Skip to content

fix(sandbox): OOM-bias session hosts that no cgroup scope bounds - #39189

Merged
KiroCrewCaptain merged 1 commit into
mainfrom
fix/oom-bias-session-host-without-cgroup-takeover
Nov 18, 2026
Merged

KiroCrewCaptain merged 1 commit into
mainfrom
fix/oom-bias-session-host-without-cgroup-takeover

Conversation

@iamwhatever

@iamwhatever iamwhatever commented Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: When a Linux host without cgroup v2 runs out of memory, the kernel kills a process in one agent session instead of the gateway.

On such a host nothing bounds an agent's memory, so the kernel OOM killer is the only ceiling left. Every session host runs at oom_score_adj 0, the same as the gateway, and so does everything it runs. The kernel then ranks by size, and the gateway is usually the largest process (#22681).

This PR carries @unstablebrainiac's commit from #22683 (authorship kept) on a branch of this repository, because a fork PR that changes the sandbox modules cannot pass Sensitive Change Review. The maintainer accepted the design on #22683; the code is unchanged apart from the rebase onto current main.

Why it matters

Losing the gateway ends every chat and subagent on the host at once, and the restarted gateway starts into the same memory shortage. Losing one agent process ends at most the sessions on that agent's runtime.

Not a goal

  • Bounding agent memory on hosts without cgroup v2.
  • Finding or limiting whichever process exhausted the memory.
  • Any change on a host where the cgroup scope wraps the session host, or off Linux.
  • The pod boot probe's 20-second kiro-cli check, which also uses session_host but runs no agent work.

What changed (motivation → approach → change)

When no cgroup scope bounds a session host, it now starts at oom_score_adj 1000, and so does everything it runs. Out of memory, the kernel then kills a process in one agent's tree instead of the gateway.

Session host spawn cgroup scope Profile
ACP launch tail acp/launch.py wraps it session_host, as today
the same launch tail could not wrap it new unbounded_session_host: same NOFILE headroom plus --oom-bias
pod boot probe agent_sdk/pod_child_probe.py either session_host, unchanged

The launch tail compares the argv before and after cgroup_scope_argv. An unchanged argv means no scope and no memory.max, so it picks the biased profile. The spawn shim writes oom_score_adj=1000 on the session host and its whole tree inherits it, including shell commands the harness runs itself. sandbox_rlimit.py defines the profile, sandbox.py forwards the name, and docs/architecture/resource-protection.md lists it. A shim-less install keeps the NOFILE headroom and drops only the bias.

Backwards compatibility

Compatible: a session host the cgroup scope wraps spawns exactly as before. One it cannot wrap gets today's limits plus the OOM bias, which only changes which process the kernel kills once memory is gone.

Removes nothing: the change adds one profile and picks it in one new case. No path, key, record or public function is taken away.

OS Before After
Linux, cgroup v2 scope wraps the host session_host, unbiased same, unchanged
Linux, no cgroup scope host tree at the gateway's oom_score_adj (0) host tree at 1000, gateway unchanged
macOS cgroup_scope_argv never wraps; session_host picks unbounded_session_host; the shim's bias is a no-op off Linux, NOFILE same, so behaviour unchanged
Windows no shim prefix no shim prefix, unchanged

Tests

  • test/test_acp_launch_goldens.py: the launch picks session_host when the scope wraps the spawn and unbounded_session_host when it does not.
  • test/test_spawn_exec_shim.py: the new profile's shim argv keeps RLIMIT_NOFILE:hard and adds --oom-bias; a shim-less install falls back to the session host's preexec, not the tool's 1024 cap; a real child under the new profile, and a command that child runs, both read oom_score_adj 1000 while session_host passes the parent's value through (Linux only; no runtime skip).
  • test/test_sandbox_refactor_facade.py: sandbox forwards the new name.
  • TestRealChild and TestSyncRealChild now share one xdist_group, so every real interpreter child in the module runs on one worker in turn instead of cold-starting side by side.

Proof: not provable -- other: reverting all production hunks removes the new constant, so the tests error at collection; per-hunk mutations were run by hand instead. Forcing the launch to always pick session_host fails test_only_a_session_host_without_a_cgroup_scope_is_an_oom_target; setting the bias-map entry to False fails test_unbounded_session_host_keeps_headroom_and_is_an_oom_target and test_unbounded_session_host_biases_what_its_harness_runs ((0, 0) == (1000, 1000)).

Determinism: the four new tests passed 10 repeated runs at -n0 and one run in reversed order, from a shell at oom_score_adj 0. The three touched files plus test_flake_pattern_ratchet.py pass on this head (835 passed, -n 2).

Manual verification

See Real-machine verification: one real session, its harness shell command, a grandchild, its MCP servers and a subagent were all read from /proc.

Spawn paths near this change:

Path Profile Tested here
session host (chat) unbounded_session_host on this host yes, 1000
harness shell command and its grandchild inherited yes, 1000 / 1000
MCP servers the harness starts inherited yes, all 1000
subagent (spawn_run) session host same launch tail yes, 1000
create_subprocess_limited tool spawns tool, already biased before this PR unchanged, not re-run
gateway's own helpers (symlink workers, multiprocessing) not agent spawns read 0, same as the gateway

Real-machine verification

Machine: own dev host, Amazon Linux 2, kernel 5.10, aarch64, 16 vCPU / 62 GiB, cgroup v1 (/sys/fs/cgroup is tmpfs), no swap, no systemd user bus.

Before (main 42d0d66, the live gateway on this host): a shell run by a live session reads its chain from /proc/<pid>/oom_score_adj: shell 0, kiro-cli 0, session host 0, gateway 0, and a grandchild sleep 0.

After (head 0eb6b2f, same production code as fc17b88): a throwaway gateway from this branch with its own KIROCREW_HOME on 127.0.0.1, one kirocrew chat --headless session running sh probe.sh:

14487 adj=0    kiro_crew gateway
16574 adj=1000 aim sandbox --client kiro-cli acp   (session host)
16584 adj=1000 kiro-cli acp
16684 adj=1000 kiro-cli node
17587 adj=1000 sh /tmp/oomprobe/probe.sh           (command)
17615 adj=1000 sleep 30                            (grandchild)

A second session listed every process under its session host: kiro-cli, the Kiro Crew Python MCP servers, builder-mcp, arcc and the other MCP servers all read 1000, the gateway 0. A subagent it started via spawn_run ran the same probe: its session host, command and grandchild read 1000, the gateway 0.

Not run: the namespace sandbox backend, because the shell these checks ran in refuses nested unshare(CLONE_NEWUSER) (EPERM); the test gateway used agent.sandbox_allow_unsandboxed_exec=true in its throwaway data home only. The bias is set by the spawn shim before the sandbox wrapper execs, and oom_score_adj survives exec and unshare.

Cleanup: own computer; the test gateway was stopped by PID and left no process at 1000.

Related Issues

Closes #22681

Supersedes #22683 (same commit, carried on a repository branch).

Related: #20489 (the loop-stall restart that ended the incident in #22681 before the kernel chose a victim)

Sibling sweep

Swept: git grep -n "RLIMIT_PROFILE_SESSION_HOST" -- src/
Sibling: src/kiro_crew/agent_sdk/pod_child_probe.py -- not affected -- a 20-second login probe that runs no agent work

Pattern harvest

Not generalizable: the session host is the only long-lived trusted spawn left unbiased on purpose, and acp/launch.py is its only launch site, so there is no wider class for a rule to catch.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title (feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...)
  • Existing tests pass and new tests added for new functionality
  • Self-review completed; code follows project style guidelines
  • Documentation updated (if applicable)
  • No secrets, credentials, or internal references in the diff

Sensitive change review

  • Head commit: fc17b88
  • What rule changed: when cgroup_scope_argv cannot wrap a session host, the ACP launch tail spawns it with the new unbounded_session_host profile instead of session_host. That profile is session_host's RLIMIT_NOFILE:hard plus the spawn shim's --oom-bias. A scoped session host keeps session_host.
  • Before -> after (what was allowed/blocked, now): before, an unscoped session host and everything it ran had the gateway's oom_score_adj, 0 on this host. After, they run at 1000. No mount, path mask, seccomp rule, environment scrub or descriptor limit changes, and nothing is newly allowed or blocked.
  • Worst case if wrong (breaks commands / leaks secret / locks user out): the kernel kills an agent process, at worst a session host and the sessions on its runtime, before it would have killed the gateway. No command breaks, no secret moves and no user is locked out, because the bias only raises oom_score_adj, which any unprivileged process may do.
  • Evidence checked (which sandbox result proves it): on Linux 5.10 with cgroup v1 and no user bus, a real session from a gateway on this head read 1000 for its session host, harness command, grandchild, MCP servers and a subagent's session host, and 0 for the gateway. Not run: the namespace OS sandbox backend, because the shell these checks ran in refuses nested unshare(CLONE_NEWUSER) with EPERM.
  • No regression:
    • Tools still work (which tools/commands were run, result): in that session the harness shell tool, MCP servers and spawn_run subagent all worked at 1000.
    • Backward compatible (old config / old data / old callers still work, how checked): a scoped session host spawns with session_host exactly as before, pinned by test_only_a_session_host_without_a_cgroup_scope_is_an_oom_target. A shim-less install keeps session_host_preexec, pinned by test_unbounded_session_host_fallback_keeps_the_session_host_preexec. No config key, path or public name is removed.
    • Existing tests (which suites passed on this head): test/test_spawn_exec_shim.py, test/test_acp_launch_goldens.py, test/test_sandbox_refactor_facade.py and test/test_flake_pattern_ratchet.py, 835 tests.
  • How to undo: revert the commit. The launch tail then passes session_host for every session host again, and no config or data needs cleaning up. Session hosts already running keep 1000 until they restart.

@github-actions

github-actions Bot commented Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

Sensitive Change Review

Sensitive files changed:

  • src/kiro_crew/sandbox.py

  • src/kiro_crew/sandbox_rlimit.py

  • @iamwhatever posted a complete reasoning template for fc17b88.

@github-actions github-actions Bot added the readiness: action required A blocking check or review needs attention label Nov 18, 2026
@github-actions

github-actions Bot commented Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision fc17b884cb7cd6b257b58a720d15344f9ac28624 touches no user-facing surface (no changes under website/ or committed screenshots), so the UX review was skipped. Does not block merge.

@github-actions

github-actions Bot commented Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of fc17b884cb7cd6b257b58a720d15344f9ac28624 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: the bias is applied only when the cgroup wrap left the argv unchanged, which is the exact case where no memory.max bounds the tree.

Notes

  • The scoped check is "argv changed" (argv == unscoped_argv), not "a memory ceiling is in force". If a scope is created while its memory limit is configured off, the tree stays unbiased and ties the gateway again. Having cgroup_scope_argv say whether it set a memory limit would make the choice exact.

[DESIGN-REVIEWED] fc17b88

Description read

[DESCRIPTION-READ] 7b851130e1fe7d45851625ad52583c020ac774aefb667d8896534e732f8a9f8f

That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with .github/scripts/pr-description-capture.sh over the same inputs; if it differs, the description or that evidence changed after this verdict was formed and any finding drawn from either is unproven.

@github-actions

github-actions Bot commented Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ PASS

Premise-level review of fc17b884cb7cd6b257b58a720d15344f9ac28624 — why this exists and whether the shipped surface is the smallest honest version. Updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

First-Principles-Verdict: PASS

Nothing blocks: a fix for the reported gateway OOM kill (#22681), working at the cause on its one agent launch site. The only rider is test-only and costs nothing.

What this change ships

Inventory (6 items) — 5 justified

Intent: when a Linux host without a cgroup scope runs out of memory, the kernel kills one agent's process instead of the gateway. This is a FIX.

  1. On Linux with no cgroup scope, each agent session host and everything it runs start at oom_score_adj 1000. The gateway stays at 0. — justified
  2. A new rlimit profile name, unbounded_session_host, exported through the sandbox facade. Its one consumer is acp/launch.py. — justified
  3. An install without the spawn shim keeps the session host's file-descriptor headroom for an unscoped host and drops only the bias. — justified
  4. On macOS, where no scope is ever applied, the launch now picks the biased profile. The bias does nothing there, so behaviour is unchanged. — justified
  5. docs/architecture/resource-protection.md lists the sixth profile and updates the bias list. — justified
  6. The real-child test classes now run in turn on one xdist worker. — rides along; test-only, no harm

[FIRST-PRINCIPLES-REVIEWED] fc17b88

Description read

[DESCRIPTION-READ] 4c3538c95bed0d8f078de24ceb8ae63aac5d3a275e8ffa9306592b1343105dbc

That sha256 names the PR description this verdict read. Recompute it with .github/scripts/pr-description-capture.sh; if it differs, the description changed after this verdict was formed and any finding drawn from the description is unproven.

@github-actions

github-actions Bot commented Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed fc17b884cb7cd6b257b58a720d15344f9ac28624 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] fc17b88

Verdict parsed from the review's SHA-scoped output markers for commit fc17b884cb7cd6b257b58a720d15344f9ac28624.

False positive or not applicable? A repository writer can comment:
/ai-review override fable fc17b884cb7cd6b257b58a720d15344f9ac28624 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 18, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of fc17b884cb7cd6b257b58a720d15344f9ac28624 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] fc17b88

False positive or not applicable? A repository writer can comment:
/ai-review override gpt fc17b884cb7cd6b257b58a720d15344f9ac28624 false-positive: <reason, 20 to 500 characters>

…ateway

On a host without cgroup v2 delegation the agent tree has no memory.max,
so the kernel's host-wide OOM killer is the only memory ceiling. Session
hosts were spawned with oom_score_adj 0, tying the gateway, so the kernel
picked by size and killed the gateway, ending every session.

The ACP launch tail now picks unbounded_session_host when
cgroup_scope_argv did not wrap the spawn. It keeps session_host's NOFILE
headroom and adds the OOM bias, which every process in the agent tree
inherits, including shell commands the harness runs itself.
@iamwhatever
iamwhatever force-pushed the fix/oom-bias-session-host-without-cgroup-takeover branch from 0eb6b2f to fc17b88 Compare November 18, 2026 18:58
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Sensitive change review

  • Head commit: fc17b88
  • What rule changed: when cgroup_scope_argv cannot wrap a session host, the ACP launch tail spawns it with the new unbounded_session_host profile instead of session_host. That profile is session_host's RLIMIT_NOFILE:hard plus the spawn shim's --oom-bias. A scoped session host keeps session_host.
  • Before -> after (what was allowed/blocked, now): before, an unscoped session host and everything it ran had the gateway's oom_score_adj, 0 on this host. After, they run at 1000. No mount, path mask, seccomp rule, environment scrub or descriptor limit changes, and nothing is newly allowed or blocked.
  • Worst case if wrong (breaks commands / leaks secret / locks user out): the kernel kills an agent process, at worst a session host and the sessions on its runtime, before it would have killed the gateway. No command breaks, no secret moves and no user is locked out, because the bias only raises oom_score_adj, which any unprivileged process may do.
  • Evidence checked (which sandbox result proves it): on Linux 5.10 with cgroup v1 and no user bus, a real session from a gateway on this head read 1000 for its session host, harness command, grandchild, MCP servers and a subagent's session host, and 0 for the gateway. Not run: the namespace OS sandbox backend, because the shell these checks ran in refuses nested unshare(CLONE_NEWUSER) with EPERM.
  • No regression:
    • Tools still work (which tools/commands were run, result): in that session the harness shell tool, MCP servers and spawn_run subagent all worked at 1000.
    • Backward compatible (old config / old data / old callers still work, how checked): a scoped session host spawns with session_host exactly as before, pinned by test_only_a_session_host_without_a_cgroup_scope_is_an_oom_target. A shim-less install keeps session_host_preexec, pinned by test_unbounded_session_host_fallback_keeps_the_session_host_preexec. No config key, path or public name is removed.
    • Existing tests (which suites passed on this head): test/test_spawn_exec_shim.py, test/test_acp_launch_goldens.py, test/test_sandbox_refactor_facade.py and test/test_flake_pattern_ratchet.py, 835 tests.
  • How to undo: revert the commit. The launch tail then passes session_host for every session host again, and no config or data needs cleaning up. Session hosts already running keep 1000 until they restart.

@iamwhatever

Copy link
Copy Markdown
Contributor Author

span=10c58b4db3bd

  • New interpreter probe bypasses required shared-child serialization

fixed in fc17b88: TestRealChild and TestSyncRealChild now carry one xdist_group("spawn_exec_shim_real_child"), so under --dist loadgroup every real interpreter child in the module runs on one worker, one at a time, never cold-started beside its siblings.
Not shared as one module-scoped child: each case needs a child spawned under its own profile (tool cap, session_host headroom, unbounded_session_host bias), so a single shared child cannot observe the inherited limits; serializing them is the part of D8 that removes the parallel cold-start.
Class sweep: git grep -n "class Test.*RealChild" test/test_spawn_exec_shim.py finds exactly these two classes; both are grouped.

@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: passed Eligible automated validation passed for the current revision and removed readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Nov 18, 2026
@KiroCrewCaptain
KiroCrewCaptain enabled auto-merge (squash) November 18, 2026 20:57

@KiroCrewCaptain KiroCrewCaptain left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approving. On head fc17b88 the review checked these points:

  • The new profile is picked only when cgroup_scope_argv returns the argv unchanged. Every wrapped argv starts with systemd-run and carries MemoryMax, so a scoped host can never be marked "unbounded" by mistake.
  • Every reader of the profile handles it. _rlimit_spec and _preexec_for_profile keep the session_host NOFILE headroom and its shim-less fallback, and _PROFILE_OOM_BIAS adds --oom-bias.
  • Each production hunk has a test that fails when that hunk is reverted.
  • The real-child test classes now share one xdist_group.

Security: the sandbox files changed here add no seal, mask, refusal or allowance. The only effect is a higher oom_score_adj for session trees on Linux hosts where no cgroup scope bounds them, which is what #22681 asks for. Scoped hosts and Windows behave as before. On macOS the bias step returns early, so nothing changes there either.

Done well: the Linux test proves that a grandchild inherits the bias, which is the real threat. It also keeps a session_host control in the same run, so a reading of 1000 is not just the runner's own baseline.

Optional:

  • Close #22683 as superseded once this lands.
  • The sibling sweep in the description could also list src/kiro_crew/coder/client.py, which is not affected because it runs a short Coder CLI command and is not a session host.

@KiroCrewCaptain
KiroCrewCaptain merged commit f47c07b into main Nov 18, 2026
105 of 106 checks passed
@KiroCrewCaptain
KiroCrewCaptain deleted the fix/oom-bias-session-host-without-cgroup-takeover branch November 18, 2026 20:57
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Nov 18, 2026
buluoray pushed a commit that referenced this pull request Nov 19, 2026
…ateway (#39189)

On a host without cgroup v2 delegation the agent tree has no memory.max,
so the kernel's host-wide OOM killer is the only memory ceiling. Session
hosts were spawned with oom_score_adj 0, tying the gateway, so the kernel
picked by size and killed the gateway, ending every session.

The ACP launch tail now picks unbounded_session_host when
cgroup_scope_argv did not wrap the spawn. It keeps session_host's NOFILE
headroom and adds the OOM bias, which every process in the agent tree
inherits, including shell commands the harness runs itself.

Co-authored-by: Sajal Narang <sajalnarang@gmail.com>
(cherry picked from commit f47c07b)
buluoray pushed a commit that referenced this pull request Nov 19, 2026
…ateway (#39189)

On a host without cgroup v2 delegation the agent tree has no memory.max,
so the kernel's host-wide OOM killer is the only memory ceiling. Session
hosts were spawned with oom_score_adj 0, tying the gateway, so the kernel
picked by size and killed the gateway, ending every session.

The ACP launch tail now picks unbounded_session_host when
cgroup_scope_argv did not wrap the spawn. It keeps session_host's NOFILE
headroom and adds the OOM bias, which every process in the agent tree
inherits, including shell commands the harness runs itself.

Co-authored-by: Sajal Narang <sajalnarang@gmail.com>
(cherry picked from commit f47c07b)
buluoray pushed a commit that referenced this pull request Nov 19, 2026
…ateway (#39189)

On a host without cgroup v2 delegation the agent tree has no memory.max,
so the kernel's host-wide OOM killer is the only memory ceiling. Session
hosts were spawned with oom_score_adj 0, tying the gateway, so the kernel
picked by size and killed the gateway, ending every session.

The ACP launch tail now picks unbounded_session_host when
cgroup_scope_argv did not wrap the spawn. It keeps session_host's NOFILE
headroom and adds the OOM bias, which every process in the agent tree
inherits, including shell commands the harness runs itself.

Co-authored-by: Sajal Narang <sajalnarang@gmail.com>
(cherry picked from commit f47c07b)
buluoray pushed a commit that referenced this pull request Nov 19, 2026
…ateway (#39189)

On a host without cgroup v2 delegation the agent tree has no memory.max,
so the kernel's host-wide OOM killer is the only memory ceiling. Session
hosts were spawned with oom_score_adj 0, tying the gateway, so the kernel
picked by size and killed the gateway, ending every session.

The ACP launch tail now picks unbounded_session_host when
cgroup_scope_argv did not wrap the spawn. It keeps session_host's NOFILE
headroom and adds the OOM bias, which every process in the agent tree
inherits, including shell commands the harness runs itself.

Co-authored-by: Sajal Narang <sajalnarang@gmail.com>
(cherry picked from commit f47c07b)
bolichen97 added a commit that referenced this pull request Nov 19, 2026
… main (#39387)

Backports to release/0.13.0 the fixes from #39342, squashed into one
commit and brought up to date with release/0.13.0 after the Kiro Memory
preview backport (#39360). Picks, in order; each [pick sha] is the
commit on the #39342 branch, whose body has main's cherry-picked-from line:

- fix(monitor): wake the session once when its watched PR merges or closes (#37776) [pick 84da419]
- fix(security): match deny rules against Windows program suffixes and cmd/PowerShell in-word escapes (#33569) [pick e4941b7]
- fix(mimocode): refuse a chat that would answer from Xiaomi's hosted model unsigned (#37629) [pick 1bfdce3]
- fix(acp): end a quiet agent-started cycle on the shared runtime's stale gate (#37932) [pick fa870a2]
- fix(conductor): re-read goal-conductor after a compaction (#37917) [pick ccdd67c]
- fix(security): refuse a command nested past 32 substitutions before the floors walk it (#37875) [pick 2f9bd67]
- fix(mates): carry a moved Bot's shell toolsSettings entry as execute_bash instead of holding it (#37973) [pick 16022f4]
- fix: hold an app to its own sessions, jobs and runs (#37804) [pick 3dff0c0]
- fix(acp): keep a KAS chat's stored record when its resume fails after the load (#37955) [pick 6ceb7b5]
- fix(gateway): ignore a repeat SIGTERM during graceful shutdown (#38031) [pick b48287d]
- fix(security): keep a quote in a $( ) from hiding a later ssh (#37558) [pick b9fed61]
- fix(agent): rebuild takes a server's disabledTools from the kiro global (#38147) [pick c50bbcc]
- fix(mcp_gateway): keep the backend when a stub leaves an open listen (#38121) [pick 3e9c7f9]
- fix: refresh plan and model list after a kiro-cli sign-in to another account (#38053) [pick 5ad3d36]
- fix(slack): keep a picture sent in a linked thread for the dashboard turn (#38076) [pick 7f8903e]
- fix: keep a resolved tool policy when the gateway is too slow to answer (#36669) [pick 9be5691]
- fix: open owner-only files and prune overlay folders without following links (#36994) [pick 6a1acc9]
- fix: refuse the local token mint to app backends (#38113) [pick d166dab]
- fix(subagent): hold a spawn's first prompt for its MCP servers (#38127) [pick e3e0298]
- fix(security): refuse a headless git --output write with no approver (#36326) [pick 1abee40]
- fix(restore): require an explicit mode, never default to replace (#38094) [pick ca86c06]
- fix: make the deny gate's shell walk linear in command length (#36437) [pick 22c100b]
- fix(chat): let a cancelled background start finish its session teardown (#36664) [pick b1dd34f]
- fix(acp): refuse a start when two differing specs declare the agent's name (#38411) [pick 80ccfff]
- fix: probe a silent turn while its co-tenant keeps the process busy (#38662) [pick 6354490]
- fix(kas): let a reopened chat switch to models its load select omits (#38376) [pick 1640822]
- fix(cloud): install a patched node 22 on run on aws instances (#38732) [pick 059cb90]
- fix: write member record files without following links (#37303) [pick aac9642]
- fix: fail a kas start fast once the host has turned its mcp off (#38677) [pick e147238]
- fix(decisions): fall back to HTTP/1.1 when h2 is missing (#38759) [pick fc16482]
- fix(mcp_gateway): free a spawn permit when its backend exits before initialize (#38793) [pick a084ba2]
- fix(kas): start an app chat whose tool policy hides every kirocrew-cron tool (#38761) [pick ccea5a9]
- fix(acp): give the tool-stall watchdog a margin over native waits (#34117) [pick b5d9e89]
- fix(mcp): bind the working-folder answer to its launch; observe launch changes behind name grants (#38983) [pick a1069be]
- fix(mcp): hide the gateway secret files from the npm install and third-party probe spawns (#39000) [pick 14d8571]
- fix(sandbox): fold env name case on Windows in the agent env scrub (#33997) [pick 9bdce76]
- fix(apps): let app turns follow the Auto approval mode (#38830) [pick e8336df]
- fix: end a dashboard turn stopped while it is still being prepared (#36478) [pick 37fff93]
- fix(acp): cleanup_session deletes the record on the session's own host (#39046) [pick 31b5ec4]
- fix(acp): scan only the new part of a streamed tool result (#38852) [pick e2870db]
- fix(sandbox): make an unscoped session host the OOM victim, not the gateway (#39189) [pick 2be6dde]
- fix(security): read aws s3 downloads piped into tail, with 2>&1, or with an AWS_PROFILE prefix (#38271) [pick bf65d97]
- fix: redact four display and log paths and use a fixed 502 message for session switch refusals (#38982) [pick 55d9ec7]
- fix(sandbox): pin a credential-masking app's folder after the masks on the namespace backend (#34339) [pick afd2b14]
- fix(acp): wait for systemd scope admission as its own startup stage (#37008) [pick 3e29c86]
- fix(acp): wait for systemd scope admission on the AcpClient spawn path (#38303) [pick 85f0a25]
- fix(acp): stamp the spawn instance on the AcpClient child (#38810) [pick f36eb5a]
- fix: end the turn when the agent never confirms a stop (#38512) [pick 2665c9d]
- fix(kas): renew a refused crew sign-in instead of failing every start (#38978) [pick 2f48cac]
- fix(security): keep self-host detection when the ssh verb is a glob (#34056) [pick ab53f10]
- fix(security): judge each substitution body for ssh-to-self (#37616) [pick d5b7ac3]
- test: check the ssh floor's nesting bound below the gate's depth cap (#37964) [pick 6c9ae1d]
- fix(mate): apply held Bot limits on shared claude sessions and refuse unnarrowed KAS children (#39212) [pick 721bbbe]
- test(integration): wait out and reset the hidden-chat refresh between boots (#37933) [pick e77586d]
- fix(browser): fall back to Kiro's Chromium under Automatic when Chrome's remote debugging is off (#39265) [pick 31912eb]

Left out of #39342's set (not needed for 0.13.0): the provider_labels
refactor, #34045, #36668, #39120 and #37627.

Merge with release/0.13.0: kept both imports in runtime_session_load,
runtime_spawn_launch and session_provider; session_allocation lists the
memory_policy owner; the keep-record resume path passes kas_memory_mode
as main does; dropped the ACP_BACKENDS_SESSION_EVICTION import that
moved to session_provider_new_conversation.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

On hosts without cgroup v2, the kernel OOM killer picks the gateway over agent session trees

3 participants