171 Commits

• Trim double Total output lines (#4787)
  pakrym-oai · 2025-10-05 16:41:55 -07:00
  a90a58f7a1
• Make output assertions more explicit (#4784)

  Match using precise regexes.

  pakrym-oai · 2025-10-05 16:01:38 -07:00
  b2d81a7cac
• Use response helpers when mounting SSE test responses (#4783)

  ## Summary
  - replace manual wiremock SSE mounts in the compact suite with the
  shared response helpers
  - simplify the exec auth_env integration test by using the
  mount_sse_once_match helper
  - rely on mount_sse_sequence plus server request collection to replace
  the bespoke SeqResponder utility in tests
  
  ## Testing
  - just fmt
  
  ------
  https://chatgpt.com/codex/tasks/task_i_68e2e238f2a88320a337f0b9e4098093

  pakrym-oai · 2025-10-05 21:58:16 +00:00
  191d620707
• Use assert_matches (#4756)

  assert_matches is soon to be in std but is experimental for now.

  pakrym-oai · 2025-10-05 21:12:31 +00:00
  5c42419b02
• Add helper for response created SSE events in tests (#4758)

  ## Summary
  - add a reusable `ev_response_created` helper that builds
  `response.created` SSE events for integration tests
  - update the exec and core integration suites to use the new helper
  instead of repeating manual JSON literals
  - keep the streaming fixtures consistent by relying on the shared helper
  in every touched test
  
  ## Testing
  - `just fmt`
  
  
  ------
  https://chatgpt.com/codex/tasks/task_i_68e1fe885bb883208aafffb94218da61

  pakrym-oai · 2025-10-05 21:11:43 +00:00
  aecbe0f333
• feat: parallel tool calls (#4663)

  Add parallel tool calls. This is configurable at model level and tool
  level

  jif-oai · 2025-10-05 16:10:49 +00:00
  dc3c6bf62a
• chore: update tool config (#4755)

  ## Summary
  Updates tool config for gpt-5-codex
  
  ## Test Plan
  - [x] Ran locally
  - [x]  Updated unit tests

  Dylan · 2025-10-04 22:47:26 -07:00
  3203862167
• Use wait_for_event helpers in tests (#4753)

  ## Summary
  - replace manual event polling loops in several core test suites with
  the shared wait_for_event helpers
  - keep prior assertions intact by using closure captures for stateful
  expectations, including plan updates, patch lifecycles, and review flow
  checks
  - rely on wait_for_event_with_timeout where longer waits are required,
  simplifying timeout handling
  
  ## Testing
  - just fmt
  
  
  ------
  https://chatgpt.com/codex/tasks/task_i_68e1d58582d483208febadc5f90dd95e

  pakrym-oai · 2025-10-04 22:04:05 -07:00
  06853d94f0
• Add truncation hint on truncated exec output. (#4740)

  When truncating output, add a hint of the total number of lines

  Ahmed Ibrahim · 2025-10-05 03:29:07 +00:00
  cc2f4aafd7
• feat: Freeform apply_patch with simple shell output (#4718)

  ## Summary
  This PR is an alternative approach to #4711, but instead of changing our
  storage, parses out shell calls in the client and reserializes them on
  the fly before we send them out as part of the request.
  
  What this changes:
  1. Adds additional serialization logic when the
  ApplyPatchToolType::Freeform is in use.
  2. Adds a --custom-apply-patch flag to enable this setting on a
  session-by-session basis.
  
  This change is delicate, but is not meant to be permanent. It is meant
  to be the first step in a migration:
  1. (This PR) Add in-flight serialization with config
  2. Update model_family default
  3. Update serialization logic to store turn outputs in a structured
  format, with logic to serialize based on model_family setting.
  4. Remove this rewrite in-flight logic.
  
  ## Test Plan
  - [x] Additional unit tests added
  - [x] Integration tests added
  - [x] Tested locally

  Dylan · 2025-10-04 19:16:36 -07:00
  4764fc1ee7
• Surface context window error to the client (#4675)

  In the past, we were treating `input exceeded context window` as a
  streaming error and retrying on it. Retrying on it has no point because
  it won't change the behavior. In this PR, we surface the error to the
  client without retry and also send a token count event to indicate that
  the context window is full.
  
  <img width="650" height="125" alt="image"
  src="https://github.com/user-attachments/assets/c26b1213-4c27-4bfc-90f4-51a270a3efd5"
  />

  Ahmed Ibrahim · 2025-10-05 01:40:06 +00:00
  90ef94d3b3
• fix: exec commands that blows up context window. (#4706)

  We truncate the output of exec commands to not blow the context window.
  However, some cases we weren't doing that. This caused reports of people
  with 76% context window left facing `input exceeded context window`
  which is weird.

  Ahmed Ibrahim · 2025-10-04 11:49:56 -07:00
  d7acd146fb
• set gpt-5 as default model for Windows users (#4676)

  Codex isn’t great yet on Windows outside of WSL, and while we’ve merged
  https://github.com/openai/codex/pull/4269 to reduce the repetitive
  manual approvals on readonly commands, we’ve noticed that users seem to
  have more issues with GPT-5-Codex than with GPT-5 on Windows.
  
  This change makes GPT-5 the default for Windows users while we continue
  to improve the CLI harness and model for GPT-5-Codex on Windows.

  iceweasel-oai · 2025-10-03 14:00:03 -07:00
  de8d77274a
• [MCP] Add support for MCP Oauth credentials (#4517)

  This PR adds oauth login support to streamable http servers when
  `experimental_use_rmcp_client` is enabled.
  
  This PR is large but represents the minimal amount of work required for
  this to work. To keep this PR smaller, login can only be done with
  `codex mcp login` and `codex mcp logout` but it doesn't appear in `/mcp`
  or `codex mcp list` yet. Fingers crossed that this is the last large MCP
  PR and that subsequent PRs can be smaller.
  
  Under the hood, credentials are stored using platform credential
  managers using the [keyring crate](https://crates.io/crates/keyring).
  When the keyring isn't available, it falls back to storing credentials
  in `CODEX_HOME/.credentials.json` which is consistent with how other
  coding agents handle authentication.
  
  I tested this on macOS, Windows, WSL (ubuntu), and Linux. I wasn't able
  to test the dbus store on linux but did verify that the fallback works.
  
  One quirk is that if you have credentials, during development, every
  build will have its own ad-hoc binary so the keyring won't recognize the
  reader as being the same as the write so it may ask for the user's
  password. I may add an override to disable this or allow
  users/enterprises to opt-out of the keyring storage if it causes issues.
  
  <img width="5064" height="686" alt="CleanShot 2025-09-30 at 19 31 40"
  src="https://github.com/user-attachments/assets/9573f9b4-07f1-4160-83b8-2920db287e2d"
  />
  <img width="745" height="486" alt="image"
  src="https://github.com/user-attachments/assets/9562649b-ea5f-4f22-ace2-d0cb438b143e"
  />

  Gabriel Peal · 2025-10-03 13:43:12 -04:00
  1d17ca1fa3
• Fix flaky test (#4672)

  This issue was due to the fact that the timeout is not always sufficient
  to have enough character for truncation + a race between synthetic
  timeout and process kill

  jif-oai · 2025-10-03 18:09:41 +01:00
  bfe3328129
• feat: add beta_supported_tools (#4669)

  Gate the new read_file tool behind a new `beta_supported_tools` flag and
  only enable it for `gpt-5-codex`

  jif-oai · 2025-10-03 16:58:03 +00:00
  e0b38bd7a2
• chore: refactor tool handling (#4510)

  # Tool System Refactor
  
  - Centralizes tool definitions and execution in `core/src/tools/*`:
  specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
  registry/dispatch (`registry.rs`), and shared context (`context.rs`).
  One registry now builds the model-visible tool list and binds handlers.
  - Router converts model responses to tool calls; Registry dispatches
  with consistent telemetry via `codex-rs/otel` and unified error
  handling. Function, Local Shell, MCP, and experimental `unified_exec`
  all flow through this path; legacy shell aliases still work.
  - Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
  make adding tools predictable and testable.
  
  Example: `read_file`
  - Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
  registered by `build_specs`).
  - Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
  1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
  - E2E test: `core/tests/suite/read_file.rs` validates the tool returns
  the requested lines.
  
  ## Next steps:
  - Decompose `handle_container_exec_with_params` 
  - Add parallel tool calls

  jif-oai · 2025-10-03 13:21:06 +01:00
  33d3ecbccc
• chore: sandbox refactor 2 (#4653)

  Revert the revert and fix the UI issue

  jif-oai · 2025-10-03 11:17:39 +01:00
  69cb72f842
• Revert "chore: sanbox extraction" (#4626)

  Reverts openai/codex#4286

  Ahmed Ibrahim · 2025-10-02 21:09:21 +00:00
  ed5d656fa8
• Separate interactive and non-interactive sessions (#4612)

  Do not show exec session in VSCode/TUI selector.

  pakrym-oai · 2025-10-02 13:06:21 -07:00
  4c566d484a
• Support CODEX_API_KEY for codex exec (#4615)

  Allows to set API key per invocation of `codex exec`

  pakrym-oai · 2025-10-02 09:59:45 -07:00
  2f6fb37d72
• chore: sanbox extraction (#4286)

  # Extract and Centralize Sandboxing
  - Goal: Improve safety and clarity by centralizing sandbox planning and
  execution.
    - Approach:
  - Add planner (ExecPlan) and backend registry (Direct/Seatbelt/Linux)
  with run_with_plan.
  - Refactor codex.rs to plan-then-execute; handle failures/escalation via
  the plan.
  - Delegate apply_patch to the codex binary and run it with an empty env
  for determinism.

  jif-oai · 2025-10-01 12:05:12 +01:00
  b8195a17e5
• fix: remove mcp-types from app server protocol (#4537)

  We continue the separation between `codex app-server` and `codex
  mcp-server`.
  
  In particular, we introduce a new crate, `codex-app-server-protocol`,
  and migrate `codex-rs/protocol/src/mcp_protocol.rs` into it, renaming it
  `codex-rs/app-server-protocol/src/protocol.rs`.
  
  Because `ConversationId` was defined in `mcp_protocol.rs`, we move it
  into its own file, `codex-rs/protocol/src/conversation_id.rs`, and
  because it is referenced in a ton of places, we have to touch a lot of
  files as part of this PR.
  
  We also decide to get away from proper JSON-RPC 2.0 semantics, so we
  also introduce `codex-rs/app-server-protocol/src/jsonrpc_lite.rs`, which
  is basically the same `JSONRPCMessage` type defined in `mcp-types`
  except with all of the `"jsonrpc": "2.0"` removed.
  
  Getting rid of `"jsonrpc": "2.0"` makes our serialization logic
  considerably simpler, as we can lean heavier on serde to serialize
  directly into the wire format that we use now.

  Michael Bolin · 2025-10-01 02:16:26 +00:00
  5881c0d6d4
• OpenTelemetry events (#2103)

  ### Title
  
  ## otel
  
  Codex can emit [OpenTelemetry](https://opentelemetry.io/) **log events**
  that
  describe each run: outbound API requests, streamed responses, user
  input,
  tool-approval decisions, and the result of every tool invocation. Export
  is
  **disabled by default** so local runs remain self-contained. Opt in by
  adding an
  `[otel]` table and choosing an exporter.
  
  ```toml
  [otel]
  environment = "staging"   # defaults to "dev"
  exporter = "none"          # defaults to "none"; set to otlp-http or otlp-grpc to send events
  log_user_prompt = false    # defaults to false; redact prompt text unless explicitly enabled
  ```
  
  Codex tags every exported event with `service.name = "codex-cli"`, the
  CLI
  version, and an `env` attribute so downstream collectors can distinguish
  dev/staging/prod traffic. Only telemetry produced inside the
  `codex_otel`
  crate—the events listed below—is forwarded to the exporter.
  
  ### Event catalog
  
  Every event shares a common set of metadata fields: `event.timestamp`,
  `conversation.id`, `app.version`, `auth_mode` (when available),
  `user.account_id` (when available), `terminal.type`, `model`, and
  `slug`.
  
  With OTEL enabled Codex emits the following event types (in addition to
  the
  metadata above):
  
  - `codex.api_request`
    - `cf_ray` (optional)
    - `attempt`
    - `duration_ms`
    - `http.response.status_code` (optional)
    - `error.message` (failures)
  - `codex.sse_event`
    - `event.kind`
    - `duration_ms`
    - `error.message` (failures)
    - `input_token_count` (completion only)
    - `output_token_count` (completion only)
    - `cached_token_count` (completion only, optional)
    - `reasoning_token_count` (completion only, optional)
    - `tool_token_count` (completion only)
  - `codex.user_prompt`
    - `prompt_length`
    - `prompt` (redacted unless `log_user_prompt = true`)
  - `codex.tool_decision`
    - `tool_name`
    - `call_id`
  - `decision` (`approved`, `approved_for_session`, `denied`, or `abort`)
    - `source` (`config` or `user`)
  - `codex.tool_result`
    - `tool_name`
    - `call_id`
    - `arguments`
    - `duration_ms` (execution time for the tool)
    - `success` (`"true"` or `"false"`)
    - `output`
  
  ### Choosing an exporter
  
  Set `otel.exporter` to control where events go:
  
  - `none` – leaves instrumentation active but skips exporting. This is
  the
    default.
  - `otlp-http` – posts OTLP log records to an OTLP/HTTP collector.
  Specify the
    endpoint, protocol, and headers your collector expects:
  
    ```toml
    [otel]
    exporter = { otlp-http = {
      endpoint = "https://otel.example.com/v1/logs",
      protocol = "binary",
      headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }
    }}
    ```
  
  - `otlp-grpc` – streams OTLP log records over gRPC. Provide the endpoint
  and any
    metadata headers:
  
    ```toml
    [otel]
    exporter = { otlp-grpc = {
      endpoint = "https://otel.example.com:4317",
      headers = { "x-otlp-meta" = "abc123" }
    }}
    ```
  
  If the exporter is `none` nothing is written anywhere; otherwise you
  must run or point to your
  own collector. All exporters run on a background batch worker that is
  flushed on
  shutdown.
  
  If you build Codex from source the OTEL crate is still behind an `otel`
  feature
  flag; the official prebuilt binaries ship with the feature enabled. When
  the
  feature is disabled the telemetry hooks become no-ops so the CLI
  continues to
  function without the extra dependencies.
  
  ---------
  
  Co-authored-by: Anton Panasenko <apanasenko@openai.com>

  vishnu-oai · 2025-09-29 11:30:55 -07:00
  04c1782e52
• [MCP] Add experimental support for streamable HTTP MCP servers (#4317)

  This PR adds support for streamable HTTP MCP servers when the
  `experimental_use_rmcp_client` is enabled.
  
  To set one up, simply add a new mcp server config with the url:
  ```
  [mcp_servers.figma]
  url = "http://127.0.0.1:3845/mcp"
  ```
  
  It also supports an optional `bearer_token` which will be provided in an
  authorization header. The full oauth flow is not supported yet.
  
  The config parsing will throw if it detects that the user mixed and
  matched config fields (like command + bearer token or url + env).
  
  The best way to review it is to review `core/src` and then
  `rmcp-client/src/rmcp_client.rs` first. The rest is tests and
  propagating the `Transport` struct around the codebase.
  
  Example with the Figma MCP:
  <img width="5084" height="1614" alt="CleanShot 2025-09-26 at 13 35 40"
  src="https://github.com/user-attachments/assets/eaf2771e-df3e-4300-816b-184d7dec5a28"
  />

  Gabriel Peal · 2025-09-26 21:24:01 -04:00
  3a1be084f9
• update composer + user message styling (#4240)

  Changes:
  
  - the composer and user messages now have a colored background that
  stretches the entire width of the terminal.
  - the prompt character was changed from a cyan `▌` to a bold `›`.
  - the "working" shimmer now follows the "dark gray" color of the
  terminal, better matching the terminal's color scheme
  
  | Terminal + Background        | Screenshot |
  |------------------------------|------------|
  | iTerm with dark bg | <img width="810" height="641" alt="Screenshot
  2025-09-25 at 11 44 52 AM"
  src="https://github.com/user-attachments/assets/1317e579-64a9-4785-93e6-98b0258f5d92"
  /> |
  | iTerm with light bg | <img width="845" height="540" alt="Screenshot
  2025-09-25 at 11 46 29 AM"
  src="https://github.com/user-attachments/assets/e671d490-c747-4460-af0b-3f8d7f7a6b8e"
  /> |
  | iTerm with color bg | <img width="825" height="564" alt="Screenshot
  2025-09-25 at 11 47 12 AM"
  src="https://github.com/user-attachments/assets/141cda1b-1164-41d5-87da-3be11e6a3063"
  /> |
  | Terminal.app with dark bg | <img width="577" height="367"
  alt="Screenshot 2025-09-25 at 11 45 22 AM"
  src="https://github.com/user-attachments/assets/93fc4781-99f7-4ee7-9c8e-3db3cd854fe5"
  /> |
  | Terminal.app with light bg | <img width="577" height="367"
  alt="Screenshot 2025-09-25 at 11 46 04 AM"
  src="https://github.com/user-attachments/assets/19bf6a3c-91e0-447b-9667-b8033f512219"
  /> |
  | Terminal.app with color bg | <img width="577" height="367"
  alt="Screenshot 2025-09-25 at 11 45 50 AM"
  src="https://github.com/user-attachments/assets/dd7c4b5b-342e-4028-8140-f4e65752bd0b"
  /> |

  Jeremy Rose · 2025-09-26 16:35:56 -07:00
  43b63ccae8
• [MCP] Introduce an experimental official rust sdk based mcp client (#4252)

  The [official Rust
  SDK](https://github.com/modelcontextprotocol/rust-sdk/tree/57fc428c578a1a3fe851ee0838bf068bda120eb3)
  has come a long way since we first started our mcp client implementation
  5 months ago and, today, it is much more complete than our own
  stdio-only implementation.
  
  This PR introduces a new config flag `experimental_use_rmcp_client`
  which will use a new mcp client powered by the sdk instead of our own.
  
  To keep this PR simple, I've only implemented the same stdio MCP
  functionality that we had but will expand on it with future PRs.
  
  ---------
  
  Co-authored-by: pakrym-oai <pakrym@openai.com>

  Gabriel Peal · 2025-09-26 13:13:37 -04:00
  e555a36c6a
• ref: state - 2 (#4229)

  Extracting tasks in a module and start abstraction behind a Trait (more
  to come on this but each task will be tackled in a dedicated PR)
  The goal was to drop the ActiveTask and to have a (potentially) set of
  tasks during each turn

  jif-oai · 2025-09-26 13:49:08 +00:00
  1fc3413a46
• Actually mount sse once (#4264)

  Mock server was responding with the same result many times.

  pakrym-oai · 2025-09-26 01:17:51 +00:00
  a10403d697
• Add codex exec testing helpers (#4254)

  Add a shortcut to create working directories and run codex exec with
  fake server.

  pakrym-oai · 2025-09-25 17:12:45 -07:00
  8e3a048fec
• make tests pass cleanly in sandbox (#4067)

  This changes the reqwest client used in tests to be sandbox-friendly,
  and skips a bunch of other tests that don't work inside the
  sandbox/without network.

  Jeremy Rose · 2025-09-25 13:11:14 -07:00
  4a5f05c136
• Send text parameter for non-gpt-5 models (#4195)

  We had a hardcoded check for gpt-5 before.
  
  Fixes: https://github.com/openai/codex/issues/4181

  pakrym-oai · 2025-09-24 22:00:06 +00:00
  e85742635f
• Add Reset in for rate limits (#4111)

  - Parse the headers
  - Reorganize the struct because it's getting too long
  - show the resets at in the tui
  
  <img width="324" height="79" alt="image"
  src="https://github.com/user-attachments/assets/ca15cd48-f112-4556-91ab-1e3a9bc4683d"
  />

  Ahmed Ibrahim · 2025-09-24 15:31:08 +00:00
  cb96f4f596
• Send limits when getting rate limited (#4102)

  Users need visibility on rate limits when they are rate limited.

  Ahmed Ibrahim · 2025-09-23 22:56:34 +00:00
  8227a5ba1b
• Add exec output-schema parameter (#4079)

  Adds structured output to `exec` via the `--structured-output`
  parameter.

  pakrym-oai · 2025-09-23 13:59:16 -07:00
  fdb8dadcae
• chore: compact do not modify instructions (#4088)

  Keep the developer instruction and insert the summarisation message as a
  user message instead

  jif-oai · 2025-09-23 17:59:17 +01:00
  b84a920067
• Use TestCodex builder in stream retry tests (#4096)

  ## Summary
  - refactor the stream retry integration tests to construct conversations
  through `TestCodex`
  - remove bespoke config and tempdir setup now handled by the shared
  builder
  
  ## Testing
  - cargo test -p codex-core --test all
  stream_error_allows_next_turn::continue_after_stream_error
  - cargo test -p codex-core --test all
  stream_no_completed::retries_on_early_close
  
  ------
  https://chatgpt.com/codex/tasks/task_i_68d2b94d83888320bc75a0bc3bd77b49

  pakrym-oai · 2025-09-23 08:57:08 -07:00
  76ecbb3d8e
• Add notifier tests (#4064)

  Proposal:
  1. Use anyhow for tests and avoid unwrap
  2. Extract a helper for starting a test instance of codex

  pakrym-oai · 2025-09-23 14:25:46 +00:00
  5c7d9e27b1
• feat: update default (#4076)

  Changes:
  - Default model and docs now use gpt-5-codex. 
  - Disables the GPT-5 Codex NUX by default.
  - Keeps presets available for API key users.

  Thibault Sottiaux · 2025-09-22 20:10:52 -07:00
  c93e77b68b
• Change headers and struct of rate limits (#4060)
  Ahmed Ibrahim · 2025-09-22 21:06:20 +00:00
  dd56750612
• chore: clippy on redundant closure (#4058)

  Add redundant closure clippy rules and let Codex fix it by minimising
  FQP

  jif-oai · 2025-09-22 19:30:16 +00:00
  be366a31ab
• chore: unify cargo versions (#4044)

  Unify cargo versions at root

  jif-oai · 2025-09-22 16:47:01 +00:00
  e5fe50d3ce
• Add non_sandbox_test helper (#3880)

  Makes tests shorter

  pakrym-oai · 2025-09-22 14:50:41 +00:00
  14a115d488
• Forward Rate limits to the UI (#3965)

  We currently get information about rate limits in the response headers.
  We want to forward them to the clients to have better transparency.
  UI/UX plans have been discussed and this information is needed.

  Ahmed Ibrahim · 2025-09-20 21:26:16 -07:00
  04504d8218
• Use helpers instead of fixtures (#3888)

  Move to using test helper method everywhere.

  pakrym-oai · 2025-09-19 06:46:25 -07:00
  9b18875a42
• Move responses mocking helpers to a shared lib (#3878)

  These are generally useful

  pakrym-oai · 2025-09-18 17:53:14 -07:00
  881c7978f1
• fix: ensure cwd for conversation and sandbox are separate concerns (#3874)

  Previous to this PR, both of these functions take a single `cwd`:
  
  
  https://github.com/openai/codex/blob/71038381aa0f51aa62e1a2bcc7cbf26a05b141f3/codex-rs/core/src/seatbelt.rs#L19-L25
  
  
  https://github.com/openai/codex/blob/71038381aa0f51aa62e1a2bcc7cbf26a05b141f3/codex-rs/core/src/landlock.rs#L16-L23
  
  whereas `cwd` and `sandbox_cwd` should be set independently (fixed in
  this PR).
  
  Added `sandbox_distinguishes_command_and_policy_cwds()` to
  `codex-rs/exec/tests/suite/sandbox.rs` to verify this.

  Michael Bolin · 2025-09-18 14:37:06 -07:00
  8595237505
• Reland "refactor transcript view to handle HistoryCells" (#3753)

  Reland of #3538

  Jeremy Rose · 2025-09-18 20:55:53 +00:00
  b34e906396
• Make ESC button work when auto-compaction (#3857)

  Only emit a task finished when the compaction comes from a `/compact`

  jif-oai · 2025-09-18 15:34:16 +00:00
  4a5d6f7c71
• Add dev message upon review out (#3758)

  Proposal: We want to record a dev message like so:
  
  ```
  {
        "type": "message",
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "<user_action>
    <context>User initiated a review task. Here's the full review output from reviewer model. User may select one or more comments to resolve.</context>
    <action>review</action>
    <results>
    {findings_str}
    </results>
  </user_action>"
          }
        ]
      },
  ```
  
  Without showing in the chat transcript.
  
  Rough idea, but it fixes issue where the user finishes a review thread,
  and asks the parent "fix the rest of the review issues" thinking that
  the parent knows about it.
  
  ### Question: Why not a tool call?
  
  Because the agent didn't make the call, it was a human. + we haven't
  implemented sub-agents yet, and we'll need to think about the way we
  represent these human-led tool calls for the agent.

  dedrisian-oai · 2025-09-16 18:43:32 -07:00
  72733e34c4