Michael Bolin
4511a668f3
Merge 7c21aa3e16 into sapling-pr-archive-bolinfest
2025-05-07 16:59:19 -07:00
Michael Bolin
7c21aa3e16
feat: support map of alternative providers like in TypeScript CLI
2025-05-07 16:59:11 -07:00
Michael Bolin
955584c4ab
merge commit for archive created by Sapling
2025-05-07 16:58:29 -07:00
Michael Bolin
60b522f4ee
feat: support map of alternative providers like in TypeScript CLI
2025-05-07 16:58:21 -07:00
Michael Bolin
86ff8a1714
merge commit for archive created by Sapling
2025-05-07 16:44:46 -07:00
Michael Bolin
d13b807980
feat: support map of alternative providers like in TypeScript CLI
2025-05-07 16:44:31 -07:00
Michael Bolin
cfe50c7107
fix: creating an instance of Codex requires a Config ( #859 )
...
I discovered that I accidentally introduced a change in
https://github.com/openai/codex/pull/829 where we load a fresh `Config`
in the middle of `codex.rs`:
https://github.com/openai/codex/blob/c3e10e180a341e719f61014ea508f6d9dbffe05b/codex-rs/core/src/codex.rs#L515-L522
This is not good because the `Config` could differ from the one that has
the user's overrides specified from the CLI. Also, in unit tests, it
means the `Config` was picking up my personal settings as opposed to
using a vanilla config, which was problematic.
This PR cleans things up by moving the common case where
`Op::ConfigureSession` is derived from `Config` (originally done in
`codex_wrapper.rs`) and making it the standard way to initialize `Codex`
by putting it in `Codex::spawn()`. Note this also eliminates quite a bit
of boilerplate from the tests and relieves the caller of the
responsibility of minting out unique IDs when invoking `submit()`.
2025-05-07 16:33:28 -07:00
Michael Bolin
3a019d4220
merge commit for archive created by Sapling
2025-05-07 16:16:23 -07:00
Michael Bolin
0b42a4aef0
fix: creating an instance of Codex requires a Config
2025-05-07 16:16:17 -07:00
Michael Bolin
c6c05788e2
merge commit for archive created by Sapling
2025-05-07 16:12:14 -07:00
Michael Bolin
6783203c20
fix: creating an instance of Codex requires a Config
2025-05-07 16:11:58 -07:00
Michael Bolin
c3e10e180a
fix: remove CodexBuilder and Recorder ( #858 )
...
These abstractions were originally created exclusively for the REPL,
which was removed in https://github.com/openai/codex/pull/754 .
Currently, the create some unnecessary Tokio tasks, so we are better off
without them. (We can always bring this back if we have a new use case.)
2025-05-07 16:11:42 -07:00
Michael Bolin
1b7b2183e4
Merge 37683450dd into sapling-pr-archive-bolinfest
2025-05-07 15:58:33 -07:00
Michael Bolin
37683450dd
fix: remove CodexBuilder and Recorder
2025-05-07 15:58:26 -07:00
Michael Bolin
a04d707d4a
merge commit for archive created by Sapling
2025-05-07 14:41:03 -07:00
Michael Bolin
e2a5c000a0
feat: support map of alternative providers like in TypeScript CLI
2025-05-07 14:40:50 -07:00
Michael Bolin
42617f8726
feat: save session transcripts when using Rust CLI ( #845 )
...
This adds support for saving transcripts when using the Rust CLI. Like
the TypeScript CLI, it saves the transcript to `~/.codex/sessions`,
though it uses JSONL for the file format (and `.jsonl` for the file
extension) so that even if Codex crashes, what was written to the
`.jsonl` file should generally still be valid JSONL content.
2025-05-07 13:49:15 -07:00
Michael Bolin
ac451d13bf
merge commit for archive created by Sapling
2025-05-07 12:58:09 -07:00
Michael Bolin
5b87df89b4
fix: make McpConnectionManager tolerant of MCPs that fail to start
2025-05-07 12:57:59 -07:00
Michael Bolin
9da6ebef3f
fix: add optional timeout to McpClient::send_request() ( #852 )
...
We now impose a 10s timeout on the initial `tools/list` request to an
MCP server. We do not apply a timeout for other types of requests yet,
but we should start enforcing those, as well.
2025-05-07 12:56:38 -07:00
Michael Bolin
4170c74be5
Merge 8111a04d3e into sapling-pr-archive-bolinfest
2025-05-07 12:55:36 -07:00
Michael Bolin
8111a04d3e
feat: save rollouts in Rust CLI
2025-05-07 12:55:31 -07:00
Michael Bolin
7499042ed3
merge commit for archive created by Sapling
2025-05-07 12:55:01 -07:00
Michael Bolin
5743c170e5
feat: support map of alternative providers like in TypeScript CLI
2025-05-07 12:54:56 -07:00
Michael Bolin
e74f213cc9
Merge ea13757d3f into sapling-pr-archive-bolinfest
2025-05-07 12:52:58 -07:00
Michael Bolin
ea13757d3f
fix: add optional timeout to McpClient::send_request()
2025-05-07 12:52:11 -07:00
Michael Bolin
17c3ebbd12
merge commit for archive created by Sapling
2025-05-07 12:51:15 -07:00
Michael Bolin
8ec2dffc7a
feat: support map of alternative providers like in TypeScript CLI
2025-05-07 12:51:05 -07:00
Michael Bolin
c131d26f07
merge commit for archive created by Sapling
2025-05-07 12:46:13 -07:00
Michael Bolin
be73b208cd
fix: add optional timeout to McpClient::send_request()
2025-05-07 12:46:04 -07:00
Michael Bolin
0360b4d0d7
feat: introduce the use of tui-markdown ( #851 )
...
This introduces the use of the `tui-markdown` crate to parse an
assistant message as Markdown and style it using ANSI for a better user
experience. As shown in the screenshot below, it has support for syntax
highlighting for _tagged_ fenced code blocks:
<img width="907" alt="image"
src="https://github.com/user-attachments/assets/900dc229-80bb-46e8-b1bb-efee4c70ba3c "
/>
That said, `tui-markdown` is not as configurable (or stylish!) as
https://www.npmjs.com/package/marked-terminal , which is what we use in
the TypeScript CLI. In particular:
* The styles are hardcoded and `tui_markdown::from_str()` does not take
any options whatsoever. It uses "bold white" for inline code style which
does not stand out as much as the yellow used by `marked-terminal`:
https://github.com/joshka/tui-markdown/blob/65402cbda70325f34e7ddf6fe1ec629bcd9459cf/tui-markdown/src/lib.rs#L464
I asked Codex to take a first pass at this and it came up with:
https://github.com/joshka/tui-markdown/pull/80
* If a fenced code block is not tagged, then it does not get
highlighted. I would rather add some logic here:
https://github.com/joshka/tui-markdown/blob/65402cbda70325f34e7ddf6fe1ec629bcd9459cf/tui-markdown/src/lib.rs#L262
that uses something like https://pypi.org/project/guesslang/ to examine
the value of `text` and try to use the appropriate syntax highlighter.
* When we have a fenced code block, we do not want to show the opening
and closing triple backticks in the output.
To unblock ourselves, we might want to bundle our own fork of
`tui-markdown` temporarily until we figure out what the shape of the API
should be and then try to upstream it.
2025-05-07 10:46:32 -07:00
Michael Bolin
0e32859c90
merge commit for archive created by Sapling
2025-05-07 10:18:54 -07:00
Michael Bolin
d289a825df
feat: introduce the use of tui_markdown
2025-05-07 10:18:46 -07:00
Michael Bolin
b2177f86dd
Merge b13eaa7c12 into sapling-pr-archive-bolinfest
2025-05-07 10:10:33 -07:00
Michael Bolin
b13eaa7c12
feat: save rollouts in Rust CLI
2025-05-07 10:10:05 -07:00
Michael Bolin
5c6c9839ff
merge commit for archive created by Sapling
2025-05-07 10:09:35 -07:00
Michael Bolin
7235e057fe
feat: introduce the use of tui_markdown
2025-05-07 10:09:00 -07:00
jcoens-openai
a080d7b0fd
Update submodules version to come from the workspace ( #850 )
...
Tie the version of submodules to the workspace version.
2025-05-07 10:08:06 -07:00
Michael Bolin
a044f30f38
Merge bd910aad64 into sapling-pr-archive-bolinfest
2025-05-07 09:55:09 -07:00
Michael Bolin
bd910aad64
feat: introduce the use of tui_markdown
2025-05-07 09:54:56 -07:00
jcoens-openai
8a89d3aeda
Update cargo to 2024 edition ( #842 )
...
Some effects of this change:
- New formatting changes across many files. No functionality changes
should occur from that.
- Calls to `set_env` are considered unsafe, since this only happens in
tests we wrap them in `unsafe` blocks
2025-05-07 08:37:48 -07:00
Michael Bolin
c48246f143
merge commit for archive created by Sapling
2025-05-06 22:53:49 -07:00
Michael Bolin
27b6fd3524
feat: save rollouts in Rust CLI
2025-05-06 22:53:42 -07:00
Michael Bolin
c7ee7b2579
merge commit for archive created by Sapling
2025-05-06 22:48:52 -07:00
Michael Bolin
0f52b17cde
feat: save rollouts in Rust CLI
2025-05-06 22:48:48 -07:00
Michael Bolin
6d99328428
merge commit for archive created by Sapling
2025-05-06 22:46:33 -07:00
Michael Bolin
3f1d34bdd7
feat: save rollouts in Rust CLI
2025-05-06 22:46:26 -07:00
Michael Bolin
96cec49cf5
Merge 0b46df2677 into sapling-pr-archive-bolinfest
2025-05-06 22:04:03 -07:00
Michael Bolin
0b46df2677
feat: save rollouts in Rust CLI
2025-05-06 22:03:57 -07:00
Michael Bolin
e9ddb55fb8
merge commit for archive created by Sapling
2025-05-06 18:57:45 -07:00
Michael Bolin