One read of Claude Code CLIclaude-code-20260828T013702Z
4 pages moved out of 191 read.
Pages moved
4
significant first
Pages read
191
in this capture
Captured
01:37 UTC
Corpus hash
529c1d9fcbcd
corpus-hash
What this read moved
1-4 of 4errors Changed · +40 / -0 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 145
145145| `Diff is too large for ultrareview` / `PR #<N> is too large for ultrareview` | [Command-line errors](#diff-is-too-large-for-ultrareview) |
146146| `Could not find merge-base with <branch>` | [Command-line errors](#could-not-find-merge-base-with-the-base-branch) |
147147| `Your checkout has no branches (detached HEAD only)` | [Command-line errors](#your-checkout-has-no-branches) |
148| `Ultrareview clones <owner>/<repo> in the cloud with the GitHub account connected to your Claude account, and none is connected` | [Command-line errors](#no-github-account-is-connected-to-your-claude-account) |
149| `Your connected GitHub account can't see <owner>/<repo>` | [Command-line errors](#your-connected-github-account-cant-see-the-repository) |
148150| `Failed to resume the conversation` | [Command-line errors](#failed-to-resume-the-conversation) |
149151| `No conversation found with session ID: <session-id>` | [Command-line errors](#no-conversation-found-with-the-session-id) |
150152| `Cannot switch renderers in this session` | [Command-line errors](#cannot-switch-renderers-in-this-session) |
from line 2063
20612063
20622064* Create a branch at your current commit with `git checkout -b <name>`, then rerun the review
20632065
2066<h3 id="no-github-account-is-connected-to-your-claude-account">
2067 No GitHub account is connected to your Claude account
2068</h3>
2069
2070You ran `/code-review ultra <PR#>` or `claude ultrareview <PR#>`, and before creating the cloud session Claude Code asks the server whether [the GitHub account connected to your Claude account](/docs/en/ultrareview#review-a-pull-request) can reach the PR's repository. No account is connected, or the connection expired, so the cloud clone would fail and Claude Code refuses the launch. Claude Code doesn't spend a free run or bill usage credits for a refused launch.
2071
2072```text theme={null}
2073Ultrareview clones <owner>/<repo> in the cloud with the GitHub account connected to your Claude account, and none is connected (or the connection expired). To fix: run /web-setup to reuse your GitHub CLI login, or connect an account at https://claude.ai/code/onboarding?step=alt-auth — then re-run /code-review ultra 1234 (allow a minute after connecting).
2074```
2075
2076When [`/web-setup`](/docs/en/web-quickstart#connect-from-your-terminal) isn't available in your session, the message names only the claude.ai link.
2077
2078**What to do:**
2079
2080* Run `/web-setup` to connect your GitHub CLI login to your Claude account, or connect an account at [claude.ai/code/onboarding](https://claude.ai/code/onboarding?step=alt-auth)
2081* Rerun the review a minute after connecting
2082
2083Before v2.1.248, Claude Code didn't check this before launch.
2084
2085<h3 id="your-connected-github-account-cant-see-the-repository">
2086 Your connected GitHub account can't see the repository
2087</h3>
2088
2089You ran `/code-review ultra <PR#>` or `claude ultrareview <PR#>`, and [the GitHub account connected to your Claude account](/docs/en/ultrareview#review-a-pull-request) can't read the PR's repository, so the cloud clone would fail and Claude Code refuses the launch. Claude Code doesn't spend a free run or bill usage credits for a refused launch.
2090
2091```text theme={null}
2092Your connected GitHub account can't see <owner>/<repo> — usually the Claude GitHub app isn't installed on <owner> or wasn't granted this repo (web-connected accounts need it for private repos), or a different GitHub account is connected. To fix: run /web-setup to reuse your GitHub CLI login, or install the app at https://github.com/apps/claude/installations/new — then re-run /code-review ultra 1234.
2093```
2094
2095When [`/web-setup`](/docs/en/web-quickstart#connect-from-your-terminal) isn't available in your session, the message names only the app install.
2096
2097**What to do:**
2098
2099* If your local `gh` CLI can read the repository, run `/web-setup` to connect that login to your Claude account
2100* Rerun the review after the change
2101
2102Before v2.1.248, Claude Code didn't check this before launch.
2103
20642104### Failed to resume the conversation
20652105
20662106Claude Code couldn't read or process the saved transcript for the session you selected from the [`claude --resume` picker](/docs/en/sessions#use-the-session-picker), so it ends the process rather than continue in a partially loaded state. The message includes the command to retry:
from line 2486
24462486
24472487### This session has no saved transcript
24482488
2449You attached to a stopped [background session](/docs/en/agent-view) that was backgrounded from another conversation with `←` or `/background` and stopped before its first response finished. Until that first response finishes, the conversation still lives only in the session it was backgrounded from, so `claude attach` refuses to start the stopped session rather than begin a blank conversation under the same session ID. The message ends with the `claude respawn` command for this session:
2450
2451```text theme={null}
2452This session has no saved transcript — it was stopped before its first response finished. If it was backgrounded from another conversation, that one is still intact; `claude respawn <id>` starts this one fresh.
2453```
2454
2455Opening the same session's row in [agent view](/docs/en/agent-view) shows `Press enter again to restart this session fresh` below the list instead, and a second `Enter` on the row restarts the session with an empty conversation. Before v2.1.212, opening the row showed the refusal message with no way to restart from agent view. Before v2.1.211, opening the stopped session silently started that blank conversation and could re-run the session's original prompt.
2456
2457**What to do:**
2458
2459* The conversation you backgrounded from is intact: resume it with [`claude --resume`](/docs/en/sessions) or keep working in it
2460* To start the stopped session fresh anyway, run `claude respawn <id>` with the ID from the message, or press `Enter` twice on its row in agent view
2461* If the session did finish a response and you still see this refusal on a version before v2.1.214, an unreadable folder in `~/.claude/projects` could make the transcript scan miss the saved conversation; update to v2.1.214 or later, which tolerates unreadable folders during the scan
2462
2463### Terminal host process died
2464
2465Each [background session's](/docs/en/agent-view) terminal runs in a host process under the background service, and that process died while the service still held its connection, so the session couldn't be reached.
2466
2467On Linux and WSL, the background service checks each host process every few seconds, marks the session failed when the process has exited but its connection to the service never closed, and shows the reason on its row in [agent view](/docs/en/agent-view#read-session-state):
2468
2469```text theme={null}
2470terminal host process died — press Enter to restart
2471```
2472
2473If you open the row before the check runs, the footer shows `This session's terminal host process died (the conversation is saved) — press Enter to restart it` and the row turns failed.
2474
2475From the shell, `claude attach <id>` restarts a session already marked failed for a dead host, and otherwise prints the cause and exits:
2476
2477```text theme={null}
2478Couldn't attach to <id> — This session's terminal host process died (the conversation is saved) — run `claude attach <id>` again to restart it on a fresh host.
2479```
2480
2481The conversation is saved either way.
2482
2483A row running a [shell command](/docs/en/agent-view#run-a-shell-command) instead shows `terminal host process died — its output is gone; the command was not run again`, and `claude attach` prints `This command's terminal host process died — its output is gone and the command was not run again`. Claude Code never reruns the command for you.
2484
2485**What to do:**
2486
2487* In agent view, press `Enter` on the failed row; the session restarts on a fresh host process and the conversation resumes
2488* From the shell, run `claude attach <id>` again. Claude Code prints `Session <id>'s terminal host died — restarting it on a fresh one…` and reopens the session
2489* You can't restart a shell-command row this way; dispatch the command again to rerun it
2490
2491Before v2.1.247, a dead host process could pass every liveness check the background service r
2489You attached to a stopped [background session](/docs/en/agent-view) that was backgrounded from another conversation with `←` or `/background` and stopped before its first response finished. Until that first response finishes, the conversation still lives only in the session it was backgrounded from, so `claude attach` refuses to start the stopped session rather than begin a blank conversation under the sam
tools-reference Changed · +19 / -3 lines
from line 185
185185
186186### Memory limit on Linux and WSL
187187
188On Linux and WSL, set [`CLAUDE_CODE_TOOL_MEMORY_LIMIT`](/docs/en/env-vars#variables) to a size such as `4G` to cap the memory that Bash and PowerShell tool commands can use, so one runaway build can't take the memory the rest of the session needs. Requires Claude Code v2.1.233 or later.
188On Linux and WSL, set [`CLAUDE_CODE_TOOL_MEMORY_LIMIT`](/docs/en/env-vars#variables) to a size such as `4G` to cap the memory that Bash, PowerShell, and [Monitor](#monitor-tool) tool commands can use, so one runaway build can't take the memory the rest of the session needs. Requires Claude Code v2.1.233 or later. Before v2.1.246, Monitor tool commands ran outside the cap.
189189
190190* Write the size as a number of bytes or with a `K`, `M`, `G`, or `T` suffix. Set `0`, `off`, `false`, `no`, or `none` to turn the cap off. Claude Code ignores any other value it can't read as a size, such as `4e9`.
191* Claude Code counts all of a session's Bash and PowerShell commands against the one cap, not each command on its own.
191* Claude Code counts all of a session's Bash, PowerShell, and Monitor commands against the one cap, not each command on its own.
192192* Claude Code applies the cap with a memory cgroup. When it can't set the cgroup up, commands run without a cap, and the debug log from `claude --debug` says why.
193* After a Bash or PowerShell tool command has turned the cap on, or has turned it off because of an off value or a failed cgroup setup, Claude Code holds that result until you relaunch. To apply a changed or removed value, or a fixed setup, launch `claude` again.
193* After the first process Claude Code starts has turned the cap on, or has turned it off because of an off value or a failed cgroup setup, Claude Code holds that result until you relaunch. To apply a changed or removed value, or a fixed setup, launch `claude` again.
194194* When commands can't stay under the cap, the kernel kills a command, and nothing in its result names the cap.
195
196Claude Code can also count other kinds of processes it starts against the same limit. Set [`CLAUDE_CODE_TOOL_MEMORY_CGROUP_EXCLUDE`](/docs/en/env-vars#variables) to a comma-separated list of the kinds to exempt from the cap; Claude Code applies the cap to every kind not on your list. Set it to `none` to cap every kind, or to `all-new` to cap only Bash, PowerShell, and Monitor tool commands. Requires Claude Code v2.1.246 or later. The kinds you can name:
197
198* `mcp`: local [MCP servers](/docs/en/mcp)
199* `lsp`: [language servers](#lsp-tool-behavior)
200* `hooks`: [hook](/docs/en/hooks) commands
201* `plugin`: commands that [plugins](/docs/en/plugins) run
202* `helper`: Claude Code's own helper commands, such as `git`
203* `agent`: child Claude Code processes, such as [agent teammates](/docs/en/agent-teams)
204
205Whatever you list, these rules apply:
206
207* **Unknown names**: Claude Code ignores names it doesn't recognize
208* **Bash, PowerShell, and Monitor**: Claude Code keeps Bash, PowerShell, and Monitor tool commands under the cap whatever you list
209* **Variable unset**: Claude Code takes the set of other capped kinds from configuration Anthropic delivers from the server, and that set can change over time, so set the variable when you need a set that doesn't change
210* **Permission-gating hooks**: even with every kind capped, Claude Code excludes from the cap a hook that can block or change the outcome of an action, and any MCP server that such a hook calls, so the kernel killing a permission-gating hook can't allow the action it was blocking
195211
196212## Edit tool behavior
197213
env-vars Changed · +2 / -1 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
Nothing in the body moved in this read. What changed is above.
ultrareview Changed · +4 / -0 lines
from line 52
5252
5353In PR mode, the remote sandbox clones the pull request directly from the host rather than bundling your local working tree. PR mode works with repositories on `github.com` and on [GitHub Enterprise Server](/docs/en/github-enterprise-server) instances that an Owner has connected to Claude Code.
5454
55For repositories on `github.com`, the sandbox clones with the GitHub account connected to your Claude account, so the account must be able to read the PR's repository. Claude Code checks this before creating the cloud session, unless you've set [`CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`](/docs/en/env-vars#variables), and refuses the launch when [no account is connected](/docs/en/errors#no-github-account-is-connected-to-your-claude-account) or [the account can't see the repository](/docs/en/errors#your-connected-github-account-cant-see-the-repository); the refusal names the fix. Before v2.1.248, Claude Code didn't check this before launch.
56
57Run [`/web-setup`](/docs/en/web-quickstart#connect-from-your-terminal) to connect your GitHub CLI login to your Claude account.
58
5559### Post findings to the pull request
5660
5761On Claude Code v2.1.227 or later, when you review a pull request on `github.com`, you can have Claude post the finished findings to the PR as a single plain comment from your own GitHub account. The comment isn't a review or an approval, and it ends with a "Generated by Claude Code" note. When you review a branch or a GitHub Enterprise Server pull request, Claude Code shows the findings in your session only.