update summary to auto #1

trevorcreech · 2025-04-16T16:59:21Z

No description provided.

Critical bugfix - auto-update detection now working Fixes: - Version parser now handles -termux suffix correctly - Tag parser accepts both rust-v* and v*-termux formats - Added test coverage for Termux tag validation Technical details: - v0.58.0 upstream merge overwrote -termux suffix support - New upstream code rejected v*-termux tag format - Prevented version.json creation and update notifications Affected versions: v0.58.0 through v0.58.3 Termux patches (4 total): - Patch openai#1: Browser login fix (termux-open-url) - Patch openai#2: RAM optimizations (lto=false, codegen-units=16) - Patch openai#3: Auto-update URL (@mmmbuto/codex-cli-termux) - Patch openai#4: Auto-update detection (this release)

Upstream changes (40+ commits): - New: codex-shell-tool-mcp MCP server - New: execpolicycheck CLI command - New: TUI animations toggle feature - New: Shell timeout increased to 1 hour - Refactor: execpolicy migration (execpolicy2 -> execpolicy) - Removed: tiktoken-rs, shell_command feature - Improved: FreeBSD portability, fuzzy search (8->20 results) Termux patches verified compatible: - openai#1 Browser login (termux-open-url) ✅ - openai#2 RAM optimizations (lto=false, codegen-units=16) ✅ - openai#8 Bash execution (sandbox, LD_*, shell detection) ✅ - openai#9 Auto-update execution ✅ Stats: 195 files changed, +5915 insertions, -2293 deletions 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>

- 8 new tests to validate Termux patches after upstream merge - Critical tests for Patch openai#1, openai#2, openai#4, openai#9 (conflicting patches) - Test auto-update execution, browser login, RAM optimization - Essential for post-merge validation before npm publish Test suite v1.2 → v1.3 (90 total tests)

Merged 61 commits from openai/codex upstream (Nov 21-27, 2025). ✅ ALL TERMUX PATCHES PRESERVED: - Patch openai#1: Browser login (termux-open-url) - VERIFIED ✅ - Patch openai#2: RAM optimization (lto=false) - VERIFIED ✅ - Patch openai#4: Auto-update URL (DioNanos/codex-termux) - VERIFIED ✅ - Patch openai#5: Version parser (-termux suffix) - VERIFIED ✅ - Patch openai#6: NPM package name (@mmmbuto/codex-cli-termux) - VERIFIED ✅ - Patch openai#9: Auto-update execution (npm install) - VERIFIED ✅ NEW UPSTREAM FEATURES: - Enterprise skip upgrade config (check_for_update_on_startup) - Unified exec pruning strategy - Custom env for unified exec process - Compaction events - Thread/turn ID in notifications - Config management app-server - Cargo audit workflow + cargo-deny - NetBSD build fixes - Windows sandbox enhancements - Documentation improvements UPSTREAM CHANGES: - 232 files changed - +11247 insertions, -7808 deletions - New codex-api/ and codex-client/ crates - Rollout session error improvements - Apply patch parsing fixes CONFLICTS RESOLVED: - README.md: Merged Testing section (Termux) + Documentation links (upstream) NEXT: Compilation + Category 13 test suite validation

…8+ requirement - Upstream: OpenAI Codex rust-v0.79.0 - Termux patches validated: openai#1-openai#6, openai#8, openai#9 - Testing: 47/49 passed (2 skipped: WebSearch, Git) - Documentation: - Added GLM-4.7 quickstart guide (docs/GLM4.7-quickstart.md) - Updated README with GLM-4.7 Path 2 in Quickstart - Node.js requirement updated to >=18 (recommended >=22) - Web search safety warning added - Tagline updated to "Built from upstream" - Package: npm-package synced with main README - Binaries: codex (59M), codex-exec (34M), codex-tui (41M) verified

…put image above user message

Agent wouldn't "see" attached images and would instead try to use the view_file tool: <img width="1516" height="504" alt="image" src="https://github.com/user-attachments/assets/68a705bb-f962-4fc1-9087-e932a6859b12" /> In this PR, we wrap image content items in XML tags with the name of each image (now just a numbered name like `[Image #1]`), so that the model can understand inline image references (based on name). We also put the image content items above the user message which the model seems to prefer (maybe it's more used to definitions being before references). We also tweak the view_file tool description which seemed to help a bit Results on a simple eval set of images: Before <img width="980" height="310" alt="image" src="https://github.com/user-attachments/assets/ba838651-2565-4684-a12e-81a36641bf86" /> After <img width="918" height="322" alt="image" src="https://github.com/user-attachments/assets/10a81951-7ee6-415e-a27e-e7a3fd0aee6f" /> ```json [ { "id": "single_describe", "prompt": "Describe the attached image in one sentence.", "images": ["image_a.png"] }, { "id": "single_color", "prompt": "What is the dominant color in the image? Answer with a single color word.", "images": ["image_b.png"] }, { "id": "orientation_check", "prompt": "Is the image portrait or landscape? Answer in one sentence.", "images": ["image_c.png"] }, { "id": "detail_request", "prompt": "Look closely at the image and call out any small details you notice.", "images": ["image_d.png"] }, { "id": "two_images_compare", "prompt": "I attached two images. Are they the same or different? Briefly explain.", "images": ["image_a.png", "image_b.png"] }, { "id": "two_images_captions", "prompt": "Provide a short caption for each image (Image 1, Image 2).", "images": ["image_c.png", "image_d.png"] }, { "id": "multi_image_rank", "prompt": "Rank the attached images from most colorful to least colorful.", "images": ["image_a.png", "image_b.png", "image_c.png"] }, { "id": "multi_image_choice", "prompt": "Which image looks more vibrant? Answer with 'Image 1' or 'Image 2'.", "images": ["image_b.png", "image_d.png"] } ] ```

- Updated workspace version to 0.80.0-termux - All Termux patches verified functional (openai#1-openai#6, openai#9 active) - Patch openai#8 no longer required (resolved upstream by PR openai#8951) - Process hardening removed from Codex CLI improves bash execution - Test suite: 49/49 passed (CODEX_TEST_REPORT_v0.80.0.md) - Upstream changes: * Thread fork endpoints (conversation branching) * Requirements/list API * Elevated sandbox onboarding NUX * Skills explicit invocation via V2 API * Metrics capabilities (otel/metrics module) * Removed process hardening from Codex CLI - Binaries compiled: codex (60M), codex-tui (42M), codex-exec (35M), codex-app-server (38M) - Updated patches/README.md for v0.80.0

- Remove old test report (CODEX_TEST_REPORT_v0.79.0.md) - Update version references from 0.79.0 to 0.80.0 - Update upstream reference from rust-v0.79.0 to rust-v0.80.0 - Update test date from 2026-01-08 to 2026-01-10 - Update test results to 49/49 passed (0 skipped) - Update patch description: 8 patches (openai#1-openai#6, openai#9) - Patch openai#8 resolved upstream - Sync npm-package/README.md with root README.md

…put image above user message

I've seen this test fail with: ``` - Mock #1. Expected range of matching incoming requests: == 2 Number of matched incoming requests: 1 ``` This is because we pop the wrong task_complete events and then the test exits. I think this is because the MCP events are now buffered after #8874. So: 1. clear the buffer before we do any user message sending 2. additionally listen for task start before task complete 3. use the ID from task start to find the correct task complete event.

I've seen this test fail with: ``` - Mock openai#1. Expected range of matching incoming requests: == 2 Number of matched incoming requests: 1 ``` This is because we pop the wrong task_complete events and then the test exits. I think this is because the MCP events are now buffered after openai#8874. So: 1. clear the buffer before we do any user message sending 2. additionally listen for task start before task complete 3. use the ID from task start to find the correct task complete event.

- Merged 30 commits from upstream rust-v0.95.0 - Resolved 4 conflicts while preserving Termux-specific settings - Kept: README.md (Termux Edition), Cargo.toml (lto=false, codegen-units=16), Cargo.lock (from upstream), tui/Cargo.toml (rustls features) - Next step: Re-apply Termux patches openai#1-openai#6, openai#9

- Updated Cargo.toml: 0.93.0 → 0.95.0 - Updated README.md: v0.93.0-termux → v0.95.0-termux, rust-v0.93.0 → rust-v0.95.0 - Updated patches/README.md: v0.93.0 → v0.95.0 - All Termux patches (openai#1-openai#6, openai#9) preserved from v0.93.0-termux - Next step: Verify patches and build

- Copied all new v0.95.0 workspace members and dependencies - Preserved all Termux patches (openai#1-openai#6, openai#9) from v0.93.0-termux - Next step: Apply Termux compilation settings and version

- Set version = "0.95.0" - Applied Patch openai#2: lto = false, codegen-units = 16 - Preserved all upstream v0.95.0 workspace members and dependencies - All Termux patches (openai#1-openai#6, openai#9) verified present - Next step: Build ARM64 binaries

- Merged 30 commits from upstream rust-v0.95.0 - Resolved 4 conflicts while preserving Termux-specific settings - Kept: README.md (Termux Edition), Cargo.toml (lto=false, codegen-units=16), Cargo.lock (from upstream), tui/Cargo.toml (rustls features) - Next step: Re-apply Termux patches #1-openai#6, openai#9

- Updated Cargo.toml: 0.93.0 → 0.95.0 - Updated README.md: v0.93.0-termux → v0.95.0-termux, rust-v0.93.0 → rust-v0.95.0 - Updated patches/README.md: v0.93.0 → v0.95.0 - All Termux patches (#1-openai#6, openai#9) preserved from v0.93.0-termux - Next step: Verify patches and build

- Copied all new v0.95.0 workspace members and dependencies - Preserved all Termux patches (#1-openai#6, openai#9) from v0.93.0-termux - Next step: Apply Termux compilation settings and version

- Set version = "0.95.0" - Applied Patch openai#2: lto = false, codegen-units = 16 - Preserved all upstream v0.95.0 workspace members and dependencies - All Termux patches (#1-openai#6, openai#9) verified present - Next step: Build ARM64 binaries

Fixes #9050 When a draft is stashed with Ctrl+C, we now persist the full draft state (text elements, local image paths, and pending paste payloads) in local history. Up/Down recall rehydrates placeholder elements and attachments so styling remains correct and large pastes still expand on submit. Persistent (cross‑session) history remains text‑only. Backtrack prefills now reuse the selected user message’s text elements and local image paths, so image placeholders/attachments rehydrate when rolling back. External editor replacements keep only attachments whose placeholders remain and then normalize image placeholders to `[Image #1]..[Image #N]` to keep the attachment mapping consistent. Docs: - docs/tui-chat-composer.md Testing: - just fix -p codex-tui - cargo test -p codex-tui Co-authored-by: Eric Traut <etraut@openai.com>

update summary to auto

738582d

trevorcreech requested a review from ibigio April 16, 2025 16:59

tibo-openai merged commit 443ffb7 into main Apr 16, 2025
1 of 2 checks passed

tibo-openai deleted the dev/tcreech/auto-summary branch April 16, 2025 17:44

rumple pushed a commit to rumple/codex that referenced this pull request Apr 24, 2025

update summary to auto (openai#1)

1aa1882

christopherok mentioned this pull request May 1, 2025

Sandbox was mandated, but no sandbox is available! #156

Closed

get-loose mentioned this pull request May 7, 2025

Likely CLI has platform-specific logic causing non-macOS "Sandbox was mandated, but no sandbox is available!" on Linux with GPT-4.1 and Model Codex CLI (v0.1.2504301751) #849

Closed

5ocworkshop mentioned this pull request Aug 13, 2025

Erroneous tokens per min #2255

Closed

salah9003 mentioned this pull request Aug 22, 2025

Feature Request: Multimodal Image Support via @ File Search #2589

Closed

shepting pushed a commit to shepting/codex that referenced this pull request Sep 16, 2025

Support gemini and open router (openai#1)

6936d58

mzltest mentioned this pull request Sep 24, 2025

bad system call termux #4197

Closed

techjoec mentioned this pull request Sep 25, 2025

bug: model occasionally does not read enough context to correctly answer #4208

Closed

AdsQnn mentioned this pull request Sep 28, 2025

30k token limit when using API after ChatGPT exhaustion (IDE) #4216

Closed

namastex888 mentioned this pull request Sep 29, 2025

feat: append user instructions from file #4436

Closed

mattcorey mentioned this pull request Oct 22, 2025

Allow specifying specific commands that don't need permission to run #3085

Closed

kcosr mentioned this pull request Oct 28, 2025

PATH env var not preserved when launching codex #5837

Open

tunerooster mentioned this pull request Nov 11, 2025

I’m sorry, but I can’t help with that. #6494

Closed

silver-ben mentioned this pull request Jan 3, 2026

A way to exclude sensitive files #2847

Open

Wildebeest mentioned this pull request Jan 5, 2026

Codex doesn't kill hung background task #8740

Closed

yuqx1561 mentioned this pull request Jan 7, 2026

Message has tool role, but there was no previous assistant message with a tool call! Message has tool role, but there was no previous assistant message with a tool call! #8816

Closed

charley-oai added a commit that referenced this pull request Jan 9, 2026

Use [Image #1] format more consistently across Ctrl+V and drag/drop, …

d002687

…put image above user message

charley-oai added a commit that referenced this pull request Jan 12, 2026

Use [Image #1] format more consistently across Ctrl+V and drag/drop, …

5e4e63c

…put image above user message

gregblass mentioned this pull request Jan 28, 2026

Plan Mode #2101

Closed

robertmsale mentioned this pull request Feb 1, 2026

Auto-Compaction Indicator at start of turn #9773

Closed

atlascodesai mentioned this pull request Feb 2, 2026

Resume picker "Updated" column not sorted by updated time #10388

Closed

ramarivera mentioned this pull request Feb 5, 2026

Nushell + Codex app breaks #10819

Open

RyderFreeman4Logos mentioned this pull request Feb 8, 2026

feat(hooks): comprehensive hook system with lifecycle events and steering #11067

Closed

4 tasks

kendonB mentioned this pull request Feb 8, 2026

Paste image not working in Windows WSL #11120

Open

pthrasher mentioned this pull request Feb 9, 2026

Codex client output truncated when scrolling in Zellij #2558

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

update summary to auto #1

update summary to auto #1

Uh oh!

trevorcreech commented Apr 16, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

update summary to auto #1

update summary to auto #1

Uh oh!

Conversation

trevorcreech commented Apr 16, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants