update summary to auto by trevorcreech · Pull Request #1 · openai/codex

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 #1: Browser login fix (termux-open-url) - Patch #2: RAM optimizations (lto=false, codegen-units=16) - Patch #3: Auto-update URL (@mmmbuto/codex-cli-termux) - Patch #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: - #1 Browser login (termux-open-url) ✅ - #2 RAM optimizations (lto=false, codegen-units=16) ✅ - #8 Bash execution (sandbox, LD_*, shell detection) ✅ - #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 #1, #2, #4, #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 #1: Browser login (termux-open-url) - VERIFIED ✅ - Patch #2: RAM optimization (lto=false) - VERIFIED ✅ - Patch #4: Auto-update URL (DioNanos/codex-termux) - VERIFIED ✅ - Patch #5: Version parser (-termux suffix) - VERIFIED ✅ - Patch #6: NPM package name (@mmmbuto/codex-cli-termux) - VERIFIED ✅ - Patch #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: #1-#6, #8, #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 (#1-#6, #9 active) - Patch #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 (#1-#6, #9) - Patch #8 resolved upstream - Sync npm-package/README.md with root README.md

…put image above user message

…ai#8950) 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 openai#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"] } ] ```

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.

Fixes openai#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 openai#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>

…i#10590) ## Summary This PR makes app-server-provided image URLs first-class attachments in TUI, so they survive resume/backtrack/history recall and are resubmitted correctly. <img width="715" height="491" alt="Screenshot 2026-02-12 at 8 27 08 PM" src="https://github.com/user-attachments/assets/226cbd35-8f0c-4e51-a13e-459ef5dd1927" /> Can delete the attached image upon backtracking: <img width="716" height="301" alt="Screenshot 2026-02-12 at 8 27 31 PM" src="https://github.com/user-attachments/assets/4558d230-f1bd-4eed-a093-8e1ab9c6db27" /> In both history and composer, remote images are rendered as normal `[Image #N]` placeholders, with numbering unified with local images. ## What changed - Plumb remote image URLs through TUI message state: - `UserHistoryCell` - `BacktrackSelection` - `ChatComposerHistory::HistoryEntry` - `ChatWidget::UserMessage` - Show remote images as placeholder rows inside the composer box (above textarea), and in history cells. - Support keyboard selection/deletion for remote image rows in composer (`Up`/`Down`, `Delete`/`Backspace`). - Preserve remote-image-only turns in local composer history (Up/Down recall), including restore after backtrack. - Ensure submit/queue/backtrack resubmit include remote images in model input (`UserInput::Image`), and keep request shape stable for remote-image-only turns. - Keep image numbering contiguous across remote + local images: - remote images occupy `[Image openai#1]..[Image #M]` - local images start at `[Image #M+1]` - deletion renumbers consistently. - In protocol conversion, increment shared image index for remote images too, so mixed remote/local image tags stay in a single sequence. - Simplify restore logic to trust in-memory attachment order (no placeholder-number parsing path). - Backtrack/replay rollback handling now queues trims through `AppEvent::ApplyThreadRollback` and syncs transcript overlay/deferred lines after trims, so overlay/transcript state stays consistent. - Trim trailing blank rendered lines from user history rendering to avoid oversized blank padding. ## Docs + tests - Updated: `docs/tui-chat-composer.md` (remote image flow, selection/deletion, numbering offsets) - Added/updated tests across `tui/src/chatwidget/tests.rs`, `tui/src/app.rs`, `tui/src/app_backtrack.rs`, `tui/src/history_cell.rs`, and `tui/src/bottom_pane/chat_composer.rs` - Added snapshot coverage for remote image composer states, including deleting the first of two remote images. ## Validation - `just fmt` - `cargo test -p codex-tui` ## Codex author `codex fork 019c2636-1571-74a1-8471-15a3b1c3f49d`

…h prefixes Code-review R3: the Contrarian APPROVED (verified the actual projection clean), but the Codex reviewer OBJECTed on a completeness edge — `(?<![\w/])` did not cover relative/home path prefixes, so `./codex` → `.codex` and `~/codex` → `~codex` would still corrupt a path whose final segment is a command name (a theoretical edge today — the Contrarian confirmed no live occurrence — but a real incompleteness). - lib/compile.js — lookbehind widened to `(?<![\w./~])`: the slash-command strip now refuses to fire when preceded by a word char, slash, dot, OR tilde, i.e. every path/URL prefix. Boundary harness (9 cases) confirms: ./codex, ./codex-pty.sh, ~/codex, openai/codex#1, .agents/skills/council/x all PRESERVED; standalone /new-feature, `/codex`, (/council), /council-at-start all STRIPPED to bare names. Full suite 482/482, tsc 0, smoke-ola9b 20/20. Next: R4 objector confirmation (Codex). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

## Stack 1. [1 of 3] Support long raw TUI goal objectives - #27508 2. [2 of 3] Support long pasted text in TUI goals - #27509 3. **[3 of 3] Support images in TUI goals** - this PR ## Why The first two PRs make goal definitions resilient to long text, but `/goal` still dropped image inputs from the composer. That meant a user could attach images while defining a goal and the resulting goal continuation would not have any useful reference to those images. Goal state still persists only objective text, so image inputs need to become paths or URLs that the agent can read later. ## What Changed - Extends TUI `GoalDraft` with local image attachments and remote image URLs. - Copies local goal images through the app-server filesystem layer into the managed goal attachment directory, then rewrites active image placeholders to file references. - Appends unplaced local images and remote image URLs to the objective as referenced image files or URLs. - Preserves goal image metadata through live `/goal` submission and queued `/goal` dispatch. ## Verification - Added goal materialization coverage for local image files and remote image URLs. - Added/updated TUI slash-command coverage showing `/goal` drafts include attached images instead of dropping them. ## Manual Testing - Attached an image by bracketed-pasting its local path into a live `/goal` composer. The `[Image #1]` placeholder became a server-host `image-1.png` reference, copied bytes matched exactly, and no attachment was written under the TUI's local home. - Deleted an image placeholder before submitting a small goal and verified no image was copied. - Attached PNG and JPEG files to the same goal. Placeholder order was preserved as `image-1.png` and `image-2.jpg`, and both remote copies matched their source bytes. - Tried extensionless, malformed-extension, and extension/content-mismatched paths; the composer rejected them as image attachments before goal dispatch rather than creating misleading managed image files. - Combined a local image, a large pasted block, and enough raw text to exceed 4,000 characters. The remote attachment directory contained the image, paste sidecar, and `goal-objective.md`; all embedded references used server-host paths and both payloads matched their sources. - Submitted an image replacement while a goal was active, verified no image was copied before confirmation, then canceled and confirmed the attachment count was unchanged.

…ai#8950) 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 openai#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"] } ] ```

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.

Fixes openai#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 openai#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>

…i#10590) ## Summary This PR makes app-server-provided image URLs first-class attachments in TUI, so they survive resume/backtrack/history recall and are resubmitted correctly. <img width="715" height="491" alt="Screenshot 2026-02-12 at 8 27 08 PM" src="https://github.com/user-attachments/assets/226cbd35-8f0c-4e51-a13e-459ef5dd1927" /> Can delete the attached image upon backtracking: <img width="716" height="301" alt="Screenshot 2026-02-12 at 8 27 31 PM" src="https://github.com/user-attachments/assets/4558d230-f1bd-4eed-a093-8e1ab9c6db27" /> In both history and composer, remote images are rendered as normal `[Image #N]` placeholders, with numbering unified with local images. ## What changed - Plumb remote image URLs through TUI message state: - `UserHistoryCell` - `BacktrackSelection` - `ChatComposerHistory::HistoryEntry` - `ChatWidget::UserMessage` - Show remote images as placeholder rows inside the composer box (above textarea), and in history cells. - Support keyboard selection/deletion for remote image rows in composer (`Up`/`Down`, `Delete`/`Backspace`). - Preserve remote-image-only turns in local composer history (Up/Down recall), including restore after backtrack. - Ensure submit/queue/backtrack resubmit include remote images in model input (`UserInput::Image`), and keep request shape stable for remote-image-only turns. - Keep image numbering contiguous across remote + local images: - remote images occupy `[Image openai#1]..[Image #M]` - local images start at `[Image #M+1]` - deletion renumbers consistently. - In protocol conversion, increment shared image index for remote images too, so mixed remote/local image tags stay in a single sequence. - Simplify restore logic to trust in-memory attachment order (no placeholder-number parsing path). - Backtrack/replay rollback handling now queues trims through `AppEvent::ApplyThreadRollback` and syncs transcript overlay/deferred lines after trims, so overlay/transcript state stays consistent. - Trim trailing blank rendered lines from user history rendering to avoid oversized blank padding. ## Docs + tests - Updated: `docs/tui-chat-composer.md` (remote image flow, selection/deletion, numbering offsets) - Added/updated tests across `tui/src/chatwidget/tests.rs`, `tui/src/app.rs`, `tui/src/app_backtrack.rs`, `tui/src/history_cell.rs`, and `tui/src/bottom_pane/chat_composer.rs` - Added snapshot coverage for remote image composer states, including deleting the first of two remote images. ## Validation - `just fmt` - `cargo test -p codex-tui` ## Codex author `codex fork 019c2636-1571-74a1-8471-15a3b1c3f49d`

## Stack 1. [1 of 3] Support long raw TUI goal objectives - openai#27508 2. [2 of 3] Support long pasted text in TUI goals - openai#27509 3. **[3 of 3] Support images in TUI goals** - this PR ## Why The first two PRs make goal definitions resilient to long text, but `/goal` still dropped image inputs from the composer. That meant a user could attach images while defining a goal and the resulting goal continuation would not have any useful reference to those images. Goal state still persists only objective text, so image inputs need to become paths or URLs that the agent can read later. ## What Changed - Extends TUI `GoalDraft` with local image attachments and remote image URLs. - Copies local goal images through the app-server filesystem layer into the managed goal attachment directory, then rewrites active image placeholders to file references. - Appends unplaced local images and remote image URLs to the objective as referenced image files or URLs. - Preserves goal image metadata through live `/goal` submission and queued `/goal` dispatch. ## Verification - Added goal materialization coverage for local image files and remote image URLs. - Added/updated TUI slash-command coverage showing `/goal` drafts include attached images instead of dropping them. ## Manual Testing - Attached an image by bracketed-pasting its local path into a live `/goal` composer. The `[Image openai#1]` placeholder became a server-host `image-1.png` reference, copied bytes matched exactly, and no attachment was written under the TUI's local home. - Deleted an image placeholder before submitting a small goal and verified no image was copied. - Attached PNG and JPEG files to the same goal. Placeholder order was preserved as `image-1.png` and `image-2.jpg`, and both remote copies matched their source bytes. - Tried extensionless, malformed-extension, and extension/content-mismatched paths; the composer rejected them as image attachments before goal dispatch rather than creating misleading managed image files. - Combined a local image, a large pasted block, and enough raw text to exceed 4,000 characters. The remote attachment directory contained the image, paste sidecar, and `goal-objective.md`; all embedded references used server-host paths and both payloads matched their sources. - Submitted an image replacement while a goal was active, verified no image was copied before confirmation, then canceled and confirmed the attachment count was unchanged.

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

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

synestiqx 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

Closed

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

Closed

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

jacobcxdev mentioned this pull request Jun 8, 2026

MCP stdio servers leak pipe fds + orphan child processes → cumulative EMFILE ("Too many open files", os error 24) #26984

Open

aditya-oss-prog mentioned this pull request Jun 9, 2026

GPT-5.5 xhigh via Amazon Bedrock stops automatically mid-task in Codex CLI, same as GPT-5.4 xhigh #26860

Open

btraut-openai mentioned this pull request Jun 10, 2026

Improve /goal in TUI to support long objectives and images #27337

Closed

gktdgktd mentioned this pull request Jun 12, 2026

Windows Computer Use @oai/sky exports mismatch still reproduces on 26.609.30741 / @oai/sky 0.4.10 #27747

Closed

mitre88 mentioned this pull request Jun 14, 2026

thread-store: a single BOM-prefixed rollout .jsonl fails the entire thread read and blocks message creation #28139

Open

antoyo mentioned this pull request Jun 18, 2026

Add setting to disable the auto-resolve in 60 seconds for questions #28969

Open

HamburgJ mentioned this pull request Jun 20, 2026

MCP client does not auto-reconnect after disconnect #11489

Open

bongsu-rapportlabs mentioned this pull request Jun 21, 2026

TypeScript SDK JSONL parser fails on multiline MCP tool results (patch available) #23131

Open

ceddybi mentioned this pull request Jun 23, 2026

Feature Request: Read-only reviewer sidecar for Codex tasks #29530

Open

snailwei mentioned this pull request Jun 23, 2026

Bug Report: Codex App — LLM Returns Invalid JSON in Function Call Arguments #29549

Open

jlitola mentioned this pull request Jun 24, 2026

fix: surface unresolved repo ref suggestions githits-com/githits-cli#193

Merged

gpoumarat mentioned this pull request Jun 25, 2026

Codex CLI feedback: recurring WSL instability / interop breakage #30040

Open

Keksuccino mentioned this pull request Jun 26, 2026

[Codex App] Confusing "Enter" behavior setting #30174

Open

odeinjul mentioned this pull request Jun 28, 2026

Codex CLI resume can create two live divergent agents after SSH disconnect #30424

Open

MrChadMWood mentioned this pull request Jun 29, 2026

Burning tokens very fast #14593

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

update summary to auto#1

update summary to auto#1
tibo-openai merged 1 commit into
mainfrom
dev/tcreech/auto-summary

trevorcreech commented Apr 16, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

8 participants

Uh oh!

Conversation

trevorcreech commented Apr 16, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

8 participants