpoint
idempotently and the backup is never clobbered.
- Scope note from #1149 stands: this routes omp's **Anthropic** provider
family. omp's other providers (OpenAI-direct, Gemini, ...) resolve their
endpoints from their own registry entries; users can already point those
at Headroom with their own custom provider in `models.yml`.
- `headroom/providers/omp/` deliberately contains no install-time / MCP
pieces — this is the thin wrap + unwrap slice only.
---------
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
Co-authored-by: Tejas Chopra <chopratejas@gmail.com>
2026-07-16 04:30:19 +09:00
|
|
|
) -> None:
|
fix: remove rtk and lean-ctx CLI context tools (#2677)
## Description
Removes both third-party CLI context tools — **rtk** and **lean-ctx** —
and with them the context-tool selector itself. Headroom no longer
downloads, installs or configures either one, and there is no
replacement.
The previous pass (#2344) gated only three entry points inside
`headroom/cli/wrap.py`. That left the feature reachable in practice:
| Gap | Effect |
|---|---|
| `scripts/install.sh:1544`, `install.ps1:1681` | Ran `rtk init --global
--auto-patch` from bash/PowerShell, **bypassing the Python gate
entirely** — `curl \| sh` still wrote a Claude Code `PreToolUse` hook
regardless of `HEADROOM_RTK` |
| `wrap.py` `_setup_context_tool_for_agent` | **`wrap openhands` was
broken by default**: `rtk_required=True` met a gate returning `None` →
`SystemExit(1)`. Invisible because all 8 openhands tests patched
`_ensure_rtk_binary` to a fake path |
| `proxy/helpers.py`, `subscription/tracker.py` | Proxy shelled out to
`rtk gain` from `/stats`, the dashboard and `headroom perf`; the tracker
polled it per contribution (`_RTK_WIRING_DEFAULT = "enabled"`) |
| No cleanup path | Nothing removed artifacts an earlier default had
installed, so a machine that once ran the old default kept rtk in the
loop forever (#1669, #1955) |
Also worth noting: the rtk binary download had **no SHA or signature
verification** — only `rtk --version` as a smoke test.
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [x] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [x] Code refactoring (no functional changes)
## Changes Made
**Removed** — `headroom/rtk/` and `headroom/lean_ctx/` packages,
`headroom/cli/wrap_rtk_metrics.py`, `_selected_context_tool` /
`_setup_context_tool_for_agent` / `_VALID_CONTEXT_TOOLS`, the `--rtk` /
`--no-rtk` / `--no-project-rtk` / `--keep-rtk` flags across all 18 wrap
subcommands, `HEADROOM_RTK*`, the proxy-side `rtk gain` polling, the
dashboard CLI-filtering panel (rows + all 8 `cliFiltering*` Alpine
getters), `paths.rtk_path()` / `lean_ctx_path()`, the SDK path helpers,
`benchmarks/rtk_loop_learn_eval.py`, and the `headroom/rtk/**` CI path
filters.
**Fails loudly, not silently** — `--context-tool` / `--no-context-tool`
/ `HEADROOM_CONTEXT_TOOL` are kept solely to error out. They live in
shell profiles, aliases and CI jobs, and accepting them as a no-op would
read as Headroom having quietly stopped working. The installers reject
them too, which matters more than it looks: their arg parsers forward
the first unknown flag **and everything after it** to the wrapped tool,
so a leftover `--no-rtk` would have silently swallowed a following
`--port` and then been ignored downstream.
**New `headroom/context_tool_cleanup.py`** — deleting the code cannot
help a machine that already ran the old default, since the hooks,
binaries and injected guidance are durable on disk.
`purge_context_tool_artifacts()` runs once per `wrap`/`unwrap` and
removes the registered hook entries, the generated hook scripts, the
Headroom-managed `~/.local/bin` symlinks, the vendored
`~/.headroom/bin/{rtk,lean-ctx}` binaries, the `lean-ctx` MCP server
entry and the marker-fenced instruction blocks. Deliberately
conservative: idempotent, **skips** a malformed config rather than
overwriting it, and only unlinks a symlink resolving inside Headroom's
own bin dir so a user's own build is untouched. It reports on
**stderr**, because `wrap/unwrap openclaw --prepare-only` emit
machine-readable JSON on stdout as their entire contract. Skipped for
`wrap selfheal` (runs from a SessionStart hook; must not race Claude
Code's writer for `~/.claude.json`) and for `--help`, which must stay
read-only.
**Client-config hardening** (discovered while investigating a "corrupted
Serena settings file" report) — `wrap.py` reset a settings file to `{}`
when an existing file would not parse, then wrote that back. One
hand-edited typo or a transient `EACCES`/`EINTR` on a valid file
destroyed the user's `permissions`, `env` and `hooks`, on **every
`headroom wrap claude`**. It now refuses to write. Separately,
`fsutil.write_text` is now atomic (temp file + `fsync` + `os.replace`),
fixing all 14 non-atomic client-config writes at once; it follows
symlinks rather than replacing them (dotfile managers) and preserves an
existing file's mode.
**Deliberately kept** — `rtk` stays in the wrapper-peel list in
`transforms/content_router.py`. It sits beside `sudo`/`env`/`timeout` as
shell-command grammar, so `rtk cat f` is still classified as a file read
for anyone running their own rtk install, which the purge intentionally
leaves alone.
## Testing
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ ruff check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
All checks passed!
$ ruff format --check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
1255 files already formatted
$ mypy headroom/
Success: no issues found in 508 source files
$ pytest tests/test_context_tool_cleanup.py -q
11 passed
$ pytest tests/test_fsutil.py -q
12 passed
$ pytest tests/test_cli/test_wrap_codex.py -q # 89 tests
89 passed in 431.68s
$ pytest tests/test_cli/test_wrap_opencode.py -q
39 passed in 257.46s
$ pytest tests/test_cli/test_wrap_helpers.py -q
45 passed
$ pytest tests/test_paths.py -q
75 passed
$ pytest tests/test_cli/test_unwrap_claude.py -q
14 passed
$ pytest tests/test_proxy_savings_history.py -q
39 passed
$ pytest tests/test_cli/test_wrap_copilot.py -q
27 passed
$ pytest tests/test_cli/test_wrap_zcode.py -q
20 passed
$ pytest tests/test_subscription_tracker.py -q
9 passed
$ pytest tests/test_proxy_dashboard_stats_cache.py -q
5 passed, 1 skipped
```
Repo-wide grep for 14 removed symbols (`headroom.rtk`,
`headroom.lean_ctx`, `_ensure_rtk_binary`, `_selected_context_tool`,
`_get_context_tool_stats`, `rtk_path`, `lean_ctx_path`,
`wrap_rtk_metrics`, `HEADROOM_RTK`, `cli_tokens_avoided`,
`tokens_saved_rtk`, …) across `*.py`, `*.ts`, `*.sh`, `*.ps1`, `*.yml`,
`*.html`: **zero hits**.
Notable test changes: `test_wrap_openhands.py` no longer patches
`_ensure_rtk_binary` and asserts `wrap openhands --prepare-only` exits 0
unpatched — the regression that was previously masked.
`test_wrap_continue.py` and `test_wrap_hintfile_agents.py` were removed
(every test drove RTK instruction injection). A new
`test_subscription_tracker.py::test_load_state_written_before_cli_context_tools_were_removed`
proves a pre-removal `subscription_state.json` still loads.
## Real Behavior Proof
- **Environment:** macOS 15.4 (darwin 25.4.0), Python 3.12.6, Headroom @
this branch, real `~/.headroom` and `~/.claude` on the dev machine.
- **Exact command / steps and observed result:**
```text
# 1. Retired flag fails loudly instead of silently no-op'ing
$ headroom wrap codex --prepare-only --context-tool rtk
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: they
rewrote shell commands through a third-party binary Headroom no longer manages.
Drop --context-tool / --no-context-tool and unset HEADROOM_CONTEXT_TOOL;
`headroom wrap` uninstalls what they left behind on first run.
$ HEADROOM_CONTEXT_TOOL=lean-ctx headroom wrap codex --prepare-only
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: ...
# 2. install.sh rejects the retired flags (extracted parse_wrap_args harness)
['--no-rtk', '--port', '9999'] rc=1 ERROR: CLI context tools ... Drop --no-rtk
['--context-tool=rtk'] rc=1 ERROR: CLI context tools ... Drop --context-tool
$ bash -n scripts/install.sh # syntax OK
# 3. Purge ran against the real machine, which had all the orphaned artifacts
$ python -c "from headroom.context_tool_cleanup import purge_context_tool_artifacts; ..."
removed ~/.headroom/bin/lean-ctx (51 MB)
removed ~/.headroom/bin/rtk (7.7 MB)
removed ~/.local/bin/rtk (symlink into ~/.headroom/bin)
removed ~/.claude/hooks/rtk-rewrite.sh
removed 8 lean-ctx-* hook scripts
# ~/.claude.json afterwards: 90 top-level keys, 19 projects, mcpServers unchanged
# → ~59 MB reclaimed, no unrelated key touched
# 4. stdout stays machine-readable while the purge reports (planted a fake artifact)
$ headroom wrap openclaw --prepare-only --gateway-provider-id codex >out 2>err
$ cat out
{"enabled":true,"config":{"proxyPort":8787,...}} # parses as JSON
$ cat err
Retired CLI context tool cleanup: removed /Users/tcms/.headroom/bin/rtk
# 5. --help is inert (planted artifact survives), a real run purges
$ headroom wrap codex --help → artifact survived: CORRECT
$ headroom wrap openclaw --prepare-only → purged: CORRECT
# 6. MCP purge dry-run against a copy of the real 82 KB ~/.claude.json
top-level keys 90 -> 90; projects 19 -> 19; LOST keys: none
all content outside mcpServers byte-identical: True
```
Dashboard rendered via the Playwright test after the panel removal:
"Token Savings" shows only `Proxy 0 (0.0%)` / `Of total wire: 36.86%`,
and "Token Usage" reads Before Compression → Proxy Removed → After
Compression with no "Filtered (this session)" row. Nothing below the
removed panel broke.
- **Not tested:** Windows and Linux (macOS only) — `install.ps1` is
verified by brace-balance and inspection, not executed, since no `pwsh`
is available locally. The wrap e2e suite (`e2e/wrap/run.py`) was updated
but not run; it needs the Docker e2e image. `serena project index`
interaction is exercised in the stacked base PR.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I did **not** edit `CHANGELOG.md` — it is generated by
release-please from my Conventional Commit PR title (a CI guard enforces
this)
## Additional Notes
**Stacked on #2676** (`tejas/serena-config-bootstrap`) — please merge
that first; this PR's base should then be retargeted to `main`, or it
will read as containing that fix too.
**Breaking-change migration for users:**
- Drop `--rtk`, `--no-rtk`, `--no-project-rtk`, `--keep-rtk`,
`--context-tool`, `--no-context-tool` from any alias, script or CI job,
and unset `HEADROOM_RTK*` / `HEADROOM_CONTEXT_TOOL`. They now error
rather than being ignored, so the failure is immediate and
self-explaining.
- Previously-installed artifacts are purged automatically on the next
`wrap`/`unwrap`; no manual cleanup needed.
- `headroom perf --json` no longer carries a `cli_filtering` key, and
`/stats` no longer returns a `context_tool` section.
**Docs:** `docs/rtk-architecture.md` deleted; RTK/lean-ctx removed from
`README.md`,
`docs/content/docs/{configuration,opencode,grok-build,docker-install,filesystem-contract}.mdx`,
`docs/observability.md` and the matching `wiki/` pages.
`REALIGNMENT/09-phase-G-rtk-observability.md` is marked SUPERSEDED
rather than deleted, to keep the planning record.
**Follow-ups not in scope:** `_emit_wrap_interrupted` was deleted as
dead code — its only caller was the `except KeyboardInterrupt` guarding
the binary download, so with no download there is nothing slow left to
interrupt.
2026-07-30 22:59:41 -07:00
|
|
|
"""`wrap omp` redirects via models.yml only; it never authors AGENTS.md."""
|
feat(wrap): add omp target (Oh My Pi) with models.yml override and unwrap (#1811)
## Description
Adds `headroom wrap omp` / `headroom unwrap omp` — a one-command wrap
for [Oh My Pi](https://www.npmjs.com/package/@oh-my-pi/pi-coding-agent)
(`omp`), the pi-mono-lineage coding agent, as proposed in #1149.
One honest correction to the issue: #1149 proposed reusing the
`ANTHROPIC_BASE_URL` redirect from `wrap claude`. During implementation
I probed that empirically and it turned out to be wrong — omp only reads
`ANTHROPIC_BASE_URL` in its web-search helper; its **chat** endpoint
comes from the model registry (`providers.anthropic.baseUrl` in
`~/.omp/agent/models.yml`). With the env var pointed at a local probe
server, omp's chat traffic still went straight to the real endpoint (0
probe hits); with a `models.yml` same-ID override, every request arrived
at the probe (9/9 hits on `/v1/messages`). A same-ID override keeps
omp's bundled Anthropic model catalog and stored credentials (both keyed
by provider id `anthropic`), so only the endpoint moves.
The wrap therefore injects a marker-fenced `providers.anthropic.baseUrl`
override into `models.yml`, snapshotting the pre-wrap file
**byte-for-byte** first, and `headroom unwrap omp` restores it exactly
(or removes the file when the wrap created it) — the same durable-wrap +
backup + unwrap contract `wrap codex` uses for `config.toml`.
Closes #1149
## Type of Change
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- `headroom/providers/omp/` (new provider slice): `models_yml_path()`
(honors `PI_CODING_AGENT_DIR`), `inject_models_override()` (yaml-merge
preserving user providers; pristine byte-for-byte backup, never
re-snapshotted while managed), `restore_models_override()` (`restored` /
`removed` / `noop`; never touches an unmanaged file),
`build_launch_env()`
- `headroom/cli/wrap.py`: `wrap omp` (mirrors the aider/vibe
`_launch_tool` shape; rtk instructions into the project's `AGENTS.md`,
which omp reads natively) and `unwrap omp` (restore models.yml + scrub
rtk block + stop proxy)
- `headroom/telemetry/context.py`: `omp` added to `_KNOWN_WRAP_AGENTS`
so the stack slug reports `wrap_omp` instead of `unknown`
- `README.md` (agent matrix row + unwrap list), `llms.txt`,
`CHANGELOG.md`
- `tests/test_cli/test_wrap_omp.py`: 16 tests (injection
fresh/merge/re-inject, restore statuses incl. unmanaged-file safety, env
passthrough, CLI wiring, unwrap flows)
## Testing
- [ ] Unit tests pass (`pytest`) — all new + `test_cli` tests pass; the
full suite carries **3 pre-existing failures** that reproduce
identically on unmodified `origin/main` (same set, same asserts — see
Test Output and the rebase-validation comment)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ uv run pytest -q # post-rebase, base 4f22cbb0
3 failed, 7723 passed, 515 skipped in 262.64s
FAILED tests/test_cli/test_wrap_claude_base_url.py::test_wrap_marker_is_stale_when_pid_reused
FAILED tests/test_rtk_session_savings.py::test_rtk_reader_returns_none_on_nonzero_exit
FAILED tests/test_rtk_session_savings.py::test_lean_ctx_reader_returns_none_on_failure_and_logs
→ all three reproduce identically on unmodified origin/main (4f22cbb0), run the
same way (same worktree + venv, sources switched): 3 failed, 7707 passed —
this branch = baseline + the 16 new tests, nothing else changes.
(The pre-rebase run against e8151f05 showed the same shape: one order-dependent
flake that also reproduced on its baseline; these are env/order-dependent.)
$ uv run pytest tests/test_cli/ -q # post-rebase
542 passed + 1 of the pre-existing failures above # includes the 16 new test_wrap_omp.py tests
$ uv run ruff check . ; echo ruff-check-exit:$?
All checks passed!
ruff-check-exit:0
$ uv run ruff format --check . # post-rebase
1 pre-existing violation: headroom/proxy/handlers/anthropic.py — flagged identically
on unmodified origin/main (not touched by this PR); every file this PR touches is clean
$ uv run mypy headroom # post-rebase; output redirected to file; exit captured
Success: no issues found in 409 source files
mypy-exit:0
```
## Real Behavior Proof
- Environment: macOS 15 (arm64, M1 Pro), Python 3.12.13 (uv venv,
editable install incl. Rust `_core`), headroom @ this branch, base
extras only (no `[ml]`), Anthropic account signed into omp. Initial
proof ran on base e8151f05 with omp 16.3.6 (`@oh-my-pi/pi-coding-agent`
via bun); re-validated after the rebase onto 4f22cbb0 with omp 16.3.11 —
fresh numbers in the rebase-validation comment.
- Exact command / steps: four scenarios, run in this order —
1. Mechanism probe (why models.yml, not env): local HTTP probe server on
`127.0.0.1:18999`; ran `omp -p "say ok" --model claude-fable-5
--no-session --no-tools` once with
`ANTHROPIC_BASE_URL=http://127.0.0.1:18999`, once with
`~/.omp/agent/models.yml` containing `providers.anthropic.baseUrl:
http://127.0.0.1:18999`.
2. One-command path: `headroom wrap omp --no-rtk --port 8790 -- -p "Read
CHANGELOG.md and count how many '### Fixed' headings it contains. Answer
with just the number." --model claude-fable-5 --no-session --max-time
180`
3. Routing stats: separate proxy on :8788, wrap with `--no-proxy`, then
`GET /stats`.
4. Restore: `headroom unwrap omp`, plus an isolated
`PI_CODING_AGENT_DIR=/tmp/omp-agent-test` run with a pre-existing user
`models.yml`, then `cmp` against the original.
- Observed result: end-to-end routing through the proxy proven for every
scenario —
- Probe: env-var run → **0 probe hits**, omp answered normally
(bypassed). models.yml run → **9 hits on `/v1/messages?beta=true`** with
real Messages bodies. This is the routing mechanism the wrap uses.
- One-command run: wrap started the proxy ("Proxy ready on
http://127.0.0.1:8790"), wrote the override (`models.yml:
providers.anthropic.baseUrl=http://127.0.0.1:8790/p/headroom-wrap-omp`),
launched omp, and omp answered **"7"** (correct — real `read` tool work
through the proxy). Proxy log for the session (3 requests,
`anthropic_messages` path):
```
PERF model=claude-fable-5 msgs=1 tok_before=36 cache_read=0
cache_write=61939 cache_hit_pct=0
PERF model=claude-fable-5 msgs=3 tok_before=796 cache_read=0
cache_write=63308 cache_hit_pct=0
PERF model=claude-fable-5 msgs=5 tok_before=935 cache_read=63308
cache_write=215 cache_hit_pct=100
```
Prompt caching survives the proxy (100% hit on the follow-up turn).
- Routing stats (:8788 session): `requests.total: 2, by_provider:
{"anthropic": 2}, by_model: {"claude-fable-5": 2}`, per-project prefix
`/p/headroom-wrap-omp` attributed.
- Unwrap: `Removed wrap-created models.yml` (file gone); isolated
pre-existing-file run: backup created, user's `my-gw` provider preserved
in the managed file, and after `unwrap omp` the restored file is
**byte-identical** (`cmp` clean).
- Compression: **not observed in this environment** — `tok_saved=0`,
`transforms=router:noop` / `too_small`. Honest reading: omp minimizes
its own tool outputs client-side (a 300-item JSON tool result reached
the proxy at only ~657 tokens) and the `[ml]` text compressor wasn't
installed; small print-mode payloads sit below crush thresholds, and
passthrough-by-default is the documented safety contract. The wrap's
value here is proven at the routing/lifecycle/cache layer; compression
numbers will match whatever the proxy does for a given content mix.
- Not tested: Windows / Linux; lean-ctx mode with omp
(`HEADROOM_CONTEXT_TOOL=lean-ctx` — `lean-ctx init --agent omp` depends
on lean-ctx recognizing the agent; failure degrades with a warning by
design); long interactive (non `-p`) sessions; `--memory` / `--learn` /
`--code-graph` flags combined with omp; OAuth-vs-API-key matrix beyond
my local account.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes — all
except the 3 documented pre-existing failures, which fail identically on
unmodified origin/main
- [x] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
N/A — terminal evidence inline above.
## Additional Notes
- The models.yml override is regenerated from the pristine backup on
every wrap, so re-running with a different `--port` updates the endpoint
idempotently and the backup is never clobbered.
- Scope note from #1149 stands: this routes omp's **Anthropic** provider
family. omp's other providers (OpenAI-direct, Gemini, ...) resolve their
endpoints from their own registry entries; users can already point those
at Headroom with their own custom provider in `models.yml`.
- `headroom/providers/omp/` deliberately contains no install-time / MCP
pieces — this is the thin wrap + unwrap slice only.
---------
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
Co-authored-by: Tejas Chopra <chopratejas@gmail.com>
2026-07-16 04:30:19 +09:00
|
|
|
with (
|
|
|
|
|
patch("headroom.cli.wrap.shutil.which", return_value="omp"),
|
|
|
|
|
patch("headroom.cli.wrap._launch_tool"),
|
|
|
|
|
):
|
|
|
|
|
result = runner.invoke(main, ["wrap", "omp"])
|
|
|
|
|
|
|
|
|
|
assert result.exit_code == 0, result.output
|
fix: remove rtk and lean-ctx CLI context tools (#2677)
## Description
Removes both third-party CLI context tools — **rtk** and **lean-ctx** —
and with them the context-tool selector itself. Headroom no longer
downloads, installs or configures either one, and there is no
replacement.
The previous pass (#2344) gated only three entry points inside
`headroom/cli/wrap.py`. That left the feature reachable in practice:
| Gap | Effect |
|---|---|
| `scripts/install.sh:1544`, `install.ps1:1681` | Ran `rtk init --global
--auto-patch` from bash/PowerShell, **bypassing the Python gate
entirely** — `curl \| sh` still wrote a Claude Code `PreToolUse` hook
regardless of `HEADROOM_RTK` |
| `wrap.py` `_setup_context_tool_for_agent` | **`wrap openhands` was
broken by default**: `rtk_required=True` met a gate returning `None` →
`SystemExit(1)`. Invisible because all 8 openhands tests patched
`_ensure_rtk_binary` to a fake path |
| `proxy/helpers.py`, `subscription/tracker.py` | Proxy shelled out to
`rtk gain` from `/stats`, the dashboard and `headroom perf`; the tracker
polled it per contribution (`_RTK_WIRING_DEFAULT = "enabled"`) |
| No cleanup path | Nothing removed artifacts an earlier default had
installed, so a machine that once ran the old default kept rtk in the
loop forever (#1669, #1955) |
Also worth noting: the rtk binary download had **no SHA or signature
verification** — only `rtk --version` as a smoke test.
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [x] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [x] Code refactoring (no functional changes)
## Changes Made
**Removed** — `headroom/rtk/` and `headroom/lean_ctx/` packages,
`headroom/cli/wrap_rtk_metrics.py`, `_selected_context_tool` /
`_setup_context_tool_for_agent` / `_VALID_CONTEXT_TOOLS`, the `--rtk` /
`--no-rtk` / `--no-project-rtk` / `--keep-rtk` flags across all 18 wrap
subcommands, `HEADROOM_RTK*`, the proxy-side `rtk gain` polling, the
dashboard CLI-filtering panel (rows + all 8 `cliFiltering*` Alpine
getters), `paths.rtk_path()` / `lean_ctx_path()`, the SDK path helpers,
`benchmarks/rtk_loop_learn_eval.py`, and the `headroom/rtk/**` CI path
filters.
**Fails loudly, not silently** — `--context-tool` / `--no-context-tool`
/ `HEADROOM_CONTEXT_TOOL` are kept solely to error out. They live in
shell profiles, aliases and CI jobs, and accepting them as a no-op would
read as Headroom having quietly stopped working. The installers reject
them too, which matters more than it looks: their arg parsers forward
the first unknown flag **and everything after it** to the wrapped tool,
so a leftover `--no-rtk` would have silently swallowed a following
`--port` and then been ignored downstream.
**New `headroom/context_tool_cleanup.py`** — deleting the code cannot
help a machine that already ran the old default, since the hooks,
binaries and injected guidance are durable on disk.
`purge_context_tool_artifacts()` runs once per `wrap`/`unwrap` and
removes the registered hook entries, the generated hook scripts, the
Headroom-managed `~/.local/bin` symlinks, the vendored
`~/.headroom/bin/{rtk,lean-ctx}` binaries, the `lean-ctx` MCP server
entry and the marker-fenced instruction blocks. Deliberately
conservative: idempotent, **skips** a malformed config rather than
overwriting it, and only unlinks a symlink resolving inside Headroom's
own bin dir so a user's own build is untouched. It reports on
**stderr**, because `wrap/unwrap openclaw --prepare-only` emit
machine-readable JSON on stdout as their entire contract. Skipped for
`wrap selfheal` (runs from a SessionStart hook; must not race Claude
Code's writer for `~/.claude.json`) and for `--help`, which must stay
read-only.
**Client-config hardening** (discovered while investigating a "corrupted
Serena settings file" report) — `wrap.py` reset a settings file to `{}`
when an existing file would not parse, then wrote that back. One
hand-edited typo or a transient `EACCES`/`EINTR` on a valid file
destroyed the user's `permissions`, `env` and `hooks`, on **every
`headroom wrap claude`**. It now refuses to write. Separately,
`fsutil.write_text` is now atomic (temp file + `fsync` + `os.replace`),
fixing all 14 non-atomic client-config writes at once; it follows
symlinks rather than replacing them (dotfile managers) and preserves an
existing file's mode.
**Deliberately kept** — `rtk` stays in the wrapper-peel list in
`transforms/content_router.py`. It sits beside `sudo`/`env`/`timeout` as
shell-command grammar, so `rtk cat f` is still classified as a file read
for anyone running their own rtk install, which the purge intentionally
leaves alone.
## Testing
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ ruff check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
All checks passed!
$ ruff format --check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
1255 files already formatted
$ mypy headroom/
Success: no issues found in 508 source files
$ pytest tests/test_context_tool_cleanup.py -q
11 passed
$ pytest tests/test_fsutil.py -q
12 passed
$ pytest tests/test_cli/test_wrap_codex.py -q # 89 tests
89 passed in 431.68s
$ pytest tests/test_cli/test_wrap_opencode.py -q
39 passed in 257.46s
$ pytest tests/test_cli/test_wrap_helpers.py -q
45 passed
$ pytest tests/test_paths.py -q
75 passed
$ pytest tests/test_cli/test_unwrap_claude.py -q
14 passed
$ pytest tests/test_proxy_savings_history.py -q
39 passed
$ pytest tests/test_cli/test_wrap_copilot.py -q
27 passed
$ pytest tests/test_cli/test_wrap_zcode.py -q
20 passed
$ pytest tests/test_subscription_tracker.py -q
9 passed
$ pytest tests/test_proxy_dashboard_stats_cache.py -q
5 passed, 1 skipped
```
Repo-wide grep for 14 removed symbols (`headroom.rtk`,
`headroom.lean_ctx`, `_ensure_rtk_binary`, `_selected_context_tool`,
`_get_context_tool_stats`, `rtk_path`, `lean_ctx_path`,
`wrap_rtk_metrics`, `HEADROOM_RTK`, `cli_tokens_avoided`,
`tokens_saved_rtk`, …) across `*.py`, `*.ts`, `*.sh`, `*.ps1`, `*.yml`,
`*.html`: **zero hits**.
Notable test changes: `test_wrap_openhands.py` no longer patches
`_ensure_rtk_binary` and asserts `wrap openhands --prepare-only` exits 0
unpatched — the regression that was previously masked.
`test_wrap_continue.py` and `test_wrap_hintfile_agents.py` were removed
(every test drove RTK instruction injection). A new
`test_subscription_tracker.py::test_load_state_written_before_cli_context_tools_were_removed`
proves a pre-removal `subscription_state.json` still loads.
## Real Behavior Proof
- **Environment:** macOS 15.4 (darwin 25.4.0), Python 3.12.6, Headroom @
this branch, real `~/.headroom` and `~/.claude` on the dev machine.
- **Exact command / steps and observed result:**
```text
# 1. Retired flag fails loudly instead of silently no-op'ing
$ headroom wrap codex --prepare-only --context-tool rtk
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: they
rewrote shell commands through a third-party binary Headroom no longer manages.
Drop --context-tool / --no-context-tool and unset HEADROOM_CONTEXT_TOOL;
`headroom wrap` uninstalls what they left behind on first run.
$ HEADROOM_CONTEXT_TOOL=lean-ctx headroom wrap codex --prepare-only
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: ...
# 2. install.sh rejects the retired flags (extracted parse_wrap_args harness)
['--no-rtk', '--port', '9999'] rc=1 ERROR: CLI context tools ... Drop --no-rtk
['--context-tool=rtk'] rc=1 ERROR: CLI context tools ... Drop --context-tool
$ bash -n scripts/install.sh # syntax OK
# 3. Purge ran against the real machine, which had all the orphaned artifacts
$ python -c "from headroom.context_tool_cleanup import purge_context_tool_artifacts; ..."
removed ~/.headroom/bin/lean-ctx (51 MB)
removed ~/.headroom/bin/rtk (7.7 MB)
removed ~/.local/bin/rtk (symlink into ~/.headroom/bin)
removed ~/.claude/hooks/rtk-rewrite.sh
removed 8 lean-ctx-* hook scripts
# ~/.claude.json afterwards: 90 top-level keys, 19 projects, mcpServers unchanged
# → ~59 MB reclaimed, no unrelated key touched
# 4. stdout stays machine-readable while the purge reports (planted a fake artifact)
$ headroom wrap openclaw --prepare-only --gateway-provider-id codex >out 2>err
$ cat out
{"enabled":true,"config":{"proxyPort":8787,...}} # parses as JSON
$ cat err
Retired CLI context tool cleanup: removed /Users/tcms/.headroom/bin/rtk
# 5. --help is inert (planted artifact survives), a real run purges
$ headroom wrap codex --help → artifact survived: CORRECT
$ headroom wrap openclaw --prepare-only → purged: CORRECT
# 6. MCP purge dry-run against a copy of the real 82 KB ~/.claude.json
top-level keys 90 -> 90; projects 19 -> 19; LOST keys: none
all content outside mcpServers byte-identical: True
```
Dashboard rendered via the Playwright test after the panel removal:
"Token Savings" shows only `Proxy 0 (0.0%)` / `Of total wire: 36.86%`,
and "Token Usage" reads Before Compression → Proxy Removed → After
Compression with no "Filtered (this session)" row. Nothing below the
removed panel broke.
- **Not tested:** Windows and Linux (macOS only) — `install.ps1` is
verified by brace-balance and inspection, not executed, since no `pwsh`
is available locally. The wrap e2e suite (`e2e/wrap/run.py`) was updated
but not run; it needs the Docker e2e image. `serena project index`
interaction is exercised in the stacked base PR.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I did **not** edit `CHANGELOG.md` — it is generated by
release-please from my Conventional Commit PR title (a CI guard enforces
this)
## Additional Notes
**Stacked on #2676** (`tejas/serena-config-bootstrap`) — please merge
that first; this PR's base should then be retargeted to `main`, or it
will read as containing that fix too.
**Breaking-change migration for users:**
- Drop `--rtk`, `--no-rtk`, `--no-project-rtk`, `--keep-rtk`,
`--context-tool`, `--no-context-tool` from any alias, script or CI job,
and unset `HEADROOM_RTK*` / `HEADROOM_CONTEXT_TOOL`. They now error
rather than being ignored, so the failure is immediate and
self-explaining.
- Previously-installed artifacts are purged automatically on the next
`wrap`/`unwrap`; no manual cleanup needed.
- `headroom perf --json` no longer carries a `cli_filtering` key, and
`/stats` no longer returns a `context_tool` section.
**Docs:** `docs/rtk-architecture.md` deleted; RTK/lean-ctx removed from
`README.md`,
`docs/content/docs/{configuration,opencode,grok-build,docker-install,filesystem-contract}.mdx`,
`docs/observability.md` and the matching `wiki/` pages.
`REALIGNMENT/09-phase-G-rtk-observability.md` is marked SUPERSEDED
rather than deleted, to keep the planning record.
**Follow-ups not in scope:** `_emit_wrap_interrupted` was deleted as
dead code — its only caller was the `except KeyboardInterrupt` guarding
the binary download, so with no download there is nothing slow left to
interrupt.
2026-07-30 22:59:41 -07:00
|
|
|
assert not (tmp_path / "AGENTS.md").exists()
|
feat(wrap): add omp target (Oh My Pi) with models.yml override and unwrap (#1811)
## Description
Adds `headroom wrap omp` / `headroom unwrap omp` — a one-command wrap
for [Oh My Pi](https://www.npmjs.com/package/@oh-my-pi/pi-coding-agent)
(`omp`), the pi-mono-lineage coding agent, as proposed in #1149.
One honest correction to the issue: #1149 proposed reusing the
`ANTHROPIC_BASE_URL` redirect from `wrap claude`. During implementation
I probed that empirically and it turned out to be wrong — omp only reads
`ANTHROPIC_BASE_URL` in its web-search helper; its **chat** endpoint
comes from the model registry (`providers.anthropic.baseUrl` in
`~/.omp/agent/models.yml`). With the env var pointed at a local probe
server, omp's chat traffic still went straight to the real endpoint (0
probe hits); with a `models.yml` same-ID override, every request arrived
at the probe (9/9 hits on `/v1/messages`). A same-ID override keeps
omp's bundled Anthropic model catalog and stored credentials (both keyed
by provider id `anthropic`), so only the endpoint moves.
The wrap therefore injects a marker-fenced `providers.anthropic.baseUrl`
override into `models.yml`, snapshotting the pre-wrap file
**byte-for-byte** first, and `headroom unwrap omp` restores it exactly
(or removes the file when the wrap created it) — the same durable-wrap +
backup + unwrap contract `wrap codex` uses for `config.toml`.
Closes #1149
## Type of Change
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- `headroom/providers/omp/` (new provider slice): `models_yml_path()`
(honors `PI_CODING_AGENT_DIR`), `inject_models_override()` (yaml-merge
preserving user providers; pristine byte-for-byte backup, never
re-snapshotted while managed), `restore_models_override()` (`restored` /
`removed` / `noop`; never touches an unmanaged file),
`build_launch_env()`
- `headroom/cli/wrap.py`: `wrap omp` (mirrors the aider/vibe
`_launch_tool` shape; rtk instructions into the project's `AGENTS.md`,
which omp reads natively) and `unwrap omp` (restore models.yml + scrub
rtk block + stop proxy)
- `headroom/telemetry/context.py`: `omp` added to `_KNOWN_WRAP_AGENTS`
so the stack slug reports `wrap_omp` instead of `unknown`
- `README.md` (agent matrix row + unwrap list), `llms.txt`,
`CHANGELOG.md`
- `tests/test_cli/test_wrap_omp.py`: 16 tests (injection
fresh/merge/re-inject, restore statuses incl. unmanaged-file safety, env
passthrough, CLI wiring, unwrap flows)
## Testing
- [ ] Unit tests pass (`pytest`) — all new + `test_cli` tests pass; the
full suite carries **3 pre-existing failures** that reproduce
identically on unmodified `origin/main` (same set, same asserts — see
Test Output and the rebase-validation comment)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ uv run pytest -q # post-rebase, base 4f22cbb0
3 failed, 7723 passed, 515 skipped in 262.64s
FAILED tests/test_cli/test_wrap_claude_base_url.py::test_wrap_marker_is_stale_when_pid_reused
FAILED tests/test_rtk_session_savings.py::test_rtk_reader_returns_none_on_nonzero_exit
FAILED tests/test_rtk_session_savings.py::test_lean_ctx_reader_returns_none_on_failure_and_logs
→ all three reproduce identically on unmodified origin/main (4f22cbb0), run the
same way (same worktree + venv, sources switched): 3 failed, 7707 passed —
this branch = baseline + the 16 new tests, nothing else changes.
(The pre-rebase run against e8151f05 showed the same shape: one order-dependent
flake that also reproduced on its baseline; these are env/order-dependent.)
$ uv run pytest tests/test_cli/ -q # post-rebase
542 passed + 1 of the pre-existing failures above # includes the 16 new test_wrap_omp.py tests
$ uv run ruff check . ; echo ruff-check-exit:$?
All checks passed!
ruff-check-exit:0
$ uv run ruff format --check . # post-rebase
1 pre-existing violation: headroom/proxy/handlers/anthropic.py — flagged identically
on unmodified origin/main (not touched by this PR); every file this PR touches is clean
$ uv run mypy headroom # post-rebase; output redirected to file; exit captured
Success: no issues found in 409 source files
mypy-exit:0
```
## Real Behavior Proof
- Environment: macOS 15 (arm64, M1 Pro), Python 3.12.13 (uv venv,
editable install incl. Rust `_core`), headroom @ this branch, base
extras only (no `[ml]`), Anthropic account signed into omp. Initial
proof ran on base e8151f05 with omp 16.3.6 (`@oh-my-pi/pi-coding-agent`
via bun); re-validated after the rebase onto 4f22cbb0 with omp 16.3.11 —
fresh numbers in the rebase-validation comment.
- Exact command / steps: four scenarios, run in this order —
1. Mechanism probe (why models.yml, not env): local HTTP probe server on
`127.0.0.1:18999`; ran `omp -p "say ok" --model claude-fable-5
--no-session --no-tools` once with
`ANTHROPIC_BASE_URL=http://127.0.0.1:18999`, once with
`~/.omp/agent/models.yml` containing `providers.anthropic.baseUrl:
http://127.0.0.1:18999`.
2. One-command path: `headroom wrap omp --no-rtk --port 8790 -- -p "Read
CHANGELOG.md and count how many '### Fixed' headings it contains. Answer
with just the number." --model claude-fable-5 --no-session --max-time
180`
3. Routing stats: separate proxy on :8788, wrap with `--no-proxy`, then
`GET /stats`.
4. Restore: `headroom unwrap omp`, plus an isolated
`PI_CODING_AGENT_DIR=/tmp/omp-agent-test` run with a pre-existing user
`models.yml`, then `cmp` against the original.
- Observed result: end-to-end routing through the proxy proven for every
scenario —
- Probe: env-var run → **0 probe hits**, omp answered normally
(bypassed). models.yml run → **9 hits on `/v1/messages?beta=true`** with
real Messages bodies. This is the routing mechanism the wrap uses.
- One-command run: wrap started the proxy ("Proxy ready on
http://127.0.0.1:8790"), wrote the override (`models.yml:
providers.anthropic.baseUrl=http://127.0.0.1:8790/p/headroom-wrap-omp`),
launched omp, and omp answered **"7"** (correct — real `read` tool work
through the proxy). Proxy log for the session (3 requests,
`anthropic_messages` path):
```
PERF model=claude-fable-5 msgs=1 tok_before=36 cache_read=0
cache_write=61939 cache_hit_pct=0
PERF model=claude-fable-5 msgs=3 tok_before=796 cache_read=0
cache_write=63308 cache_hit_pct=0
PERF model=claude-fable-5 msgs=5 tok_before=935 cache_read=63308
cache_write=215 cache_hit_pct=100
```
Prompt caching survives the proxy (100% hit on the follow-up turn).
- Routing stats (:8788 session): `requests.total: 2, by_provider:
{"anthropic": 2}, by_model: {"claude-fable-5": 2}`, per-project prefix
`/p/headroom-wrap-omp` attributed.
- Unwrap: `Removed wrap-created models.yml` (file gone); isolated
pre-existing-file run: backup created, user's `my-gw` provider preserved
in the managed file, and after `unwrap omp` the restored file is
**byte-identical** (`cmp` clean).
- Compression: **not observed in this environment** — `tok_saved=0`,
`transforms=router:noop` / `too_small`. Honest reading: omp minimizes
its own tool outputs client-side (a 300-item JSON tool result reached
the proxy at only ~657 tokens) and the `[ml]` text compressor wasn't
installed; small print-mode payloads sit below crush thresholds, and
passthrough-by-default is the documented safety contract. The wrap's
value here is proven at the routing/lifecycle/cache layer; compression
numbers will match whatever the proxy does for a given content mix.
- Not tested: Windows / Linux; lean-ctx mode with omp
(`HEADROOM_CONTEXT_TOOL=lean-ctx` — `lean-ctx init --agent omp` depends
on lean-ctx recognizing the agent; failure degrades with a warning by
design); long interactive (non `-p`) sessions; `--memory` / `--learn` /
`--code-graph` flags combined with omp; OAuth-vs-API-key matrix beyond
my local account.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes — all
except the 3 documented pre-existing failures, which fail identically on
unmodified origin/main
- [x] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
N/A — terminal evidence inline above.
## Additional Notes
- The models.yml override is regenerated from the pristine backup on
every wrap, so re-running with a different `--port` updates the endpoint
idempotently and the backup is never clobbered.
- Scope note from #1149 stands: this routes omp's **Anthropic** provider
family. omp's other providers (OpenAI-direct, Gemini, ...) resolve their
endpoints from their own registry entries; users can already point those
at Headroom with their own custom provider in `models.yml`.
- `headroom/providers/omp/` deliberately contains no install-time / MCP
pieces — this is the thin wrap + unwrap slice only.
---------
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
Co-authored-by: Tejas Chopra <chopratejas@gmail.com>
2026-07-16 04:30:19 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# CLI: unwrap omp
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
fix: remove rtk and lean-ctx CLI context tools (#2677)
## Description
Removes both third-party CLI context tools — **rtk** and **lean-ctx** —
and with them the context-tool selector itself. Headroom no longer
downloads, installs or configures either one, and there is no
replacement.
The previous pass (#2344) gated only three entry points inside
`headroom/cli/wrap.py`. That left the feature reachable in practice:
| Gap | Effect |
|---|---|
| `scripts/install.sh:1544`, `install.ps1:1681` | Ran `rtk init --global
--auto-patch` from bash/PowerShell, **bypassing the Python gate
entirely** — `curl \| sh` still wrote a Claude Code `PreToolUse` hook
regardless of `HEADROOM_RTK` |
| `wrap.py` `_setup_context_tool_for_agent` | **`wrap openhands` was
broken by default**: `rtk_required=True` met a gate returning `None` →
`SystemExit(1)`. Invisible because all 8 openhands tests patched
`_ensure_rtk_binary` to a fake path |
| `proxy/helpers.py`, `subscription/tracker.py` | Proxy shelled out to
`rtk gain` from `/stats`, the dashboard and `headroom perf`; the tracker
polled it per contribution (`_RTK_WIRING_DEFAULT = "enabled"`) |
| No cleanup path | Nothing removed artifacts an earlier default had
installed, so a machine that once ran the old default kept rtk in the
loop forever (#1669, #1955) |
Also worth noting: the rtk binary download had **no SHA or signature
verification** — only `rtk --version` as a smoke test.
## Type of Change
- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [x] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [x] Code refactoring (no functional changes)
## Changes Made
**Removed** — `headroom/rtk/` and `headroom/lean_ctx/` packages,
`headroom/cli/wrap_rtk_metrics.py`, `_selected_context_tool` /
`_setup_context_tool_for_agent` / `_VALID_CONTEXT_TOOLS`, the `--rtk` /
`--no-rtk` / `--no-project-rtk` / `--keep-rtk` flags across all 18 wrap
subcommands, `HEADROOM_RTK*`, the proxy-side `rtk gain` polling, the
dashboard CLI-filtering panel (rows + all 8 `cliFiltering*` Alpine
getters), `paths.rtk_path()` / `lean_ctx_path()`, the SDK path helpers,
`benchmarks/rtk_loop_learn_eval.py`, and the `headroom/rtk/**` CI path
filters.
**Fails loudly, not silently** — `--context-tool` / `--no-context-tool`
/ `HEADROOM_CONTEXT_TOOL` are kept solely to error out. They live in
shell profiles, aliases and CI jobs, and accepting them as a no-op would
read as Headroom having quietly stopped working. The installers reject
them too, which matters more than it looks: their arg parsers forward
the first unknown flag **and everything after it** to the wrapped tool,
so a leftover `--no-rtk` would have silently swallowed a following
`--port` and then been ignored downstream.
**New `headroom/context_tool_cleanup.py`** — deleting the code cannot
help a machine that already ran the old default, since the hooks,
binaries and injected guidance are durable on disk.
`purge_context_tool_artifacts()` runs once per `wrap`/`unwrap` and
removes the registered hook entries, the generated hook scripts, the
Headroom-managed `~/.local/bin` symlinks, the vendored
`~/.headroom/bin/{rtk,lean-ctx}` binaries, the `lean-ctx` MCP server
entry and the marker-fenced instruction blocks. Deliberately
conservative: idempotent, **skips** a malformed config rather than
overwriting it, and only unlinks a symlink resolving inside Headroom's
own bin dir so a user's own build is untouched. It reports on
**stderr**, because `wrap/unwrap openclaw --prepare-only` emit
machine-readable JSON on stdout as their entire contract. Skipped for
`wrap selfheal` (runs from a SessionStart hook; must not race Claude
Code's writer for `~/.claude.json`) and for `--help`, which must stay
read-only.
**Client-config hardening** (discovered while investigating a "corrupted
Serena settings file" report) — `wrap.py` reset a settings file to `{}`
when an existing file would not parse, then wrote that back. One
hand-edited typo or a transient `EACCES`/`EINTR` on a valid file
destroyed the user's `permissions`, `env` and `hooks`, on **every
`headroom wrap claude`**. It now refuses to write. Separately,
`fsutil.write_text` is now atomic (temp file + `fsync` + `os.replace`),
fixing all 14 non-atomic client-config writes at once; it follows
symlinks rather than replacing them (dotfile managers) and preserves an
existing file's mode.
**Deliberately kept** — `rtk` stays in the wrapper-peel list in
`transforms/content_router.py`. It sits beside `sudo`/`env`/`timeout` as
shell-command grammar, so `rtk cat f` is still classified as a file read
for anyone running their own rtk install, which the purge intentionally
leaves alone.
## Testing
- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ ruff check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
All checks passed!
$ ruff format --check headroom/ tests/ e2e/ --exclude headroom/dashboard/templates
1255 files already formatted
$ mypy headroom/
Success: no issues found in 508 source files
$ pytest tests/test_context_tool_cleanup.py -q
11 passed
$ pytest tests/test_fsutil.py -q
12 passed
$ pytest tests/test_cli/test_wrap_codex.py -q # 89 tests
89 passed in 431.68s
$ pytest tests/test_cli/test_wrap_opencode.py -q
39 passed in 257.46s
$ pytest tests/test_cli/test_wrap_helpers.py -q
45 passed
$ pytest tests/test_paths.py -q
75 passed
$ pytest tests/test_cli/test_unwrap_claude.py -q
14 passed
$ pytest tests/test_proxy_savings_history.py -q
39 passed
$ pytest tests/test_cli/test_wrap_copilot.py -q
27 passed
$ pytest tests/test_cli/test_wrap_zcode.py -q
20 passed
$ pytest tests/test_subscription_tracker.py -q
9 passed
$ pytest tests/test_proxy_dashboard_stats_cache.py -q
5 passed, 1 skipped
```
Repo-wide grep for 14 removed symbols (`headroom.rtk`,
`headroom.lean_ctx`, `_ensure_rtk_binary`, `_selected_context_tool`,
`_get_context_tool_stats`, `rtk_path`, `lean_ctx_path`,
`wrap_rtk_metrics`, `HEADROOM_RTK`, `cli_tokens_avoided`,
`tokens_saved_rtk`, …) across `*.py`, `*.ts`, `*.sh`, `*.ps1`, `*.yml`,
`*.html`: **zero hits**.
Notable test changes: `test_wrap_openhands.py` no longer patches
`_ensure_rtk_binary` and asserts `wrap openhands --prepare-only` exits 0
unpatched — the regression that was previously masked.
`test_wrap_continue.py` and `test_wrap_hintfile_agents.py` were removed
(every test drove RTK instruction injection). A new
`test_subscription_tracker.py::test_load_state_written_before_cli_context_tools_were_removed`
proves a pre-removal `subscription_state.json` still loads.
## Real Behavior Proof
- **Environment:** macOS 15.4 (darwin 25.4.0), Python 3.12.6, Headroom @
this branch, real `~/.headroom` and `~/.claude` on the dev machine.
- **Exact command / steps and observed result:**
```text
# 1. Retired flag fails loudly instead of silently no-op'ing
$ headroom wrap codex --prepare-only --context-tool rtk
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: they
rewrote shell commands through a third-party binary Headroom no longer manages.
Drop --context-tool / --no-context-tool and unset HEADROOM_CONTEXT_TOOL;
`headroom wrap` uninstalls what they left behind on first run.
$ HEADROOM_CONTEXT_TOOL=lean-ctx headroom wrap codex --prepare-only
Error: CLI context tools (rtk, lean-ctx) have been removed from Headroom: ...
# 2. install.sh rejects the retired flags (extracted parse_wrap_args harness)
['--no-rtk', '--port', '9999'] rc=1 ERROR: CLI context tools ... Drop --no-rtk
['--context-tool=rtk'] rc=1 ERROR: CLI context tools ... Drop --context-tool
$ bash -n scripts/install.sh # syntax OK
# 3. Purge ran against the real machine, which had all the orphaned artifacts
$ python -c "from headroom.context_tool_cleanup import purge_context_tool_artifacts; ..."
removed ~/.headroom/bin/lean-ctx (51 MB)
removed ~/.headroom/bin/rtk (7.7 MB)
removed ~/.local/bin/rtk (symlink into ~/.headroom/bin)
removed ~/.claude/hooks/rtk-rewrite.sh
removed 8 lean-ctx-* hook scripts
# ~/.claude.json afterwards: 90 top-level keys, 19 projects, mcpServers unchanged
# → ~59 MB reclaimed, no unrelated key touched
# 4. stdout stays machine-readable while the purge reports (planted a fake artifact)
$ headroom wrap openclaw --prepare-only --gateway-provider-id codex >out 2>err
$ cat out
{"enabled":true,"config":{"proxyPort":8787,...}} # parses as JSON
$ cat err
Retired CLI context tool cleanup: removed /Users/tcms/.headroom/bin/rtk
# 5. --help is inert (planted artifact survives), a real run purges
$ headroom wrap codex --help → artifact survived: CORRECT
$ headroom wrap openclaw --prepare-only → purged: CORRECT
# 6. MCP purge dry-run against a copy of the real 82 KB ~/.claude.json
top-level keys 90 -> 90; projects 19 -> 19; LOST keys: none
all content outside mcpServers byte-identical: True
```
Dashboard rendered via the Playwright test after the panel removal:
"Token Savings" shows only `Proxy 0 (0.0%)` / `Of total wire: 36.86%`,
and "Token Usage" reads Before Compression → Proxy Removed → After
Compression with no "Filtered (this session)" row. Nothing below the
removed panel broke.
- **Not tested:** Windows and Linux (macOS only) — `install.ps1` is
verified by brace-balance and inspection, not executed, since no `pwsh`
is available locally. The wrap e2e suite (`e2e/wrap/run.py`) was updated
but not run; it needs the Docker e2e image. `serena project index`
interaction is exercised in the stacked base PR.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I did **not** edit `CHANGELOG.md` — it is generated by
release-please from my Conventional Commit PR title (a CI guard enforces
this)
## Additional Notes
**Stacked on #2676** (`tejas/serena-config-bootstrap`) — please merge
that first; this PR's base should then be retargeted to `main`, or it
will read as containing that fix too.
**Breaking-change migration for users:**
- Drop `--rtk`, `--no-rtk`, `--no-project-rtk`, `--keep-rtk`,
`--context-tool`, `--no-context-tool` from any alias, script or CI job,
and unset `HEADROOM_RTK*` / `HEADROOM_CONTEXT_TOOL`. They now error
rather than being ignored, so the failure is immediate and
self-explaining.
- Previously-installed artifacts are purged automatically on the next
`wrap`/`unwrap`; no manual cleanup needed.
- `headroom perf --json` no longer carries a `cli_filtering` key, and
`/stats` no longer returns a `context_tool` section.
**Docs:** `docs/rtk-architecture.md` deleted; RTK/lean-ctx removed from
`README.md`,
`docs/content/docs/{configuration,opencode,grok-build,docker-install,filesystem-contract}.mdx`,
`docs/observability.md` and the matching `wiki/` pages.
`REALIGNMENT/09-phase-G-rtk-observability.md` is marked SUPERSEDED
rather than deleted, to keep the planning record.
**Follow-ups not in scope:** `_emit_wrap_interrupted` was deleted as
dead code — its only caller was the `except KeyboardInterrupt` guarding
the binary download, so with no download there is nothing slow left to
interrupt.
2026-07-30 22:59:41 -07:00
|
|
|
def test_unwrap_omp_restores_pristine_and_stops_proxy(runner: CliRunner, omp_home: Path) -> None:
|
feat(wrap): add omp target (Oh My Pi) with models.yml override and unwrap (#1811)
## Description
Adds `headroom wrap omp` / `headroom unwrap omp` — a one-command wrap
for [Oh My Pi](https://www.npmjs.com/package/@oh-my-pi/pi-coding-agent)
(`omp`), the pi-mono-lineage coding agent, as proposed in #1149.
One honest correction to the issue: #1149 proposed reusing the
`ANTHROPIC_BASE_URL` redirect from `wrap claude`. During implementation
I probed that empirically and it turned out to be wrong — omp only reads
`ANTHROPIC_BASE_URL` in its web-search helper; its **chat** endpoint
comes from the model registry (`providers.anthropic.baseUrl` in
`~/.omp/agent/models.yml`). With the env var pointed at a local probe
server, omp's chat traffic still went straight to the real endpoint (0
probe hits); with a `models.yml` same-ID override, every request arrived
at the probe (9/9 hits on `/v1/messages`). A same-ID override keeps
omp's bundled Anthropic model catalog and stored credentials (both keyed
by provider id `anthropic`), so only the endpoint moves.
The wrap therefore injects a marker-fenced `providers.anthropic.baseUrl`
override into `models.yml`, snapshotting the pre-wrap file
**byte-for-byte** first, and `headroom unwrap omp` restores it exactly
(or removes the file when the wrap created it) — the same durable-wrap +
backup + unwrap contract `wrap codex` uses for `config.toml`.
Closes #1149
## Type of Change
- [ ] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)
## Changes Made
- `headroom/providers/omp/` (new provider slice): `models_yml_path()`
(honors `PI_CODING_AGENT_DIR`), `inject_models_override()` (yaml-merge
preserving user providers; pristine byte-for-byte backup, never
re-snapshotted while managed), `restore_models_override()` (`restored` /
`removed` / `noop`; never touches an unmanaged file),
`build_launch_env()`
- `headroom/cli/wrap.py`: `wrap omp` (mirrors the aider/vibe
`_launch_tool` shape; rtk instructions into the project's `AGENTS.md`,
which omp reads natively) and `unwrap omp` (restore models.yml + scrub
rtk block + stop proxy)
- `headroom/telemetry/context.py`: `omp` added to `_KNOWN_WRAP_AGENTS`
so the stack slug reports `wrap_omp` instead of `unknown`
- `README.md` (agent matrix row + unwrap list), `llms.txt`,
`CHANGELOG.md`
- `tests/test_cli/test_wrap_omp.py`: 16 tests (injection
fresh/merge/re-inject, restore statuses incl. unmanaged-file safety, env
passthrough, CLI wiring, unwrap flows)
## Testing
- [ ] Unit tests pass (`pytest`) — all new + `test_cli` tests pass; the
full suite carries **3 pre-existing failures** that reproduce
identically on unmodified `origin/main` (same set, same asserts — see
Test Output and the rebase-validation comment)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed
### Test Output
```text
$ uv run pytest -q # post-rebase, base 4f22cbb0
3 failed, 7723 passed, 515 skipped in 262.64s
FAILED tests/test_cli/test_wrap_claude_base_url.py::test_wrap_marker_is_stale_when_pid_reused
FAILED tests/test_rtk_session_savings.py::test_rtk_reader_returns_none_on_nonzero_exit
FAILED tests/test_rtk_session_savings.py::test_lean_ctx_reader_returns_none_on_failure_and_logs
→ all three reproduce identically on unmodified origin/main (4f22cbb0), run the
same way (same worktree + venv, sources switched): 3 failed, 7707 passed —
this branch = baseline + the 16 new tests, nothing else changes.
(The pre-rebase run against e8151f05 showed the same shape: one order-dependent
flake that also reproduced on its baseline; these are env/order-dependent.)
$ uv run pytest tests/test_cli/ -q # post-rebase
542 passed + 1 of the pre-existing failures above # includes the 16 new test_wrap_omp.py tests
$ uv run ruff check . ; echo ruff-check-exit:$?
All checks passed!
ruff-check-exit:0
$ uv run ruff format --check . # post-rebase
1 pre-existing violation: headroom/proxy/handlers/anthropic.py — flagged identically
on unmodified origin/main (not touched by this PR); every file this PR touches is clean
$ uv run mypy headroom # post-rebase; output redirected to file; exit captured
Success: no issues found in 409 source files
mypy-exit:0
```
## Real Behavior Proof
- Environment: macOS 15 (arm64, M1 Pro), Python 3.12.13 (uv venv,
editable install incl. Rust `_core`), headroom @ this branch, base
extras only (no `[ml]`), Anthropic account signed into omp. Initial
proof ran on base e8151f05 with omp 16.3.6 (`@oh-my-pi/pi-coding-agent`
via bun); re-validated after the rebase onto 4f22cbb0 with omp 16.3.11 —
fresh numbers in the rebase-validation comment.
- Exact command / steps: four scenarios, run in this order —
1. Mechanism probe (why models.yml, not env): local HTTP probe server on
`127.0.0.1:18999`; ran `omp -p "say ok" --model claude-fable-5
--no-session --no-tools` once with
`ANTHROPIC_BASE_URL=http://127.0.0.1:18999`, once with
`~/.omp/agent/models.yml` containing `providers.anthropic.baseUrl:
http://127.0.0.1:18999`.
2. One-command path: `headroom wrap omp --no-rtk --port 8790 -- -p "Read
CHANGELOG.md and count how many '### Fixed' headings it contains. Answer
with just the number." --model claude-fable-5 --no-session --max-time
180`
3. Routing stats: separate proxy on :8788, wrap with `--no-proxy`, then
`GET /stats`.
4. Restore: `headroom unwrap omp`, plus an isolated
`PI_CODING_AGENT_DIR=/tmp/omp-agent-test` run with a pre-existing user
`models.yml`, then `cmp` against the original.
- Observed result: end-to-end routing through the proxy proven for every
scenario —
- Probe: env-var run → **0 probe hits**, omp answered normally
(bypassed). models.yml run → **9 hits on `/v1/messages?beta=true`** with
real Messages bodies. This is the routing mechanism the wrap uses.
- One-command run: wrap started the proxy ("Proxy ready on
http://127.0.0.1:8790"), wrote the override (`models.yml:
providers.anthropic.baseUrl=http://127.0.0.1:8790/p/headroom-wrap-omp`),
launched omp, and omp answered **"7"** (correct — real `read` tool work
through the proxy). Proxy log for the session (3 requests,
`anthropic_messages` path):
```
PERF model=claude-fable-5 msgs=1 tok_before=36 cache_read=0
cache_write=61939 cache_hit_pct=0
PERF model=claude-fable-5 msgs=3 tok_before=796 cache_read=0
cache_write=63308 cache_hit_pct=0
PERF model=claude-fable-5 msgs=5 tok_before=935 cache_read=63308
cache_write=215 cache_hit_pct=100
```
Prompt caching survives the proxy (100% hit on the follow-up turn).
- Routing stats (:8788 session): `requests.total: 2, by_provider:
{"anthropic": 2}, by_model: {"claude-fable-5": 2}`, per-project prefix
`/p/headroom-wrap-omp` attributed.
- Unwrap: `Removed wrap-created models.yml` (file gone); isolated
pre-existing-file run: backup created, user's `my-gw` provider preserved
in the managed file, and after `unwrap omp` the restored file is
**byte-identical** (`cmp` clean).
- Compression: **not observed in this environment** — `tok_saved=0`,
`transforms=router:noop` / `too_small`. Honest reading: omp minimizes
its own tool outputs client-side (a 300-item JSON tool result reached
the proxy at only ~657 tokens) and the `[ml]` text compressor wasn't
installed; small print-mode payloads sit below crush thresholds, and
passthrough-by-default is the documented safety contract. The wrap's
value here is proven at the routing/lifecycle/cache layer; compression
numbers will match whatever the proxy does for a given content mix.
- Not tested: Windows / Linux; lean-ctx mode with omp
(`HEADROOM_CONTEXT_TOOL=lean-ctx` — `lean-ctx init --agent omp` depends
on lean-ctx recognizing the agent; failure degrades with a warning by
design); long interactive (non `-p`) sessions; `--memory` / `--learn` /
`--code-graph` flags combined with omp; OAuth-vs-API-key matrix beyond
my local account.
## Review Readiness
- [x] I have performed a self-review
- [x] This PR is ready for human review
## Checklist
- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes — all
except the 3 documented pre-existing failures, which fail identically on
unmodified origin/main
- [x] I have updated the CHANGELOG.md if applicable
## Screenshots (if applicable)
N/A — terminal evidence inline above.
## Additional Notes
- The models.yml override is regenerated from the pristine backup on
every wrap, so re-running with a different `--port` updates the endpoint
idempotently and the backup is never clobbered.
- Scope note from #1149 stands: this routes omp's **Anthropic** provider
family. omp's other providers (OpenAI-direct, Gemini, ...) resolve their
endpoints from their own registry entries; users can already point those
at Headroom with their own custom provider in `models.yml`.
- `headroom/providers/omp/` deliberately contains no install-time / MCP
pieces — this is the thin wrap + unwrap slice only.
---------
Co-authored-by: JerrettDavis <mxjerrett@gmail.com>
Co-authored-by: Tejas Chopra <chopratejas@gmail.com>
2026-07-16 04:30:19 +09:00
|
|
|
original = "providers:\n anthropic:\n apiKey: sk-user-secret\n"
|
|
|
|
|
omp_home.write_bytes(original.encode("utf-8"))
|
|
|
|
|
inject_models_override(8787, "proj")
|
|
|
|
|
|
|
|
|
|
stopped: list[int] = []
|
|
|
|
|
with patch(
|
|
|
|
|
"headroom.cli.wrap._stop_local_proxy_for_unwrap",
|
|
|
|
|
side_effect=lambda port: stopped.append(port) or "not_running",
|
|
|
|
|
):
|
|
|
|
|
result = runner.invoke(main, ["unwrap", "omp"])
|
|
|
|
|
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert "Restored pre-wrap models.yml" in result.output
|
|
|
|
|
assert omp_home.read_bytes() == original.encode("utf-8")
|
|
|
|
|
assert not backup_path(omp_home).exists()
|
|
|
|
|
|
|
|
|
|
# A real restore (not a noop) attempts to stop the proxy on the given port.
|
|
|
|
|
assert stopped == [8787]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_unwrap_omp_removes_wrap_created_file(runner: CliRunner, omp_home: Path) -> None:
|
|
|
|
|
inject_models_override(8787, "proj") # fresh create → no backup
|
|
|
|
|
|
|
|
|
|
stopped: list[int] = []
|
|
|
|
|
with patch(
|
|
|
|
|
"headroom.cli.wrap._stop_local_proxy_for_unwrap",
|
|
|
|
|
side_effect=lambda port: stopped.append(port) or "not_running",
|
|
|
|
|
):
|
|
|
|
|
result = runner.invoke(main, ["unwrap", "omp", "--port", "9191"])
|
|
|
|
|
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert "Removed wrap-created models.yml" in result.output
|
|
|
|
|
assert not omp_home.exists()
|
|
|
|
|
assert stopped == [9191]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_unwrap_omp_noop_leaves_unmanaged_and_skips_proxy_stop(
|
|
|
|
|
runner: CliRunner, omp_home: Path
|
|
|
|
|
) -> None:
|
|
|
|
|
user_content = "providers:\n anthropic:\n apiKey: sk-user-secret\n"
|
|
|
|
|
omp_home.write_bytes(user_content.encode("utf-8"))
|
|
|
|
|
|
|
|
|
|
with patch("headroom.cli.wrap._stop_local_proxy_for_unwrap") as stop_proxy:
|
|
|
|
|
result = runner.invoke(main, ["unwrap", "omp"])
|
|
|
|
|
|
|
|
|
|
assert result.exit_code == 0, result.output
|
|
|
|
|
assert "nothing to restore" in result.output
|
|
|
|
|
# Unmanaged file is left exactly as the user had it.
|
|
|
|
|
assert omp_home.read_bytes() == user_content.encode("utf-8")
|
|
|
|
|
# noop status → the proxy is left running (the `status != "noop"` guard).
|
|
|
|
|
stop_proxy.assert_not_called()
|