Refactor native SDK tool wiring and tighten CI JSON reporting by ScriptedAlchemy · Pull Request #92 · ScriptedAlchemy/codex-native

ScriptedAlchemy · 2025-11-24T07:12:12Z

Summary

refactor sdk/native to use new codex-core exports (tiktoken tokenizer, external tool registrations)
wire pending external tools/interceptors into core registry build
filter ci-json output to only warnings/errors and keep reporting concise
keep changes minimal in codex-rs while aligning native bindings

Testing

pnpm -C sdk/native test
pnpm run ci:json

That's to centralize the truncation in one place. Next step would be to make only two methods public: one with bytes/lines and one with tokens.

This PR does the following: - Add compact prefix to the summary - Change the compaction prompt - Allow multiple compaction for long running tasks - Filter out summary messages on the following compaction Considerations: - Filtering out the summary message isn't the most clean - Theoretically, we can end up in infinite compaction loop if the user messages > compaction limit . However, that's not possible in today's code because we have hard cap on user messages. - We need to address having multiple user messages because it confuses the model. Testing: - Making sure that after compact we always end up with one user message (task) and one summary, even on multiple compaction.

…anonical examples (#5910) The Custom Prompts documentation (docs/prompts.md) was incomplete for named arguments: 1. **Documentation for custom prompts was incomplete** - named argument usage was mentioned briefly but lacked comprehensive canonical examples showing proper syntax and behavior. 2. **Fixed by adding canonical, tested syntax and examples:** - Example 1: Basic named arguments with TICKET_ID and TICKET_TITLE - Example 2: Mixed positional and named arguments with FILE and FOCUS - Example 3: Using positional arguments - Example 4: Updated draftpr example to use proper $FEATURE_NAME syntax - Added clear usage examples showing KEY=value syntax - Added expanded prompt examples showing the result - Documented error handling and validation requirements 3. **Added Implementation Reference section** that references the relevant feature implementation from the codebase (PRs #4470 and #4474 for initial implementation, #5332 and #5403 for clarifications). This addresses issue #5039 by providing complete, accurate documentation for named argument usage in custom prompts. --------- Co-authored-by: Eric Traut <etraut@openai.com>

## What? Fixes MCP server initialization failures on Windows when using script-based tools like `npx`, `pnpm`, and `yarn` that rely on `.cmd`/`.bat` files rather than `.exe` binaries. Fixes #2945 ## Why? Windows users encounter "program not found" errors when configuring MCP servers with commands like `npx` in their `~/.codex/config.toml`. This happens because: - Tools like `npx` are batch scripts (`npx.cmd`) on Windows, not executable binaries - Rust's `std::process::Command` bypasses the shell and cannot execute these scripts directly - The Windows shell normally handles this by checking `PATHEXT` for executable extensions Without this fix, Windows users must specify full paths or add `.cmd` extensions manually, which breaks cross-platform compatibility. ## How? Added platform-specific program resolution using the `which` crate to find the correct executable path: - **Windows**: Resolves programs through PATH/PATHEXT to find `.cmd`/`.bat` scripts - **Unix**: Returns the program unchanged (no-op, as Unix handles scripts natively) ### Changes - Added `which = "6"` dependency to `mcp-client/Cargo.toml` - Implemented `program_resolver` module in `mcp_client.rs` with platform-specific resolution - Added comprehensive tests for both Windows and Unix behavior ### Testing Added platform-specific tests to verify: - Unix systems execute scripts without extensions - Windows fails without proper extensions - Windows succeeds with explicit extensions - Cross-platform resolution enables successful execution **Tested on:** - Windows 11 (NT 10.0.26100.0 x64) - PowerShell 5.1 & 7+, CMD, Git Bash - MCP servers: playwright, context7, supabase - WSL (verified no regression) **Local checks passed:** ```bash cargo test && cargo clippy --tests && cargo fmt -- --config imports_granularity=Item ``` ### Results **Before:** ``` 🖐 MCP client for `playwright` failed to start: program not found ``` **After:** ``` 🖐 MCP client for `playwright` failed to start: request timed out ``` Windows users can now use simple commands like `npx` in their config without specifying full paths or extensions. The timeout issue is a separate concern that will be addressed in a follow-up PR. --------- Co-authored-by: Eric Traut <etraut@openai.com>

This reverts commit 4719cba

### Summary - Treat AltGr chords (Ctrl+Alt) as literal character input in the Codex TUI textarea so Windows terminals that report backslash and other characters via AltGr insert correctly. - Add regression test altgr_ctrl_alt_char_inserts_literal to ensure Ctrl+Alt char events append the character and advance the cursor. ### Motivation On US/UK keyboard layouts, backslash is produced by a plain key, so Ctrl+Alt handling is never exercised and the bug isn’t visible. On many non‑US layouts (e.g., German), backslash and other symbols require AltGr, which terminals report as Ctrl+Alt+<char>. Our textarea previously filtered these chords like navigation bindings, so AltGr input was dropped on affected layouts. This change treats AltGr chords as literal input so backslash and similar symbols work on Windows terminals. This fixes multiple reported Issues where the \ symbol got cut off. Like: C:\Users\Admin became C:UsersAdmin Co-authored-by: Eric Traut <etraut@openai.com>

…ason handling (#6728) ## Summary Fixes streaming issue where Claude models return only 1-4 characters instead of full responses when used through certain API providers/proxies. ## Environment - **OS**: Windows - **Models affected**: Claude models (e.g., claude-haiku-4-5-20251001) - **API Provider**: AAAI API proxy (https://api.aaai.vip/v1) - **Working models**: GLM, Google models work correctly ## Problem When using Claude models in both TUI and exec modes, only 1-4 characters are displayed despite the backend receiving the full response. Debug logs revealed that some API providers send SSE chunks with an empty string finish_reason during active streaming, rather than null or omitting the field entirely. The current code treats any non-null finish_reason as a termination signal, causing the stream to exit prematurely after the first chunk. The problematic chunks contain finish_reason with an empty string instead of null. ## Solution Fix empty finish_reason handling in chat_completions.rs by adding a check to only process non-empty finish_reason values. This ensures empty strings are ignored and streaming continues normally. ## Testing - Tested on Windows with Claude Haiku model via AAAI API proxy - Full responses now received and displayed correctly in both TUI and exec modes - Other models (GLM, Google) continue to work as expected - No regression in existing functionality ## Impact - Improves compatibility with API providers that send empty finish_reason during streaming - Enables Claude models to work correctly in Windows environment - No breaking changes to existing functionality ## Related Issues This fix resolves the issue where Claude models appeared to return incomplete responses. The root cause was identified as a compatibility issue in parsing SSE responses from certain API providers/proxies, rather than a model-specific problem. This change improves overall robustness when working with various API endpoints. --------- Co-authored-by: Eric Traut <etraut@openai.com>

This fixes bug #6697

…hardening (#6680) ## Summary Builds on FreeBSD and OpenBSD were failing due to globally enabled Linux-specific keyring features and hardening code paths not gated by OS. This PR scopes keyring native backends to the appropriate targets, disables default features at the workspace root, and adds a BSD-specific hardening function. Linux/macOS/Windows behavior remains unchanged, while FreeBSD/OpenBSD now build and run with a supported backend. ## Key Changes - Keyring features: - Disable keyring default features at the workspace root to avoid pulling Linux backends on non-Linux. - Move native backend features into target-specific sections in the affected crates: - Linux: linux-native-async-persistent - macOS: apple-native - Windows: windows-native - FreeBSD/OpenBSD: sync-secret-service - Process hardening: - Add pre_main_hardening_bsd() for FreeBSD/OpenBSD, applying: - Set RLIMIT_CORE to 0 - Clear LD_* environment variables - Simplify process-hardening Cargo deps to unconditional libc (avoid conflicting OS fragments). - No changes to CODEX_SANDBOX_* behavior. ## Rationale - Previously, enabling keyring native backends globally pulled Linux-only features on BSD, causing build errors. - Hardening logic was tailored for Linux/macOS; BSD builds lacked a gated path with equivalent safeguards. - Target-scoped features and BSD hardening make the crates portable across these OSes without affecting existing behavior elsewhere. ## Impact by Platform - Linux: No functional change; backends now selected via target cfg. - macOS: No functional change; explicit apple-native mapping. - Windows: No functional change; explicit windows-native mapping. - FreeBSD/OpenBSD: Builds succeed using sync-secret-service; BSD hardening applied during startup. ## Testing - Verified compilation across affected crates with target-specific features. - Smoke-checked that Linux/macOS/Windows feature sets remain identical functionally after scoping. - On BSD, confirmed keyring resolves to sync-secret-service and hardening compiles. ## Risks / Compatibility - Minimal risk: only feature scoping and OS-gated additions. - No public API changes in the crates; runtime behavior on non-BSD platforms is preserved. - On BSD, the new hardening clears LD_*; this is consistent with security posture on other Unix platforms. ## Reviewer Notes - Pay attention to target-specific sections for keyring in the affected Cargo.toml files. - Confirm pre_main_hardening_bsd() mirrors the safe subset of Linux/macOS hardening without introducing Linux-only calls. - Confirm no references to CODEX_SANDBOX_ENV_VAR or CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR were added/modified. ## Checklist - Disable keyring default features at workspace root. - Target-specific keyring features mapped per OS (Linux/macOS/Windows/BSD). - Add BSD hardening (RLIMIT_CORE=0, clear LD_*). - Simplify process-hardening dependencies to unconditional libc. - No changes to sandbox env var code. - Formatting and linting: just fmt + just fix -p for changed crates. - Project tests pass for changed crates; broader suite unchanged. --------- Co-authored-by: celia-oai <celia@openai.com>

## Summary Ensures we're serializing calls to `shell_command` ## Testing - [x] Added unit test

## Summary - Introduces the `codex-execpolicy2` crate. - This PR covers only the prefix-rule subset of the planned execpolicy v2 language; a richer language will follow. ## Policy - Policy language centers on `prefix_rule(pattern=[...], decision?, match?, not_match?)`, where `pattern` is an ordered list of tokens; any element may be a list to denote alternatives. `decision` defaults to `allow`; valid values are `allow`, `prompt`, and `forbidden`. `match` / `not_match` hold example commands that are tokenized and validated at load time (think of these as unit tests). ## Policy shapes - Prefix rules use Starlark syntax: ```starlark prefix_rule( pattern = ["cmd", ["alt1", "alt2"]], # ordered tokens; list entries denote alternatives decision = "prompt", # allow | prompt | forbidden; defaults to allow match = [["cmd", "alt1"]], # examples that must match this rule (enforced at compile time) not_match = [["cmd", "oops"]], # examples that must not match this rule (enforced at compile time) ) ``` ## Response shapes - Match: ```json { "match": { "decision": "allow|prompt|forbidden", "matchedRules": [ { "prefixRuleMatch": { "matchedPrefix": ["<token>", "..."], "decision": "allow|prompt|forbidden" } } ] } } ``` - No match: ```json "noMatch" ``` - `matchedRules` lists every rule whose prefix matched the command; `matchedPrefix` is the exact prefix that matched. - The effective `decision` is the strictest severity across all matches (`forbidden` > `prompt` > `allow`). --------- Co-authored-by: Michael Bolin <mbolin@openai.com>

…test (#6759) We're running into quite a bit of drag maintaining this test, since every time we add fields to an EventMsg that happened to be dumped into the `binary-size-log.jsonl` fixture, this test starts to fail. The fix is usually to either manually update the `binary-size-log.jsonl` fixture file, or update the `upgrade_event_payload_for_tests` function to map the data in that file into something workable. Eason says it's fine to delete this test, so let's just delete it

This makes MCP startup not block TUI startup. Messages sent while MCPs are booting will be queued. https://github.com/user-attachments/assets/96e1d234-5d8f-4932-a935-a675d35c05e0 Fixes #6317 --------- Co-authored-by: pakrym-oai <pakrym@openai.com>

add table of contents, lifecycle and events to readme.

## Overview Adds LM Studio OSS support. Closes #1883 ### Changes This PR enhances the behavior of `--oss` flag to support LM Studio as a provider. Additionally, it introduces a new flag`--local-provider` which can take in `lmstudio` or `ollama` as values if the user wants to explicitly choose which one to use. If no provider is specified `codex --oss` will auto-select the provider based on whichever is running. #### Additional enhancements The default can be set using `oss-provider` in config like: ``` oss_provider = "lmstudio" ``` For non-interactive users, they will need to either provide the provider as an arg or have it in their `config.toml` ### Notes For best performance, [set the default context length](https://lmstudio.ai/docs/app/advanced/per-model) for gpt-oss to the maximum your machine can support --------- Co-authored-by: Matt Clayton <matt@lmstudio.ai> Co-authored-by: Eric Traut <etraut@openai.com>

## Summary Consolidates `shell` and `shell_command` tool instructions. ## Testing - [x] Updated tests, tested locally

`--disable shell_tool` disables the built-in shell tool. This is useful for MCP-only operation. --------- Co-authored-by: Michael Bolin <mbolin@openai.com>

This PR fixes keyboard handling for the Right Alt (aka "Alt-Gr") key on Windows. This key appears on keyboards in Central and Eastern Europe. Codex has effectively never worked for Windows users in these regions because the code didn't properly handle this key, which is used for typing common symbols like `\` and `@`. A few days ago, I merged a [community-authored PR](openai/codex#6720) that supplied a partial fix for this issue. Upon closer inspect, that PR was 1) too broad (not scoped to Windows only) and 2) incomplete (didn't fix all relevant code paths, so paste was still broken). This improvement is based on another [community-provided PR](openai/codex#3241) by @marektomas-cz. He submitted it back in September and later closed it because it didn't receive any attention. This fix addresses the following bugs: #5922, #3046, #3092, #3519, #5684, #5843.

…6798) The `cap_sid` file contains the IDs of the two custom SIDs that the Windows sandbox creates/manages to implement read-only and workspace-write sandbox policies. It previously lived in `<cwd>/.codex` which means that the sandbox could write to it, which could degrade the efficacy of the sandbox. This change moves it to `~/.codex/` (or wherever `CODEX_HOME` points to) so that it is outside the workspace.

fetching rate limits every minute asynchronously

This PR adds the API V2 version of the command‑execution approval flow for the shell tool. This PR wires the new RPC (`item/commandExecution/requestApproval`, V2 only) and related events (`item/started`, `item/completed`, and `item/commandExecution/delta`, which are emitted in both V1 and V2) through the app-server protocol. The new approval RPC is only sent when the user initiates a turn with the new `turn/start` API so we don't break backwards compatibility with VSCE. The approach I took was to make as few changes to the Codex core as possible, leveraging existing `EventMsg` core events, and translating those in app-server. I did have to add additional fields to `EventMsg::ExecCommandEndEvent` to capture the command's input so that app-server can statelessly transform these events to a `ThreadItem::CommandExecution` item for the `item/completed` event. Once we stabilize the API and it's complete enough for our partners, we can work on migrating the core to be aware of command execution items as a first-class concept. **Note**: We'll need followup work to make sure these APIs work for the unified exec tool, but will wait til that's stable and landed before doing a pass on app-server. Example payloads below: ``` { "method": "item/started", "params": { "item": { "aggregatedOutput": null, "command": "/bin/zsh -lc 'touch /tmp/should-trigger-approval'", "cwd": "/Users/owen/repos/codex/codex-rs", "durationMs": null, "exitCode": null, "id": "call_lNWWsbXl1e47qNaYjFRs0dyU", "parsedCmd": [ { "cmd": "touch /tmp/should-trigger-approval", "type": "unknown" } ], "status": "inProgress", "type": "commandExecution" } } } ``` ``` { "id": 0, "method": "item/commandExecution/requestApproval", "params": { "itemId": "call_lNWWsbXl1e47qNaYjFRs0dyU", "parsedCmd": [ { "cmd": "touch /tmp/should-trigger-approval", "type": "unknown" } ], "reason": "Need to create file in /tmp which is outside workspace sandbox", "risk": null, "threadId": "019a93e8-0a52-7fe3-9808-b6bc40c0989a", "turnId": "1" } } ``` ``` { "id": 0, "result": { "acceptSettings": { "forSession": false }, "decision": "accept" } } ``` ``` { "params": { "item": { "aggregatedOutput": null, "command": "/bin/zsh -lc 'touch /tmp/should-trigger-approval'", "cwd": "/Users/owen/repos/codex/codex-rs", "durationMs": 224, "exitCode": 0, "id": "call_lNWWsbXl1e47qNaYjFRs0dyU", "parsedCmd": [ { "cmd": "touch /tmp/should-trigger-approval", "type": "unknown" } ], "status": "completed", "type": "commandExecution" } } } ```

- enabling execpolicy2 parser to parse multiple policy files to build a combined `Policy` (useful if codex detects many `.codexpolicy` files) - adding functionality to `Policy` to allow evaluation of multiple cmds at once (useful when we have chained commands)

…stderr (#6808)

## Summary - update documentation, example configs, and automation defaults to reference gpt-5.1 / gpt-5.1-codex - bump the CLI and core configuration defaults, model presets, and error messaging to the new models while keeping the model-family/tool coverage for legacy slugs - refresh tests, fixtures, and TUI snapshots so they expect the upgraded defaults ## Testing - `cargo test -p codex-core config::tests::test_precedence_fixture_with_gpt5_profile` ------ [Codex Task](https://chatgpt.com/codex/tasks/task_i_6916c5b3c2b08321ace04ee38604fc6b)

OpenCode executor should use the cheap model (workerModelLow), not the regular workerModel. Updated the model selection logic to: - supervisorModel: Uses workerModelHigh (smart/expensive like gpt-5.1-codex-max) - openCodeModel: Uses workerModelLow with fallback to claude-sonnet-4-5 This ensures cost-effective execution: smart model for strategic planning, cheap model for file operations. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>

The verification was checking Git's index status (UU) which remains until staging, causing false negatives. Now checks actual file content for conflict markers using rg. This fixes the issue where OpenCode successfully removed markers but verification reported they were still present.

Root Cause: - OpenCode was successfully removing conflict markers from files - But resolved files were never staged with 'git add' - Git kept files in UU (unmerged) status causing final verification to fail - Result: All 26 files resolved but workflow reported "FAILED (0/26 resolved)" Changes: 1. workflow-orchestrator.ts: - Added automatic staging of resolved files after OpenCode removes markers - Stage files immediately after successful resolution outcome - Log staging operations for debugging 2. git.ts: - Added stageFile(relPath: string) method to GitRepo class - Simple wrapper around 'git add' for staging resolved files This completes the merge resolution pipeline: 1. Supervisor creates strategic plan 2. OpenCode executes plan and removes conflict markers 3. Verify markers are removed (content-based check) 4. Stage the resolved file 5. Final verification checks if file is properly resolved 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>

…er conflict handling Changes: 1. OpenCode Server Cleanup: - Added close() method to OpenCodeAgent to shut down the server - Store server close callback when creating OpenCode instance - Call close() in finally block to prevent zombie processes 2. Supervisor Fallback: - When OpenCode fails to resolve conflicts, supervisor (smart model) takes over - Supervisor uses CodexAgent with full tool access to attempt resolution - Falls back gracefully with clear error messages if both fail 3. Modify/Delete Conflict Handling: - Check if file exists before running rg verification - Handle modify/delete conflicts specially (file doesn't exist) - Return early with appropriate status for non-existent files 4. Fix Variable Shadowing: - Removed 'const' from opencodeAgent assignment to use outer scope variable - Enables cleanup in finally block These fixes resolve the zombie process issue and improve success rate for complex conflicts by allowing the smarter supervisor model to handle cases where the cheaper OpenCode model fails. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>

The fallback mechanism was trying to import CodexAgent which doesn't exist in the SDK. Updated to use the native Codex class which is the correct agent for direct resolution. Changes: - Import Codex instead of CodexAgent from @codex-native/sdk - Use Codex.startThread() API to create a thread - Run fallback prompt via thread.run() method - Handle Turn result correctly (output and error properties) This fixes the SyntaxError on import and enables the supervisor fallback to work correctly when OpenCode fails to resolve conflicts. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>

Changed --unified=40 to --unified=1 and reduced character limits by ~50% to show only the essential conflicting regions with minimal context instead of displaying nearly entire files in three-way merge diffs. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>

Removed all pre-computed diffs and content snapshots from worker prompts. Agents now use git commands to actively explore conflicts instead of consuming massive diff content in prompts. This dramatically reduces prompt size and gives agents control over what context they need. Changes: - Removed: diffExcerpt, baseVsOursDiff, baseVsTheirsDiff, oursVsTheirsDiff - Removed: oursExcerpt, theirsExcerpt, baseExcerpt, originRefContent, upstreamRefContent - Added: Explicit git command instructions for three-way merge inspection - Kept: File metadata and git history logs for context 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>

changeset-bot · 2025-11-24T07:12:16Z

⚠️ No Changeset found

Latest commit: 133696b

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

Changed the regex pattern to accept 2 or more newlines (\n{2,}) instead of exactly 2 (\n\n) to handle formatting variations in the unified exec output summary. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>

aibrahim-oai and others added 30 commits November 15, 2025 06:44

Refactor truncation helpers into its own file (#6683)

94dfb21

That's to centralize the truncation in one place. Next step would be to make only two methods public: one with bytes/lines and one with tokens.

Tighten panic on double truncation (#6701)

3f1c4b9

Revert "tmp: drop sccache for windows (#6673)" (#6751)

fa5f6e7

This reverts commit 4719cba

Exempt the "codex" github user from signing the CLA (#6724)

a52cf4d

This fixes bug #6697

fix(core) serialize shell_command (#6744)

497fb4a

## Summary Ensures we're serializing calls to `shell_command` ## Testing - [x] Added unit test

feat: placeholder for image that can't be decoded to prevent 400 (#6773)

7c8d333

tmp: drop sccache for windows 2 (#6775)

98a90a3

nit: personal git ignore (#6787)

2c665fb

[app-server] add events to readme (#6690)

842a1b7

add table of contents, lifecycle and events to readme.

fix: annotate all app server v2 types with camelCase (#6791)

03a6e85

chore(core) Update shell instructions (#6679)

daf77b8

## Summary Consolidates `shell` and `shell_command` tool instructions. ## Testing - [x] Updated tests, tested locally

core: add a feature to disable the shell tool (#6481)

ab2e749

`--disable shell_tool` disables the built-in shell tool. This is useful for MCP-only operation. --------- Co-authored-by: Michael Bolin <mbolin@openai.com>

background rate limits fetch (#6789)

4000e26

fetching rate limits every minute asynchronously

Demote function call payload log to debug to avoid noisy error-level …

8465f1f

…stderr (#6808)

codex-bot and others added 10 commits November 23, 2025 18:03

Merge remote-tracking branch 'upstream/main'

10aee9c

Refactor native SDK and filter CI JSON output

e7ca142

Wire external tools into registry build

d1c0265

ScriptedAlchemy changed the title ~~syncupstream~~ Refactor native SDK tool wiring and tighten CI JSON reporting Nov 24, 2025

codex-bot and others added 10 commits November 23, 2025 23:39

Restore read_file tool, xhigh parsing, and background event UI

6091b4a

Stabilize native jest runs and cleanup runtime state

9a1fd65

Silence napi JsObject deprecation to unblock CI

b425e84

Remove napi compat-mode and clean up exports

0bbd9c2

Install cross targets in CI to fix missing core errors

6ec70ed

Fix tool specs and speed up native sdk ci

db252b1

CI: reclaim disk space on linux test runners

5e612a7

CI: free disk before lint/test on Linux

88da499

Fix unified exec large output regex and remove python dependency

0ff16f8

ScriptedAlchemy force-pushed the syncupstream branch from 858df2c to 0ff16f8 Compare November 24, 2025 14:01

codex-bot added 6 commits November 24, 2025 06:05

Fix unified exec large-output test timing and clippy lint

20b0bad

Handle out-of-order raw response notifications

9e2a560

Stabilize Windows test flakiness

155e8e6

Increase codex CLI stack to fix Windows tests

3984116

Make ci:json match full CI and emit toon report

3f1d248

ci:json include readme checks and prettier

133696b

ScriptedAlchemy merged commit 92a474c into main Nov 24, 2025
28 checks passed

Navigation Menu

Repository navigation

Refactor native SDK tool wiring and tighten CI JSON reporting - #92

Refactor native SDK tool wiring and tighten CI JSON reporting#92
ScriptedAlchemy merged 203 commits into
mainfrom
syncupstream

ScriptedAlchemy commented Nov 24, 2025 •

edited

Loading

Uh oh!

changeset-bot Bot commented Nov 24, 2025 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Uh oh!

Assignees

Labels

Projects

Milestone

Development

Uh oh!

20 participants

Conversation

ScriptedAlchemy commented Nov 24, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Testing

Uh oh!

changeset-bot Bot commented Nov 24, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

⚠️ No Changeset found

Uh oh!

Uh oh!

Reviewers

Uh oh!

Assignees

Labels

Projects

Milestone

Development

Uh oh!

20 participants

ScriptedAlchemy commented Nov 24, 2025 •

edited

Loading

changeset-bot Bot commented Nov 24, 2025 •

edited

Loading