- Headless runs now switch to device-code login automatically so sign-in works without a browser. (#8756)
- TUI lets you queue messages with Tab during active turns (including /review), shows queue hints, and streams exec output inline for smoother updates. (#9077, #9122, #9138, #9194)
- WebSocket transport reuses connections and supports incremental append requests to reduce streaming overhead. (#9127, #9128)
- Linux sandbox can mount paths read-only to better protect files from writes. (#9112)
- Default API model moved to gpt-5.2-codex. (#9188)
## Bug Fixes
- Alternate-screen handling now avoids breaking Zellij scrollback and adds a config/flag to control it. (#8555)
- Windows correctly prompts before unsafe commands when running with a read-only sandbox policy. (#9117)
- Config.toml and rules parsing errors are reported to app-server clients/TUI instead of failing silently. (#9182, #9011)
- Worked around a macOS system-configuration crash in proxy discovery. (#8954)
- Invalid user image uploads now surface an error instead of being silently replaced. (#9146)
## Documentation
- Published a generated JSON Schema for `config.toml` in `docs/` to validate configs. (#8956)
- Documented the TUI paste-burst state machine for terminals without reliable bracketed paste. (#9020)
## Chores
- Added Bazel build support plus a `just bazel-codex` helper for contributors. (#8875, #9177)
## Changelog
Full Changelog: https://github.com/openai/codex/compare/rust-v0.80.0...rust-v0.81.0
- #8756 [device-auth] When headless environment is detected, show device login flow instead. @mzeng-openai
- #8930 feat: first pass on clb tool @jif-oai
- #8966 nit: rename session metric @jif-oai
- #8969 chore: non mutable btree when building specs @jif-oai
- #8968 chore: move otel provider outside of trace module @jif-oai
- #8973 chore: add mcp call metric @jif-oai
- #8970 chore: add approval metric @jif-oai
- #8975 chore: metrics tool call @jif-oai
- #8901 chore: update metrics temporality @jif-oai
- #8954 Work around crash in system-configuration library @etraut-openai
- #8873 fix(app-server): set originator header from initialize JSON-RPC request @owenlin0
- #8909 Add config to disable /feedback @gt-oai
- #8985 chore: nuke telemetry file @jif-oai
- #8986 Revert "fix(app-server): set originator header from initialize JSON-RPC request" @jif-oai
- #8978 nit: rename to analytics_enabled @jif-oai
- #8963 renaming: task to turn @jif-oai
- #8555 fix: add tui.alternate_screen config and --no-alt-screen CLI flag for Zellij scrollback @hjanuschka
- #8875 feat: add support for building with Bazel @zbarsky-openai
- #8988 fix(app-server): set originator header from initialize (re-revert) @owenlin0
- #8766 fix: harden arg0 helper PATH handling @viyatb-oai
- #8949 Log unhandled sse events @pakrym-oai
- #8996 Add hierarchical agent prompt @pakrym-oai
- #9003 Delete announcement_tip.toml @pakrym-oai
- #8940 Refactor remote models tests to use TestCodex builder @aibrahim-oai
- #8981 Add model provider info to /status if non-default @gt-oai
- #8984 Add URL to responses error messages @gt-oai
- #9008 fix: add .git to .bazelignore @bolinfest
- #9010 fix: include AGENTS.md as repo root marker for integration tests @bolinfest
- #8950 Label attached images so agent can understand in-message labels @charley-oai
- #9032 Revert "Delete announcement_tip.toml" @jif-oai
- #9018 fix: support remote arm64 builds, as well @zbarsky-openai
- #8983 feat: testing harness for collab 1 @jif-oai
- #9088 feat: add wait tool implementation for collab @jif-oai
- #9090 feat: add close tool implementation for collab @jif-oai
- #8971 add static mcp callback uri support @WhammyLeaf
- #9099 nit: add docstring @jif-oai
- #8994 feat: wire fork to codex cli @apanasenko-oai
- #9071 chore(deps): bump tui-scrollbar from 0.2.1 to 0.2.2 in /codex-rs @dependabot
- #9072 chore(deps): bump ts-rs from 11.0.1 to 11.1.0 in /codex-rs @dependabot
- #9074 chore(deps): bump which from 6.0.3 to 8.0.0 in /codex-rs @dependabot
- #9075 chore(deps): bump clap from 4.5.53 to 4.5.54 in /codex-rs @dependabot
- #9076 chore(deps): bump tokio-util from 0.7.16 to 0.7.18 in /codex-rs @dependabot
- #8957 feat: hot reload mcp servers @shijie-oai
- #9107 Remove unused conversation_id header @pakrym-oai
- #9080 Add some tests for image attachments @charley-oai
- #9114 Extract single responses SSE event parsing @pakrym-oai
- #8961 Assemble sandbox/approval/network prompts dynamically @aibrahim-oai
- #9102 Add model client sessions @pakrym-oai
- #8246 fix(tui): show in-flight coalesced tool calls in transcript overlay @Chriss4123
- #9127 Reuse websocket connection @pakrym-oai
- #9117 fix: prompt for unsafe commands on Windows @bolinfest
- #9128 Websocket append support @pakrym-oai
- #9077 Send message by default mid turn. queue messages by tab @aibrahim-oai
- #9049 Handle image paste from empty paste events @aibrahim-oai
- #8952 Use markdown for migration screen @aibrahim-oai
- #9109 Updated heuristic for tool call summary to detect file modifications @etraut-openai
- #9138 Show tab queue hint in footer @aibrahim-oai
- #9140 Use thread rollback for Esc backtrack @aibrahim-oai
- #9143 chore: better error handling on collab tools @jif-oai
- #9147 nit: collab send input cleaning @jif-oai
- #9129 Support response.done and add integration tests @pakrym-oai
- #8798 ollama: default to Responses API for built-ins @drifkin
- #8956 add generated jsonschema for config.toml @sayan-oai
- #9122 Fix queued messages during /review @charley-oai
- #9126 fix: drop session span at end of the session @apanasenko-oai
- #9101 Restrict MCP servers from `requirements.toml` @gt-oai
- #9020 fix(tui): document paste-burst state machine @joshka-oai
- #9118 feat(app-server): add an --analytics-default-enabled flag @owenlin0
- #9130 Fresh tooltips @mzeng-openai
- #9134 fix(windows-sandbox-rs) bump SETUP_VERSION @dylan-hurd-oai
- #9121 test(tui): add deterministic paste-burst tests @joshka-oai
- #8661 Fix spinner/Esc interrupt when MCP startup completes mid-turn @2mawi2
- #9165 Allow close skill popup with esc. @xl-openai
- #9169 Fix flakiness in WebSocket tests @pakrym-oai
- #9011 fix: report an appropriate error in the TUI for malformed rules @bolinfest
- #9166 fix: integration test for #9011 @bolinfest
- #9177 feat: add bazel-codex entry to justfile @bolinfest
- #9175 WebSocket test server script @pakrym-oai
- #9136 Update models.json @github-actions
- #9168 clean models manager @aibrahim-oai
- #8933 [CODEX-4427] improve parsed commands @aibrahim-oai
- #9174 Renew cache ttl on etag match @aibrahim-oai
- #9124 fix(tui): harden paste-burst state transitions @joshka-oai
- #9186 Use offline cache for tui migrations @aibrahim-oai
- #9182 Improve handling of config and rules errors for app server clients @etraut-openai
- #8997 chore: clarify default shell for unified_exec @sayan-oai
- #9192 feat: add threadId to MCP server messages @bolinfest
- #9188 change api default model @aibrahim-oai
- #9150 feat: add sourcing of rc files to shell snapshot @jif-oai
- #9155 fix: shell snapshot clean-up @jif-oai
- #9146 feat: return an error if the image sent by the user is a bad image @jif-oai
- #9197 feat: only source shell snapshot if the file exists @jif-oai
- #9145 fix: drop double waiting header in TUI @jif-oai
- #9194 Render exec output deltas inline @aibrahim-oai
- #9156 chore: clamp min yield time for empty write_stdin @jif-oai
- #9105 feat: add auto refresh on thread listeners @jif-oai
- #9112 feat: add support for read-only bind mounts in the linux sandbox @viyatb-oai
- #9179 Use current model for review @pakrym-oai
Instead of having a hard-coded default review model, use the current
model for running `/review` unless one is specified in the config.
Also inherit current reasoning effort
### Motivation
- Landlock alone cannot prevent writes to sensitive in-repo files like
`.git/` when the repo root is writable, so explicit mount restrictions
are required for those paths.
- The sandbox must set up any mounts before calling Landlock so Landlock
can still be applied afterwards and the two mechanisms compose
correctly.
### Description
- Add a new `linux-sandbox` helper `apply_read_only_mounts` in
`linux-sandbox/src/mounts.rs` that: unshares namespaces, maps uids/gids
when required, makes mounts private, bind-mounts targets, and remounts
them read-only.
- Wire the mount step into the sandbox flow by calling
`apply_read_only_mounts(...)` before network/seccomp and before applying
Landlock rules in `linux-sandbox/src/landlock.rs`.
This PR is in the scope of multi-agent work.
An agent (=thread) can now spawn other agents. Those other agents are
not attached to any clients. We need a way to make sure that the clients
are aware of the new threads to look at (for approval for example). This
PR adds a channel to the `ThreadManager` that pushes the ID of those
newly created agents such that the client (here the app-server) can also
subscribe to those ones.
## Before
When we detect an `InvalidImageRequest`, we replace the image by a
placeholder and keep going
## Now
In such `InvalidImageRequest`, we check if the image is due to a user
message or a tool call output. For tool call output we still replace it
with a placeholder to avoid breaking the agentic loop bu tif this is
because of a user message, we send an error to the user
Clean all shell snapshot files corresponding to sessions that have not
been updated in 7 days
Those files should never leak. The only known cases were it can leak are
during non graceful interrupt of the process (`kill -9, `panic`, OS
crash, ...)
The description of the `shell` arg for `exec_command` states the default
is `/bin/bash`, but AFAICT it's the user's default shell.
Default logic
[here](2a06d64bc9/codex-rs/core/src/tools/handlers/unified_exec.rs (L123)).
EDIT: #9004 has an alternative where we inform the model of the default
shell itself.
When an invalid config.toml key or value is detected, the CLI currently
just quits. This leaves the VSCE in a dead state.
This PR changes the behavior to not quit and bubble up the config error
to users to make it actionable. It also surfaces errors related to
"rules" parsing.
This allows us to surface these errors to users in the VSCE, like this:
<img width="342" height="129" alt="Screenshot 2026-01-13 at 4 29 22 PM"
src="https://github.com/user-attachments/assets/a79ffbe7-7604-400c-a304-c5165b6eebc4"
/>
<img width="346" height="244" alt="Screenshot 2026-01-13 at 4 45 06 PM"
src="https://github.com/user-attachments/assets/de874f7c-16a2-4a95-8c6d-15f10482e67b"
/>
User-facing symptom: On terminals that deliver pastes as rapid
KeyCode::Char/Enter streams (notably Windows), paste-burst transient
state
can leak into the next input. Users can see Enter insert a newline when
they meant to submit, or see characters appear late / handled through
the
wrong path.
System problem: PasteBurst is time-based. Clearing only the
classification window (e.g. via clear_window_after_non_char()) can erase
last_plain_char_time without emitting buffered text. If a buffer is
still
non-empty after that, flush_if_due() no longer has a timeout clock to
flush against, so the buffer can get "stuck" until another plain char
arrives.
This was surfaced while adding deterministic regression tests for
paste-burst behavior.
Fix: when disabling burst detection, defuse any in-flight burst state:
flush held/buffered text through handle_paste() (so it follows normal
paste integration), then clear timing and Enter suppression.
Document the rationale inline and update docs/tui-chat-composer.md so
"disable_paste_burst" matches the actual behavior.
**make command summaries more accurate by distinguishing
list/search/read operations across common CLI tools.**
- Added parsing helpers to centralize operand/flag handling (cd_target,
sed_read_path, first_non_flag_operand, single_non_flag_operand,
parse_grep_like, awk_data_file_operand, python_walks_files,
is_python_command) and reused them in summarize_main_tokens/shell
parsing.
- Newly parsed list-files commands: git ls-files, rg --files (incl.
rga/ripgrep-all), eza/exa, tree, du, python -c file-walks, plus fd/find
map to ListFiles when no query.
- Newly parsed search commands: git grep, grep/egrep/fgrep, ag/ack/pt,
rg/rga files-with-matches flags (-l/-L, --files-with-matches,
--files-without-match), with improved flag skipping to avoid
misclassifying args as paths.
- Newly parsed read commands: bat/batcat, less, more, awk <file>, and
more flexible sed -n range + file detection.
- refine “small formatting command” detection for awk/sed, handle cd
with -- or multiple operands, keep pipeline summaries focused on primary
command.
Have only the following Methods:
- `list_models`: getting current available models
- `try_list_models`: sync version no refresh for tui use
- `get_default_model`: get the default model (should be tightened to
core and received on session configuration)
- `get_model_info`: get `ModelInfo` for a specific model (should be
tightened to core but used in tests)
- `refresh_if_new_etag`: trigger refresh on different etags
Also move the cache to its own struct
This is less straightforward than I realized, so created an entry for
this in our `justfile`.
Verified that running `just bazel-codex` from anywhere in the repo uses
the user's `$PWD` as the one to run Codex.
While here, updated the `MODULE.bazel.lock`, though it looks like I need
to add a CI job that runs `bazel mod deps --lockfile_mode=error` or
something.
Adds an integration test for the new behavior introduced in
https://github.com/openai/codex/pull/9011. The work to create the test
setup was substantial enough that I thought it merited a separate PR.
This integration test spawns `codex` in TUI mode, which requires
spawning a PTY to run successfully, so I had to introduce quite a bit of
scaffolding in `run_codex_cli()`. I was surprised to discover that we
have not done this in our codebase before, so perhaps this should get
moved to a common location so it can be reused.
The test itself verifies that a malformed `rules` in `$CODEX_HOME`
prints a human-readable error message and exits nonzero.
The underlying issue is that when we encountered an error starting a
conversation (any sort of error, though making `$CODEX_HOME/rules` a
file rather than folder was the example in #8803), then we were writing
the message to stderr, but this could be printed over by our UI
framework so the user would not see it. In general, we disallow the use
of `eprintln!()` in this part of the code for exactly this reason,
though this was suppressed by an `#[allow(clippy::print_stderr)]`.
This attempts to clean things up by changing `handle_event()` and
`handle_tui_event()` to return a `Result<AppRunControl>` instead of a
`Result<bool>`, which is a new type introduced in this PR (and depends
on `ExitReason`, also a new type):
```rust
#[derive(Debug)]
pub(crate) enum AppRunControl {
Continue,
Exit(ExitReason),
}
#[derive(Debug, Clone)]
pub enum ExitReason {
UserRequested,
Fatal(String),
}
```
This makes it possible to exit the primary control flow of the TUI with
richer information. This PR adds `ExitReason` to the existing
`AppExitInfo` struct and updates `handle_app_exit()` to print the error
and exit code `1` in the event of `ExitReason::Fatal`.
I tried to create an integration test for this, but it was a bit
involved, so I published it as a separate PR:
https://github.com/openai/codex/pull/9166. For this PR, please have
faith in my manual testing!
Fixes https://github.com/openai/codex/issues/8803.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/9011).
* #9166
* __->__ #9011
The connection was being added to the list after the WebSocket response
was sent.
So the test can sometimes race and observe connections before the list
was updated.
After this change, connection and request is added to the list before
the response is sent.
## **Problem**
Codex’s TUI uses a single “task running” indicator (spinner + Esc interrupt hint)
to communicate “the UI is busy”. In practice, “busy” can mean two different
things: an agent turn is running, or MCP servers are still starting up. Without a
clear contract, those lifecycles can interfere: startup completion can clear the
spinner while a turn is still in progress, or the UI can appear idle while MCP is
still booting. This is user-visible confusion during the most important moments
(startup and the first turn), so it was worth making the contract explicit and
guarding it.
## **Mental model**
`ChatWidget` is the UI-side adapter for the `codex_core::protocol` event stream.
It receives `EventMsg` events and updates two major UI surfaces: the transcript
(history/streaming cells) and the bottom pane (composer + status indicator).
The key concept after this change is that the bottom pane’s “task running”
indicator is treated as **derived UI-busy state**, not “agent is running”. It is
considered active while either:
- an agent turn is in progress (`TurnStarted` → completion/abort), or
- MCP startup is in progress (`McpStartupUpdate` → `McpStartupComplete`).
Those lifecycles are tracked independently, and the bottom-pane indicator is
defined as their union.
## **Non-goals**
- This does not introduce separate UI indicators for “turn busy” vs “MCP busy”.
- This does not change MCP startup behavior, ordering guarantees, or core
protocol semantics.
- This does not rework unrelated status/header rendering or transcript layout.
## **Tradeoffs**
- The “one flag represents multiple lifecycles” approach remains lossy: it
preserves correct “busy vs idle” semantics but cannot express *which* kind of
busy is happening without further UI changes.
- The design keeps complexity low by keeping a single derived boolean, rather
than adding a more expressive bottom-pane state machine. That’s chosen because
it matches existing UX and minimizes churn while fixing the confusion.
## **Architecture**
- `codex-core` owns the actual lifecycles and emits `codex_core::protocol`
events.
- `ChatWidget` owns the UI interpretation of those lifecycles. It is responsible
for keeping the bottom pane’s derived “busy” state consistent with the event
stream, and for updating the status header when MCP progress updates arrive.
- The bottom pane remains a dumb renderer of the single “task running” flag; it
does not learn about MCP or agent turns directly.
## **Observability**
- When working: the spinner/Esc hint stays visible during MCP startup and does
not disappear mid-turn when `McpStartupComplete` arrives; startup status
headers can update without clearing “busy” for an active turn.
- When broken: you’ll see the spinner/hint flicker off while output is still
streaming, or the UI appears idle while MCP startup status is still changing.
## **Tests**
- Adds/strengthens a regression test that asserts MCP startup completion does
not clear the “task running” indicator for an active turn (in both `tui` and
`tui2` variants).
- These tests prove the **contract** (“busy is the union of turn + startup”) at
the UI boundary; they do not attempt to validate MCP startup ordering,
real-world startup timing, or backend integration behavior.
Fixes#7017
Signed-off-by: 2mawi2 <2mawi2@users.noreply.github.com>
Co-authored-by: 2mawi2 <2mawi2@users.noreply.github.com>
Co-authored-by: Josh McKinney <joshka@openai.com>
Replace the old timing-dependent non-ASCII paste test with deterministic
coverage by forcing an active `PasteBurst` and asserting the exact flush
payload.
Add focused unit tests for `PasteBurst` transitions, and add short
"Behavior:" rustdoc notes on chat composer tests to make the state
machine contracts explicit.
## Summary
Bumps the windows setup version, to re-trigger windows sandbox setup for
users in the experimental sandbox. We've seen some drift in the ACL
controls, amongst a few other changes. Hopefully this should fix#9062.
## Testing
- [x] Tested locally
Add a new `codex app-server --analytics-default-enabled` CLI flag that
controls whether analytics are enabled by default.
Analytics are disabled by default for app-server. Users have to
explicitly opt in
via the `analytics` section in the config.toml file.
However, for first-party use cases like the VSCode IDE extension, we
default analytics
to be enabled by default by setting this flag. Users can still opt out
by setting this
in their config.toml:
```toml
[analytics]
enabled = false
```
See https://developers.openai.com/codex/config-advanced/#metrics for
more details.
Add a narrative doc and inline rustdoc explaining how `ChatComposer`
and `PasteBurst` compose into a single state machine on terminals that
lack reliable bracketed paste (notably Windows).
This documents the key states, invariants, and integration points
(`handle_input_basic`, `handle_non_ascii_char`, tick-driven flush) so
future changes are easier to reason about.
Enterprises want to restrict the MCP servers their users can use.
Admins can now specify an allowlist of MCPs in `requirements.toml`. The
MCP servers are matched on both Name and Transport (local path or HTTP
URL) -- both must match to allow the MCP server. This prevents
circumventing the allowlist by renaming MCP servers in user config. (It
is still possible to replace the local path e.g. rewrite say
`/usr/local/github-mcp` with a nefarious MCP. We could allow hash
pinning in the future, but that would break updates. I also think this
represents a broader, out-of-scope problem.)
We introduce a new field to Constrained: "normalizer". In general, it is
a fn(T) -> T and applies when `Constrained<T>.set()` is called. In this
particular case, it disables MCP servers which do not match the
allowlist. An alternative solution would remove this and instead throw a
ConstraintError. That would stop Codex launching if any MCP server was
configured which didn't match. I think this is bad.
We currently reuse the enabled flag on MCP servers to disable them, but
don't propagate any information about why they are disabled. I'd like to
add that in a follow up PR, possibly by switching out enabled with an
enum.
In action:
```
# MCP server config has two MCPs. We are going to allowlist one of them.
➜ codex git:(gt/restrict-mcps) ✗ cat ~/.codex/config.toml | grep mcp_servers -A1
[mcp_servers.hello_world]
command = "hello-world-mcp"
--
[mcp_servers.docs]
command = "docs-mcp"
# Restrict the MCPs to the hello_world MCP.
➜ codex git:(gt/restrict-mcps) ✗ defaults read com.openai.codex requirements_toml_base64 | base64 -d
[mcp_server_allowlist.hello_world]
command = "hello-world-mcp"
# List the MCPs, observe hello_world is enabled and docs is disabled.
➜ codex git:(gt/restrict-mcps) ✗ just codex mcp list
cargo run --bin codex -- "$@"
Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.25s
Running `target/debug/codex mcp list`
Name Command Args Env Cwd Status Auth
docs docs-mcp - - - disabled Unsupported
hello_world hello-world-mcp - - - enabled Unsupported
# Remove the restrictions.
➜ codex git:(gt/restrict-mcps) ✗ defaults delete com.openai.codex requirements_toml_base64
# Observe both MCPs are enabled.
➜ codex git:(gt/restrict-mcps) ✗ just codex mcp list
cargo run --bin codex -- "$@"
Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.25s
Running `target/debug/codex mcp list`
Name Command Args Env Cwd Status Auth
docs docs-mcp - - - enabled Unsupported
hello_world hello-world-mcp - - - enabled Unsupported
# A new requirements that updates the command to one that does not match.
➜ codex git:(gt/restrict-mcps) ✗ cat ~/requirements.toml
[mcp_server_allowlist.hello_world]
command = "hello-world-mcp-v2"
# Use those requirements.
➜ codex git:(gt/restrict-mcps) ✗ defaults write com.openai.codex requirements_toml_base64 "$(base64 -i /Users/gt/requirements.toml)"
# Observe both MCPs are disabled.
➜ codex git:(gt/restrict-mcps) ✗ just codex mcp list
cargo run --bin codex -- "$@"
Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.75s
Running `target/debug/codex mcp list`
Name Command Args Env Cwd Status Auth
docs docs-mcp - - - disabled Unsupported
hello_world hello-world-mcp - - - disabled Unsupported
```
Sending a message during /review interrupts the review, whereas during
normal operation, sending a message while the agent is running will
queue the message. This is unexpected behavior, and since /review
usually takes a while, it takes away a potentially useful operation.
Summary
- Treat review mode as an active task for message queuing so inputs
don’t inject into the running review turn.
- Prevents user submissions from rendering immediately in the transcript
while the review continues streaming.
- Keeps review UX consistent with normal “task running” behavior and
avoids accidental interrupt/replacement.
Notes
- This change only affects UI queuing logic; core review flow and task
lifecycle remain unchanged.
### What
Add JSON Schema generation for `config.toml`, with checked‑in
`docs/config.schema.json`. We can move the schema elsewhere if preferred
(and host it if there's demand).
Add fixture test to prevent drift and `just write-config-schema` to
regenerate on schema changes.
Generate MCP config schema from `RawMcpServerConfig` instead of
`McpServerConfig` because that is the runtime type used for
deserialization.
Populate feature flag values into generated schema so they can be
autocompleted.
### Tests
Added tests + regenerate script to prevent drift. Tested autocompletions
using generated jsonschema locally with Even Better TOML.
https://github.com/user-attachments/assets/5aa7cd39-520c-4a63-96fb-63798183d0bc
This is an alternate PR to solving the same problem as
<https://github.com/openai/codex/pull/8227>.
In this PR, when Ollama is used via `--oss` (or via `model_provider =
"ollama"`), we default it to use the Responses format. At runtime, we do
an Ollama version check, and if the version is older than when Responses
support was added to Ollama, we print out a warning.
Because there's no way of configuring the wire api for a built-in
provider, we temporarily add a new `oss_provider`/`model_provider`
called `"ollama-chat"` that will force the chat format.
Once the `"chat"` format is fully removed (see
<https://github.com/openai/codex/discussions/7782>), `ollama-chat` can
be removed as well
---------
Co-authored-by: Eric Traut <etraut@openai.com>
Co-authored-by: Michael Bolin <mbolin@openai.com>
Handle image paste on empty paste events.
- Intent: make image paste work in terminals that emit empty paste
events.
- Approach: route paste events through an image-aware handler and read
the clipboard when text is empty.
- That's best effort to detect it. Some terminals don't send the empty
signal.
