feat(providers): Codex CLI provider — OpenAI via ModelProvider.OPENAI (#659)

* feat(providers): Codex CLI provider — OpenAI via ModelProvider.OPENAI

Mirrors the grok blueprint end to end: CodexCliProvider (RO ~/.codex
mount, ANTHROPIC_* blanked), an orchestrator-side codex_auth.py
refresher (JWT-exp staleness, atomic rewrite, lock-serialized single-use
rotation, --check backstop; the CLI's own in-process refresh write
no-ops on the RO mount by design — margins keep the orchestrator ahead
of the CLI's 5-minute window), config.toml rendering with required=true
gateway MCP servers, execpolicy deny rules (forbidden-only), per-role
--sandbox (developer=workspace-write, review/doc roles read-only),
codex exec --json with pinned ROBOCO_CODEX_CLI_MODEL (gpt-5.3-codex),
usage summed from typed turn.completed events priced via the real
4-bucket split, dedicated image + entrypoint, registry/park/finalize/
compose/release wiring. V1 excludes interactive intake/secretary.

Per adversarial review: migration 083 seeds the openai provider row
enabled=True (without it every routing path 404'd — the whole feature
was operationally dead code; grok needed the same seed in 039), the
panel picker gained the OpenAI catalog group it silently lacked, and
exit classification is structural — only stderr and error.message
fields from error events are sniffed (word-boundaried patterns, exact
auth phrases, bare 'login' dropped), so the model echoing on-topic
words can never false-park the provider fleet-wide, proven by a
benign-transcript test. Known open risk flagged, not claimed: whether
codex's workspace-write OS sandbox excludes /app is unverified, and no
hook mechanism exists to port the bash-guard defense-in-depth.

* fix(providers): containment barrier on usage.json reads (code scanning)

CodeQL flagged the codex usage read as path injection — correctly:
os.path.basename does not neutralize '..', and the upstream segment
validator isn't in CodeQL's taint model. The grok/codex reads collapse
into one _read_usage_json_contained helper that resolves the built path
and refuses anything outside the resolved usage root — a hostile id can
never escape regardless of upstream drift. Traversal + containment
regression tests added; a stray noqa in the test file replaced with a
named constant per repo rule.

* fix(providers): use realpath+startswith containment CodeQL recognizes

The is_relative_to() guard was a real barrier but not in CodeQL's
py/path-injection sanitizer model, so the alert persisted. Switch to
the canonical os.path.realpath + startswith(root + os.sep) form, which
CodeQL recognizes as a path-traversal barrier; behavior is identical
(refuse any candidate resolving outside the usage root).

* fix(providers): regexp-allowlist the usage-id segment (CodeQL barrier)

Neither is_relative_to nor realpath+startswith was recognized by
CodeQL's py/path-injection sanitizer model across the str->Path->open
flow. Sanitize the tainted component at the source instead: the id must
fullmatch a strict slug token ([A-Za-z0-9][A-Za-z0-9._-]*, no
separators, no '..'), which CodeQL recognizes as a path-injection
barrier; the realpath+startswith containment stays as defense-in-depth.

* fix(providers): standalone regexp guard so CodeQL recognizes the barrier

The sanitizer was one disjunct of a compound 'or' condition, which
CodeQL's guard analysis does not trace as a barrier. Split the regexp
fullmatch into its own single-condition guard (the redundant '..' check
is dropped — the required alphanumeric first char already excludes it).

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>

tests/unit/runtime/test_codex_usage_finalize.py

@@ -0,0 +1,166 @@
+"""OPENAI (codex) agents capture real input/output/cache-split token usage
+from their captured ``usage.json`` — unlike grok's single cumulative total,
+codex's JSONL carries a genuine split (see ``codex_cli_usage``), so finalize
+must return the real 4-tuple instead of folding everything into output.
+"""
+
+from __future__ import annotations
+
+import json
+import tempfile
+from typing import TYPE_CHECKING
+
+import httpx
+import pytest
+from roboco.models.runtime import AgentInstance
+from roboco.runtime import orchestrator as orch_mod
+from roboco.runtime.orchestrator import AgentOrchestrator
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+
+def _write_usage(path: Path, **fields: object) -> None:
+    payload = {
+        "model": "gpt-5.3-codex",
+        "tokens_input": 0,
+        "tokens_output": 0,
+        "tokens_cache_read": 0,
+        "tokens_cache_write": 0,
+        "cost_usd": 0.0,
+        "turns": 1,
+        **fields,
+    }
+    path.write_text(
+        json.dumps(payload),
+        encoding="utf-8",
+    )
+
+
+def test_codex_usage_returns_real_split(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    usage = tmp_path / "usage.json"
+    _write_usage(
+        usage, tokens_input=700, tokens_output=250, tokens_cache_read=300, turns=2
+    )
+    orch = AgentOrchestrator.__new__(AgentOrchestrator)
+    monkeypatch.setattr(
+        orch, "_codex_usage_json", lambda _aid: json.loads(usage.read_text())
+    )
+
+    expected_turns = 2
+    assert orch._codex_usage_tokens("be-dev-1") == (700, 250, 300, 0)
+    assert orch._codex_usage_turns("be-dev-1") == expected_turns
+
+
+def test_read_usage_json_contained_refuses_escape(tmp_path: Path) -> None:
+    """A '..' id resolves outside the usage root and must be refused —
+    basename alone does not neutralize '..', the containment check does."""
+    (tmp_path / "usage.json").write_text('{"leak": 1}', encoding="utf-8")
+    base = tmp_path / "root"
+    base.mkdir()
+
+    assert AgentOrchestrator._read_usage_json_contained(base, "..") is None
+
+
+def test_read_usage_json_contained_reads_inside_root(tmp_path: Path) -> None:
+    agent_dir = tmp_path / "be-dev-1"
+    agent_dir.mkdir()
+    (agent_dir / "usage.json").write_text('{"total_tokens": 5}', encoding="utf-8")
+
+    data = AgentOrchestrator._read_usage_json_contained(tmp_path, "be-dev-1")
+    assert data == {"total_tokens": 5}
+
+
+def test_codex_usage_zero_when_store_missing(monkeypatch: pytest.MonkeyPatch) -> None:
+    orch = AgentOrchestrator.__new__(AgentOrchestrator)
+    monkeypatch.setattr(orch, "_codex_usage_json", lambda _aid: None)
+    assert orch._codex_usage_tokens("be-dev-1") == (0, 0, 0, 0)
+    assert orch._codex_usage_turns("be-dev-1") == 0
+
+
+@pytest.mark.asyncio
+async def test_resolve_final_usage_routes_openai_to_usage_json(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    orch = AgentOrchestrator.__new__(AgentOrchestrator)
+    monkeypatch.setattr(
+        orch,
+        "_codex_usage_json",
+        lambda _aid: {
+            "tokens_input": 12,
+            "tokens_output": 34,
+            "tokens_cache_read": 5,
+            "tokens_cache_write": 1,
+        },
+    )
+    cfg = type("C", (), {"provider_type": "openai"})()
+    orch._instances = {"be-dev-1": AgentInstance(agent_id="be-dev-1", config=cfg)}
+
+    assert await orch._resolve_final_token_usage("be-dev-1") == (12, 34, 5, 1)
+
+
+@pytest.mark.asyncio
+async def test_resolve_final_turns_tools_routes_openai_to_usage_json(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    orch = AgentOrchestrator.__new__(AgentOrchestrator)
+    monkeypatch.setattr(orch, "_codex_usage_turns", lambda _aid: 3)
+    cfg = type("C", (), {"provider_type": "openai"})()
+    orch._instances = {"be-dev-1": AgentInstance(agent_id="be-dev-1", config=cfg)}
+
+    # Codex has no tool-call signal — tool_calls stays 0.
+    assert await orch._resolve_final_turns_tools("be-dev-1") == (3, 0)
+
+
+@pytest.mark.asyncio
+async def test_resolve_active_tokens_routes_openai_to_usage_json(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    orch = AgentOrchestrator.__new__(AgentOrchestrator)
+    monkeypatch.setattr(
+        orch,
+        "_codex_usage_json",
+        lambda _aid: {"tokens_input": 12, "tokens_output": 34},
+    )
+    cfg = type("C", (), {"provider_type": "openai"})()
+    orch._instances = {"be-dev-1": AgentInstance(agent_id="be-dev-1", config=cfg)}
+    async with httpx.AsyncClient() as client:
+        assert await orch._resolve_active_tokens(client, "be-dev-1") == (12, 34, 0, 0)
+
+
+def test_codex_usage_dir_branches_compose_vs_local(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setattr(orch_mod, "PROJECT_HOST_PATH", "")
+    local = AgentOrchestrator._codex_usage_dir("be-dev-1")
+    assert "roboco-codex-usage" in str(local)
+    assert local.name == "be-dev-1"
+
+    monkeypatch.setattr(orch_mod, "PROJECT_HOST_PATH", "/volume1/roboco")
+    monkeypatch.setattr(orch_mod, "CODEX_USAGE_DATA_DIR", "/data/codex-usage")
+    assert str(AgentOrchestrator._codex_usage_dir("be-dev-1")) == (
+        "/data/codex-usage/be-dev-1"
+    )
+
+
+@pytest.mark.parametrize(
+    "bad",
+    ["..", ".", "../etc", "a/b", "a\\b", "", "be-dev-1/../x", "x\x00y"],
+)
+def test_codex_usage_dir_rejects_path_traversal(bad: str) -> None:
+    with pytest.raises(ValueError, match="unsafe agent id"):
+        AgentOrchestrator._codex_usage_dir(bad)
+
+
+def test_codex_usage_json_reads_the_real_local_dir(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    monkeypatch.setattr(orch_mod, "PROJECT_HOST_PATH", "")
+    monkeypatch.setattr(tempfile, "gettempdir", lambda: str(tmp_path))
+    udir = tmp_path / "roboco-codex-usage" / "be-dev-1"
+    udir.mkdir(parents=True)
+    _write_usage(udir / "usage.json", tokens_input=55, tokens_output=10)
+    orch = AgentOrchestrator.__new__(AgentOrchestrator)
+    assert orch._codex_usage_tokens("be-dev-1") == (55, 10, 0, 0)