# Codex CLI 0.164.0: our test log

Canonical: https://theagenticweekly.com/tests/codex-cli · Last verified: 2026-10-25 · Published: 2026-10-25 · Author: Agentic Weekly (operated independently from Texas, US) · Evidence: Tested by us on 2026-10-25. Local open-weight model, not the vendor's hosted models. A smoke test on a CPU-only box, not a benchmark.

> Codex CLI 0.164.0 changed calc.py by running a sed command in its sandbox with a local 3B model; an earlier plain-language edit request ran no edit.

## Result at a glance

Table: Codex CLI test record

| Field | Value |
|---|---|
| Result | Partly worked |
| Version tested | 0.164.0 |
| Date and time | 2026-10-25, 17:45 to 17:51 CDT (America/Chicago) |
| Task | In a throwaway folder, give the tool a small bug and ask a local model to fix it through the tool's own editing. calc.py contained `def add(a,b): return a-b`. Pass means the file ended as `return a+b` after the tool's own edit. |
| Model used | Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11 |
| Hardware | Linux x86_64 virtual machine (Debian 13), 8 vCPU (Intel Xeon, 1 thread per core), 15 GiB RAM, no GPU |
| Run 3 command exit code | 0 |
| Run 3 tokens | 7,934 in (3,930 cached), 152 out |
| Runs kept | 2 (one without an edit, one with) |

## What we found

- With an explicit instruction to run sed, Codex executed the command in its workspace-write sandbox and the command exited 0.
- The plain-language request (run 2) did not edit the file in the log: the small model went to a sub-agent tool call and produced a parse error.
- We kept two Codex logs, so this is two runs, not a pass rate. We did not store a separate file-content check for run 3; the exit code and the command are what the log shows.

## What we ran, step by step

Table: Commands run, wall-clock time and exit code

| Step | Wall time | Exit code | Notes |
|---|---|---|---|
| npm install (shared command, cold) | 15 s | 0 | One command installed four tools: added 12 packages in 15 s. This is the time for all four together, not for one tool. npm warned that three install scripts were not approved (including claude-code 2.1.197 and opencode-ai 1.19.4). |
| Run 2: plain-language edit request | n/a | n/a | The model tried to spawn a sub-agent, a tool call failed to parse ("missing field `type`"), and it ended by printing code in the chat. The log shows no edit command run. |
| Run 3: told to run a sed command | n/a | 0 | Codex ran `sed -i 's/a-b/a+b/' calc.py` in its sandbox; the command exited 0. 7,934 input tokens (3,930 cached), 152 output tokens. |

Exact commands (paths shortened)

```
# npm install (shared command, cold)
npm i @anthropic-ai/claude-code @openai/codex @google/gemini-cli opencode-ai

# Run 2: plain-language edit request
codex exec --oss --local-provider ollama -s workspace-write "The file calc.py is in the current directory. Its add function returns a-b. Use the apply_patch or shell tool to change it so it returns a+b. Do not ask questions; make the edit."

# Run 3: told to run a sed command
codex exec --oss --local-provider ollama -s workspace-write --json   # the prompt told it to run the sed command (exact wording not saved)
```

## Raw output (excerpts)

Run 2 (codex-run2.log, trimmed)

```
OpenAI Codex v0.164.0
model: qwen2.5-3b:latest
provider: ollama
sandbox: workspace-write [workdir, /tmp, $TMPDIR]
collab: SpawnAgent
...
2026-10-25T22:45:01Z ERROR codex_core::tools::router: error=failed to parse function arguments: missing field `type` at line 1 column 336
```

Run 3 (codex-run3.jsonl, trimmed)

```
{"type":"item.completed","item":{"type":"command_execution","command":"/bin/bash -lc \"sed -i 's/a-b/a+b/' calc.py\"","exit_code":0,"status":"completed"}}
{"type":"turn.completed","usage":{"input_tokens":7934,"cached_input_tokens":3930,"output_tokens":152}}
```

## Gotchas and things that broke

- Codex warned that metadata for `qwen2.5-3b:latest` was not found and used fallback metadata; the model name needs the :latest tag.
- The sed command did the edit, not Codex's apply_patch tool, so this does not show that apply_patch works with a small model.

## What we did not test

- ChatGPT sign-in, OpenAI-hosted models, presets, /model and /permissions arguments, MCP sign-in and image previews.
- The apply_patch tool, and any run where the model was left to choose its own editing method successfully.
- Reliability: two runs, so this is not a pass rate.

## Reproduce it

Versions change. These commands install whatever is latest on the day you run them unless a version is pinned, so expect different results later. The version we measured is in the table above.

```
npm i @openai/codex
# create calc.py with `return a-b`, run a local Ollama server, then:
codex exec --oss --local-provider ollama -s workspace-write --json "Run this command in the current directory: sed -i 's/a-b/a+b/' calc.py"
```

## How to read this test

Every number on this page was measured on this one machine, which also ran other jobs, so timings are indicative and vary run to run. A pass means our small task worked once or as stated, a fail means it did not work as we ran it; neither says how the tool behaves with a vendor's frontier model, on a GPU, or at scale. Where a tool could not run without an account or a GPU, we say so instead of guessing.

See the [testing rig](https://theagenticweekly.com/methodology#testing-rig) for the hardware, the local model and the rules we follow, and the [test hub](https://theagenticweekly.com/tests) for every other test.

## FAQ

### Can Codex CLI run against a local model?

It started and ran a shell command with a local Ollama model in our run, with no ChatGPT sign-in. It did not complete a plain-language edit with the small model we used.

## Sources

- [GitHub release rust-v0.164.0](https://github.com/openai/codex/releases/tag/rust-v0.164.0) (fetched 2026-10-25)

## Related

- [All test logs](https://theagenticweekly.com/tests)
- [Methodology and testing rig](https://theagenticweekly.com/methodology#testing-rig)
- [Study: install size and first-task results across 16 frameworks](https://theagenticweekly.com/research/agent-framework-install-and-first-task)
- [Codex CLI facts and sources](https://theagenticweekly.com/tools/codex-cli)

## How to cite

Agentic Weekly, "Codex CLI 0.164.0: our test log", last updated 2026-10-25, https://theagenticweekly.com/tests/codex-cli