Repository navigation
feat: add Google Antigravity ACP harness - #37974
Conversation
Sensitive Change ReviewSensitive files changed:
|
UX Review (Opus 5.5) — ✅ PASS (a BLOCK with no Trigger and no Outcome does not block)UX-level review of UX-Verdict: PASS cannot evaluate: missing screenshots of the new "Google Antigravity" harness choice. The PR adds a user-visible backend option, a backend card, an install hint and sign-in/version refusal messages, and the PR supplies no image. Nobody has looked at any of these surfaces. Evidence gaps
[UX-REVIEWED] 4641a47 Description read[DESCRIPTION-READ] b2d2165e0529431da5e5f5c1657d7c9d5f56c6e0cbe1f49b47c4c0777dfb8b7d That sha256 names everything this verdict read: the PR description, plus the 3 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 |
Design Review (Opus 5.5) — ✅ PASSDesign-level review of Design-Verdict: PASS Nothing blocks: the new harness plugs into the existing per-backend seams and capability sets, and the codex-only branches become set membership instead of new identity checks. Notes
[DESIGN-REVIEWED] 4641a47 Description read[DESCRIPTION-READ] 47b9686498c046aa1b2d4b3bcd7205b7901938a0e24a7b7f6dbb947af6862beb 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 |
First Principles Review (Opus 5.5) — ✅ PASSPremise-level review of First-Principles-Verdict: PASS Nothing blocks. Antigravity is a new What this change shipsInventory (10 items) — 9 justifiedIntent: let users drive Google Antigravity's standalone ACP runtime from Kiro Crew like the other harnesses. This is an ADDITION.
[FIRST-PRINCIPLES-REVIEWED] 4641a47 Description read[DESCRIPTION-READ] f3c3a8ea3fc5912a7c67252bf0b07c776bd30562e584fbb405e3a309cdc94706 That sha256 names the PR description this verdict read. Recompute it with |
Opus 5.5 Review — ✅ no blocking findingsReviewed Verdict parsed from the review's SHA-scoped output markers for commit False positive or not applicable? A repository writer can comment: |
GPT 6.1 Review — ✅ no blocking findingsGPT 6.1 completed its review of This comment is updated in place on each push. Review detailsNo findings. False positive or not applicable? A repository writer can comment: |
Security Scope Review -- ✅ PASSWhich legitimate operations does Verdict basis: adjudicated, zero confirmed regressions. Security scope review -- adjudicated candidates
No candidate flipped from allowed to refused. Scope-Verdict: PASS Reason: The shell composite this lane can classify ( TIGHTENING: Antigravity permission requests are now judged as unverifiable shell calls when the tool is ADJUDICATED: 18 candidates, 0 confirmed newly-refused PLATFORM COVERAGE: The diff makes three platform assumptions: the
One gap is not covered: the Windows UNADJUDICATED:
[SCOPE-REVIEWED] 4641a47 |
Sensitive change review
This PR is the in-repo move of #26171 (author LuisBrel); the template is posted by the PR author account so the check can be judged in-repo. AI-assisted, sent by Bolin Review bot |
217c2a0 to
1d4c1a0
Compare
Sensitive change review
This PR is the in-repo move of #26171 (author LuisBrel); the template is posted by the PR author account so the check can be judged in-repo. AI-assisted, sent by Bolin Review bot |
Sensitive change review
This PR is the in-repo move of #26171 (author LuisBrel); the template is posted by the PR author account so the check can be judged in-repo. AI-assisted, sent by Bolin Review bot |
|
@iamwhatever could you review this one? It is LuisBrel's Antigravity harness from #26171, moved to an in-repo branch so Sensitive Change Review can run (it touches
AI-assisted, sent by Bolin Review bot |
|
Thanks @bolichen97. Two macOS shards are red ( The branch also conflicts with main now, in |
Register the standalone Antigravity ACP runtime as a public harness, pin the verified release, route permission mode through session config, and declare its auth, MCP, model, effort, hook, and install contracts. Add live handshake, session, load, and MCP-startup evidence and one signed-in 1.4.4 turn corpus (shell, read, edit, refused calls and a stdio MCP call), plus focused behavior and parity tests. Refuse run_workflow, which runs the Python in its Script argument, and invoke_subagent, whose sub-agents' own tool calls no capture has shown asking, as shell calls whose command cannot be verified.
An Antigravity MCP call is named from its trusted _meta.mcp pair, so a server and tool that fuse into a native name (@view/file into view_file) must not meet the native read hook. Return only the MCP matcher forms, as the envelope-named harnesses already do.
Code change approver recommendation: A person should decideWhy: the decider estimates a 12% chance that this change introduces a defect, within the 12% limit for approving on its own, but it changes 6049 lines, more than the 400 it may approve on its own. Adds Google Antigravity (agy_acp_server 1.4.4) as an opt-in ACP backend using the existing per-harness seams. Verified in code: the version pin is enforced before the mode=default write; auto_edit and yolo are refused; prompt commands are limited to plan and usage. Main's unasked-call tripwire is armed at spawn and excludes shell and MCP calls from the expected unasked reads, which are limited to Antigravity's read, grep and glob built-ins. run_workflow, invoke_subagent and arguments named script or subagent are refused as unverifiable shell calls, on Antigravity only and not for MCP calls. Shared code changes keep existing behaviour: requires_server preserves the KAS row; the hook vocabulary is the same for existing backends plus Antigravity; the extra harness_backend argument is inside a KAS-only branch. The own-token exclusion on the credential mask follows the accepted precedent for codex, OpenCode, pi, goose and Copilot. Default backend unchanged, every check green, extensive tests added. No blocking issue found. An automated recommendation, not a review: a maintainer still decides. It approves on its own only when the estimated chance of a defect is at most 12% and the change has at most 400 changed lines. Decider v3c (217fe607) · commit |
0b43764 to
4641a47
Compare
Sensitive change review
This PR is the in-repo move of #26171 (author LuisBrel); the template is posted by the PR author account so the check can be judged in-repo. AI-assisted, sent by Bolin Review bot |
|
@iamwhatever thanks for reviewing. What changed since your review request:
New head: 4641a47. Locally, 34 touched test files pass (3105 tests), plus mypy, harness parity and docs lint. AI-assisted, sent by Bolin Review bot |
KiroCrewCaptain
left a comment
There was a problem hiding this comment.
Approving. On head 4641a47 the review read the full non-test diff and traced the permission event builder, the tool-call identity cache, the unasked-call tripwire, mode routing, the version pin, the credential floor, the sandbox preflight and model selection. It ran test/test_acp_antigravity_backend.py (208 passed) and the 12 test files this PR touches (1525 passed, apart from 4 that fail only because the review checkout did not include the parity script). It also ran 14 mutations of the guard lines, and 13 of them turned a test red. Every harness identity check is positive (== ACP_BACKEND_ANTIGRAVITY or a named set), and the Kiro path is unchanged.
Security: this PR changes the permission gate, the credential floor and the tripwire, and every change makes them tighter. Antigravity runs only in default mode, and auto_edit and yolo are refused whether they arrive at open or mid-session. run_workflow, invoke_subagent, and any argument whose name has the whole word script or subagent are judged as shell calls with no command, so the deny-by-default tier refuses them. When the command spellings in a request disagree, command is dropped. Path-named arguments only add targets to the sensitive-path check. The child starts behind the sandbox preflight and the credential mask, and the two Antigravity token leaves join the floor for every other harness. Unasked file reads are disclosed in the PR. They are kept out of the spec-hook and zero-tool sets, and crew-home secrets stay behind the OS mask.
Done well: each safety choice rests on a signed-in 1.4.4 wire capture, and the replay test runs those sessions through the real client to show that the tripwire does not fire on the harness's real unasked reads.
Optional:
- The UX lane could not evaluate this head because the PR has no screenshots. Please attach the mocked-probe captures you already have: the picker row, the card in its MISSING state with the install hint, and the version-refusal text.
- In
tool_call_identity.py:157, if a frame ever carriesis_mcp_tool_callwithout a readable_meta.mcp, the codex fallback readsrawInput.server/tool. On Antigravity those fields hold the model's own flattened arguments. One fix is to skip that branch when_meta.mcpis a dict, with a pinning test. - The PR body still describes one commit at head 2eeb923. It does not mention 4641a47, which keeps Antigravity MCP calls out of the fused native hook aliases. It also lists the shared tripwire early return, which tightens MiMo Code too, under no Reader line. Editing the body fixes both, with no push needed.
…he synthetic-credential fixtures The pin moves from 9b32941be6 to bb6e096df4 (the merge of kirodotdev/KiroCrew#37974, the in-repo move of #26171), whose shared validator refuses the two Antigravity token files the local fence names. That host no longer treats the AWS documentation example key or an AWS key ID as a secret, so the redaction tests take #31863 and the matching test changes of #37408 (tests only): their credentials come from kiro_crew.testing.synthetic_credentials. Recorded in PORTING.md.
Problem / Motivation
Goal: Let Kiro Crew users select Google Antigravity's standalone ACP runtime alongside Kiro CLI, Claude Code, Codex, OpenCode, and the other supported harnesses.
Google Antigravity publishes an ACP server in the ACP Registry, but Kiro Crew cannot currently expose it as an
agent.acp_backendchoice, resolve its two-file distribution, declare its host capabilities, or pin its permission behavior. Users who want to drive their Google-backed coding agent from Kiro Crew have to leave Crew and use a separate ACP client.Why it matters
The existing harness switch already supports multiple vendors. Adding Antigravity makes Google's agent available through the same dashboard, CLI, channels, scheduling, MCP tools, hooks, and approval flow as the other coding agents. It also keeps Crew's harness seam honest: the host contract, install probe, model/effort options, auth mask, and permission routing are declared instead of inferred.
Not a goal
agyterminal UI; this uses the standaloneagy_acp_serverACP runtime.What changed (motivation → approach → change)
Antigravity uses the existing per-session ACP seams. The launcher resolves agy_acp_server and its sibling helper together, sends MCP servers through its own
_antigravity_session_mcp_serversseam in the shared session array (gated on Antigravity, like the copilot, deepseek and pi seams), and uses the advertised model and thinking-level options. Defaults stay unchanged. The dashboard catalogs and glossary include Google Antigravity.Only ACP 1.4.4 is verified; missing or different versions are refused. The backend card, install hint and sign-in remedy say so. Permission mode stays default; modes that suppress asking are refused. Prompt commands are limited to plan and usage.
Antigravity joins the set whose unstartable stdio MCP servers are pruned before
session/new: measured on 1.4.4 signed out with an invalid API key, the session is created and nothing on the wire or stderr names a server whose command does not exist.Antigravity arms main's unasked-call tripwire (
AcpClient._tripwire_pi_gate) at spawn, as MiMo Code does: a call that reportscompletedwith nosession/request_permissionfor itstoolCallIdstops the harness. It acts after completion and cannot undo that call. ItsHARNESS_UNASKED_TOOL_IDSrow lists only the read-only built-ins (fs_read,grepandglobrows of the tool table), because 1.4.4 runs file reads unasked;harness_tool_namereads theRunning <name>title such a read carries, so the recorded name isview_file. The tripwire is fail-closed: any other unasked completion, a call whose name was never recorded included, ends the session, and a call whose frame named an MCP server never passes as a listed read. Replaying the three signed-in captures trips nothing. Main's tripwire state is not reset when the process respawns; that is shared with pi, DeepSeek and MiMo Code and is left as it is.Path-like argument names feed the sensitive-path check, including nested values and decoded file URIs. Unfamiliar command-like names detect disagreement but never supply a trusted command. Other arbitrary unknown keys are not blanket-refused.
Antigravity's
run_workflowruns the Python in itsScriptargument, which no command or path rule reads, andinvoke_subagentstarts sub-agents whose own tool calls no capture has shown asking. Such a call, named by its tool_call frame or carrying an argument whose name has the whole wordscriptorsubagent(soDescription, the edit tool's own argument, does not count), is judged as a shell call with no verifiable command, which the unverifiable-shell tier refuses on every approval policy. Its other arguments are dropped first, so none can stand in for the call as the command.ACP_BACKENDS_CONFIG_MODEL_SELECT_IS_CANONICAL makes the shared picker use configOptions model ids, because the Antigravity models list combines model and effort (for example gemini-3.8-flash-high). Antigravity stays outside the four launch/reload capability sets: model and effort use session options, MCP uses session/new, and relaunch/reload behavior is unverified. The mirror rules the new
toolsSettingsconcernno-channel, as goose and strands do: the session/new element set has no field for it, and a new chat session whose spec sets it gets one notice naming what goes unapplied. Antigravity is inACP_BACKENDS_CREW_FIRES_SPEC_OBSERVER_HOOKSbeside claude and codex, not inACP_BACKENDS_CREW_FIRES_SPEC_HOOKS: its file reads raise no permission request, so a spec'spreToolUsehooks do not run, a new session whose spec has one is told so, andpostToolUse,userPromptSubmit,agentSpawnandstopstill fire, and an unasked read is named for apostToolUsematcher by itstool_callevent. Session Activity counts Antigravity sessions from its usage rows (_SHARD_COUNTED_HARNESSES), since it writes no kiro-cli or KAS transcript.The credential declaration and packaging fence cover both token files; on a host that adopted aws-control, the fence entries arrive through KiroCrewCaptain/kirocrew-app-aws-control#10. Its own tokens remain readable for sign-in; a maintainer accepted, in review, the
host_auth.pychange that allows this, and its comment now says so. The unusedis_antigravity_backendproperty is removed. The one-line MCP seam stays: the Strands mirror test fails on a bare_session_mcp_servers()splice in the session arrays, so Antigravity uses a named seam like the other harnesses. Provider labels move unchanged into acp/provider_labels.py and are re-exported from acp/types.py to meet the line cap. Process recognition tests use launcher-shaped bytes; a live 1.4.4 process on Linux, launched with the argv Crew's spawn plan uses (absolute path only), reads back the same/proc/<pid>/cmdlineshape, and the production check recognizes it. The turn corpus is one signed-in 1.4.4 session in three files (turn-live-tools,turn-live-refused,turn-live-mcp). The optional batch write guard does not cover every Antigravity native tool name; the permission floor and unasked-call tripwire do not depend on that guard. A separate documentation correction aligns the DeepSeek mirror table with its existing runtime projection and adds a regression test; it is not an Antigravity rebase-conflict fix.src/kiro_crew/acp,src/kiro_crew/acp_backends.pysrc/kiro_crew/agent_sdksrc/kiro_crew/providers,src/kiro_crew/session_pid_harness.pysrc/kiro_crew/apps,scriptssrc/kiro_crew/docs,docswebsite/src/api,website/src/i18n,testBackwards compatibility
Compatible: this adds a backend id without changing the default backend or existing launch paths. The credential floor gains Antigravity token leaves, which enforced sibling backends also mask unless their own declarations exclude them; settings files and their parent directory are not fenced as token files.
Antigravity starts with a credential mask that hides other credential stores, including
.awsand.ssh. Its own two token files remain readable to the child for sign-in. Git over SSH works there only through the ssh-agent forward the operator consents to: the private keys stay hidden, and~/.ssh/known_hostscomes back read-only, as for every enforced harness since #34328. A maintainer accepted the own-token exclusion in review.Reader: src/kiro_crew/security/paths.py:sensitive_path_refusal -- chat -- the shared file gate also refuses Antigravity's two token leaves for existing backends; the settings file and parent directory remain readable.
Reader: src/kiro_crew/agent_sdk/tool_gate.py:adapter_hidden_credential_dirs -- chat -- builds the mask; for
antigravityit leaves out the adapter's ownacp_token.jsonandacp_business_token.jsonand keeps.awsand.sshin it, and enforced siblings gain the token leaves unless their own declarations exclude them; test_antigravity_credential_mask_spares_only_its_own_token_filesReader: src/kiro_crew/acp/client_start.py:_spawn -- chat -- takes the mask from the launcher's spawn plan; only the
antigravityplan is new; test_antigravity_spawn_sets_helper_and_credential_maskReader: src/kiro_crew/acp/client_lifecycle.py:_sandbox_init_failure -- chat -- hands the mask the spawn recorded to the sandbox init probe; the Antigravity mask is one more value of the same type
Reader: src/kiro_crew/acp/transport_errors.py:sandbox_init_failure_for_runtime -- chat -- hands the runtime's recorded mask to the same probe; same type, no new code path
Reader: src/kiro_crew/security/paths_lists.py:_SENSITIVE_HOME_DIRS -- chat -- the shared read and write gates fence the two token leaves for every backend, not the settings file or the whole parent directory.
Reader: src/kiro_crew/security/paths_targets.py:_home_dir_targets_uncached -- subagent -- GEMINI_HOME re-anchors the two exact token leaves; ordinary Gemini settings remain outside this credential addition.
Reader: src/kiro_crew/dashboard/file_api/grep.py:_grep_sensitive_globs -- crew page -- search excludes the credential targets before reading them; per-hit sensitive-path checks remain the authority.
Reader: src/kiro_crew/dashboard/side_readonly_spec.py:credential_denied_paths -- crew page -- Side Chat derives its denied paths from the shared credential targets and therefore also refuses the new token leaves.
Reader: src/kiro_crew/acp/client_claude_session.py:_claude_side_read_deny_rules -- chat -- Claude Side Chat adds denies for the same targets while keeping ordinary project settings available.
Reader: src/kiro_crew/mcp_cron_shell_scan.py:_CRON_CRED_PATH_RE -- cron -- scheduled shell commands also reject literal references to the new token leaves; ordinary scripts retain the same scanner.
Reader: src/kiro_crew/skills_script_validator.py:_SENSITIVE_PATH_RE -- app -- generated skill scripts pick up the two token leaves from the shared floor; no new script syntax is required.
Reader: src/kiro_crew/apps/builtins/aws_control/crew/packaging/pipeline/sensitive.py:_SENSITIVE_RELATIVE_DIRS -- release -- the standalone packaging fence excludes the same two token files without excluding their settings siblings.
Reader: src/kiro_crew/apps/builtins/papyrus/backend/latex.py:_sensitive_hidden_dirs -- app -- the compiler child inherits the home-relative credential floor and hides the new token leaves.
Reader: src/kiro_crew/dashboard/handlers/office_slides.py:_sensitive_hidden_dirs -- crew page -- the document converter derives its home-relative hidden paths from the same floor.
Reader: src/kiro_crew/security_posture_controls.py:_sensitive_path_items -- crew page -- the security posture view derives its credential items from the shared floor rather than a separate list.
Tests
The PR head is 2eeb923, one commit on main 969de99: 4e0d321 rebased. Two files conflicted. In
acp/client_tool_events.pymain moved the DeepSeek session code offAcpClient(#37641), so theACP_BACKEND_DEEPSEEKimport has no use left, and this PR'sstart_event_tool_idreplaces the last use ofACP_BACKEND_CODEX, so that import goes too (flake8 F401 found it). Inacp/types.pymain'ssteering_wirere-export gained two goose readers (#37567), so the resolution keeps main's four names and this PR'sprovider_labelsre-export. No other file's patch changed. On 2eeb923, 62 related test files ran: 5331 passed, 38 skipped and 4 failed, and the same 4 fail on clean main 969de99 on the same machine (twotest_pid_lifecycle.pyreclaim tests,test_worker_agent_spawn_gate.py::test_the_kas_projection_reads_nothing_after_the_gateandtest_acp_client_stale_turn.py::TestStaleTurnProbeAccounting::test_priming_verdict_defers_then_real_evidence_reaps). 4e0d321 was one commit on main 25860b2: bcb339e rebased. #37602 moved the opencode session code offAcpClientintoOpencodeAcpClient, so theclient_class.pyconflict keeps main's move and this PR's_is_antigravity, and twoagent-host-contract.mdtables keep main's rows plus the Antigravity cell. aws-control is now pinned for adoption (#37411), so its wheel-copy fence entries are ported in KiroCrewCaptain/kirocrew-app-aws-control#10, named under Related Issues. That PR lands after this one: its fence test compares the list with the shared validator of its pinned Kiro Crew, which has no Antigravity entries until this PR merges. Dropping the two wheel-copy lines here instead fails two of this repository's tests (test_every_harness_owned_credential_leaf_is_fenced_standaloneand the wheel copy'stest_the_local_subset_fences_every_foreign_credential_store), so they stay. bcb339e was one commit on main faac7ea: be1babb rebased, plus one fix. #37521 addedClaudeHarnessto the exports inacp/harness/__init__.py, beside this PR'sAntigravityLaunch, so the resolution keeps both names; no other file conflicted, and #37472's per-harness runtime-sharing switches list KAS and Codex only. The fix: this PR's owntest_slash_command_no_channel.pyexpected/helpon Antigravity to get the dashboard's notice, but Antigravity had noACP_BACKEND_PROMPT_HANDLER_COMMANDSrow, so/helpwent to the client, which refused it before the wire, and the/menu listed every kiro-cli command. Antigravity now has a row of/usage, the one Crew harness command in its prompt allowlist, as Copilot has one. The/menu lists that and the dashboard's own commands, any other kiro-cli command gets the notice, and/plan(not a Crew harness command) stays prompt text that the allowlist admits. The slash-commands cell inagent-host-contract.mdchanges from gap to partial, andharness-parity.mdlists the row. On bcb339e, 45 related test files ran: 4451 passed, 19 skipped and 3 failed, and the same 3 fail on main on the same machine (twotest_pid_lifecycle.pyreclaim tests andtest_worker_agent_spawn_gate.py::test_the_kas_projection_reads_nothing_after_the_gate). be1babb was one commit on main fd4c0d3: f59827b rebased. #37535 moved the goose session code offAcpClientintoGooseAcpClient, so theclient_class.pyandtest_acp_mcp_startable.pyconflicts keep main's move and re-add only this PR's Antigravity lines (the version check binding, and Antigravity's own MCP array in the startable test's per-backend map); one table inagent-host-contract.mdkeeps main's rows plus the Antigravity cell. The patch's added and removed line counts are unchanged. f59827b was one commit on main 2e56b3b: 4dd8455 rebased, plus the two GPT 6.1 findings on it and one CI fix. #37484 moved the claude-agent-acp code offAcpClientintoClaudeAcpClient, so theclient_class.py,acp_launch_capture.pyandtest_client_bindings.pyconflicts keep main's move and re-add only this PR's Antigravity lines; the two tables inagent-host-contract.mdkeep main's rows plus the Antigravity cell. Atool_callevent now names an Antigravity call for its PostToolUse spec hooks (start_event_tool_id, shared with codex), because 1.4.4's reads send no permission request: the recordedRunning view_fileisantigravity#view_file, which afs_readmatcher meets. An MCP call is named from its trusted_meta.mcppair on both events (@probe/echo_probe, not the fused titleprobe_echo_probe). The usage facade namesACP_BACKEND_ANTIGRAVITYfor type checkers. 4dd8455 was one commit on main 3397952: cda20d5 rebased, where the only conflict wastest/test_client_bindings.py, whose frozen member inventory gained main's_note_claude_adapter_versionbeside this PR's_refuse_unverified_antigravity_version; both entries are kept, and the patch's added and removed line counts are unchanged. cda20d5 was one commit on main 3887f88. On 3fdb7d4 the review lanes found that the PR's own unasked-call watch (client_unasked_watch.py,ACP_BACKEND_MUST_ASK_TOOL_KINDS) duplicated main's tripwire, so it is deleted and Antigravity uses main's; that a substring match markedDescriptionas a script argument, so every edit was refused; and that Antigravity promisedpreToolUseon every call. CI found the_dispatchfacade missing five forwarded names and Session Activity not placing Antigravity. All are fixed in cda20d5. Before that, 3fdb7d4 was 616cb8b, the signed-in capture (4f045ce, 0179f0c, 9c2f239) and therun_workflowandinvoke_subagentrefusals (9b58adc, b00a8ee5), squashed with the same tree as 1398028, then rebased onto 3887f88 with the two CI fixes below. 616cb8b is the commit reviewed as 94a0a9e, rebased onto main fe6b063, e08544c, 5e8741f, 4b820ae and bf9b611 (as 12f22c1, then amended with the watch field bound above as f065d86), then onto a104344 (as e89e2d3) and 1e990f8 (as 2d323b3), then amended to move the unasked-call tripwire into its own module (as a95e158), amended to bound Antigravity's MCP identity (below), rebased onto bab2387 (as 3041371), onto 3535135 (as 63a5da4), onto df553b0 (as cc5739e), onto a398062 (as 6c46cdb), onto b358303 (as 153e78a), onto 3c7981d (as 16d11ce), onto b4b8a01 (as 9386ca2), onto a496a7d (as 75347f2), onto baf55ed (as f2cd8c4), onto b7b7b6c (as b4e6fb9, then amended for CI as 650551b) onto 35dc109 (as 4ffb5fa) onto 45227df (as 64b35ca) onto 478d13a (as 2adf1d2), onto 06d61fe (as a7eceac), onto 1bccaa1 (as d9367bf), onto 048700a (as 460ab00) then onto fbf08dd and de6219e (as 7810a68), onto b3f274d (as b4674eb), onto 9e9de7b (as 62e9656), onto 2cd247a (as 019eaf7), onto 0842788 and 5dc219c (as b7be5a8) and onto 2a8daa3 (as 77f10af7, then amended to complete a test table, below, as 36d3aa60), onto c000f31 (as 56c81aa), onto 911bde8 (as a6bbabe), onto f9ebf3a (as d17eec5) and onto d9840be (as 616cb8b). Each rebase except the one onto c000f31 hit conflicts. #30131 changed one row of the section 5 MCP table and #30237 rewrote the spec-hooks paragraph, both indocs/system-specs/modules/agent-host-contract.md. #30108 added atoolsSettingsshell and write allowlist row to the backend table there, and touchedclient_lifecycle.py(docstring),client_permissions.py(imports),test_slash_command_no_channel.py(imports) andtest_tools_settings_notice.py(backend lists). #30086 added a Claude tool table and import toacp/harness_tool_names.py, next to this PR's Antigravity tables, and changed the CC cells of two rows of the harness tool-names table. Each of those resolutions keeps upstream's text and re-applies only this PR's change: the Antigravity table cells (on #30108's new row the cell is "not applied", because Crew enforces those allowlists only for Claude), antigravity in the two spec-hooks backend lists, and the union of both sides in the code and test files. On bab2387, #31812 changed the kiro-clisign_in_remedycell of the host identity table inagent-host-contract.md(sign in, then send the message again), and #31571 rewrote theplace_single_binary_arraydocstring inproviders/mirrors/opencode.pyto cover every single-binary harness. Both resolutions keep main's text: the table keeps this PR's Antigravity column, and the PR no longer changesopencode.py. On 3535135, #32666 changed the Codex cells of the section 6 "Quota API" and "Consumer surface" rows (Codex's 5-hour and weekly windows, read from its own rollout logs), and #32600 changed the section 9 row for MCP servers the spec declares (the Kerberos and ssh-agent pointers relayed to servers). Those resolutions keep main's text in the three rows and re-apply only this PR's existing change to them: the Antigravity cells, and in "Quota API" the shorter kiro-cli cell this PR already had. No other file conflicted, and every other file's patch is unchanged from 3041371. On df553b0, #30937 changedfs_writetowrite(kiro-cli's own name for it) in the spec-hooks paragraph, the same line where this PR adds antigravity to two backend lists. The resolution keeps both changes, and no other file's patch changed. On a398062, #29509 added threecrewmate_harness_*keys toagentBackendTabinen.jsonand the pseudo-locale, beside this PR'santigravitykey inen-XA.json. The resolution keeps both, in the order the pseudo-locale generator writes them (en.jsonkeys, thenen.manual.jsonkeys), and every file's added and removed lines are unchanged. On b358303, three files conflicted, each only beside this PR's lines: inacp-client.mdthe claude launch bullet (KIROCREW_NODE_BIN_DIR) next to the antigravity bullet this PR adds; inagent-host-contract.mdthe Readiness probe row of the entitlement table, where #32970 renamed the enterprise build to the LTS build; and inen-XA.json#32849's newagentBackendTabcard summary keys next toantigravity. Each resolution keeps main's text and re-adds only this PR's lines (the antigravity bullet, the Antigravity cells, theantigravitykey in generator order). The Readiness probe row is the only added or removed line that changed, picking up main's LTS wording. On 3c7981d, #33189 added cron-turn sentences to the spec-hooks paragraph, the same line where this PR adds antigravity to two backend lists; the resolution keeps both, and no added or removed line of the patch changed except that paragraph, which now carries main's new sentences. On b4b8a01, #34472 raised the Strands CLI pin from 0.2.3 to 0.2.4, which changed the Strands cell of the "Failure mode when missing" row of the section 8 table inagent-host-contract.md; the resolution keeps main's row and re-adds only this PR's Antigravity cell, and that row is the only added or removed line of the patch that changed. Antigravity stays out of main's newACP_BACKENDS_CREW_OAUTH_BRIDGE: each member there cites a live capture, and this PR has none for the bridge. On a496a7d, #33510 added a sentence on KASaskgrants (kas_hook_coverage.hook_held_grants) to the spec-hooks paragraph, the same line where this PR adds antigravity to two backend lists; the resolution keeps both, and that paragraph is the only added or removed line of the patch that changed. #33510 also passesgovernance_appto every harness'ssession_extras; the Antigravity harness inherits the base method, which takes it. On baf55ed, #34328 gave~/.ssh/known_hostsback read-only to every enforced harness throughtool_gate.adapter_expose_files, changed the "Extra hidden paths" row of the sandbox table inagent-host-contract.md, and added a test that every enforced harness's launch module calls that function. Antigravity is enforced, so its launch now passesextra_expose_files=acp_tool_gate.adapter_expose_files(self.backend, hidden), the same line #34328 added for goose, and its "Extra hidden paths" cell saysknown_hostscomes back read-only. The table conflict was resolved row by row: main's "Extra hidden paths" row plus the Antigravity cell, and this PR's rows where main changed nothing. That row and the twoantigravity.pylines (the import and the argument) are the only added or removed lines of the patch that changed. On b7b7b6c, #34333 made every harness that signs in with its own credential file say that its sign-in runs in a terminal on the gateway host, followed byhost_auth.HOST_TERMINAL_NOTE(where the dashboard opens such a terminal), and added a test over every such declaration. Antigravity's declaration is one, so itssign_in_remedyandsigned_out_messagenow say the same, and itssign_in_remedycell inagent-host-contract.mdstarts with "in a terminal on the gateway host". The table conflict was again resolved row by row: main'ssign_in_remedyrow plus the Antigravity cell. That row and the two Antigravity sign-in texts inhost_auth.pyare the only added or removed lines of the patch that changed. CI on b4e6fb9 then failedtest_spec_hook_kiro_cli_payload.py::test_every_native_tool_of_every_harness_gets_its_kiro_cli_name(added by #30937): this PR listed Antigravity'sfind_fileandsearch_directoryunder bothfs_readandglob, and the first row decides the built-in a spec hook's stdin names, so theglobrows came out as kiro-cli'sread. They are now underglobonly, kiro-cli's own file finder (payload tagsreadand@builtin), as no other harness table lists a tool under two rows;test_acp_antigravity_backendasserts the new first name, and that is the amend to 650551b. The other CI failure on b4e6fb9,test_session_markdown.py::test_a_condition_one_opener_is_closed_as_the_parser_reads_it[long-s], is #34654 (markdown-it-py 4.3.0 no longer reads<ſcript>as a script block), not this PR. The rebase onto 35dc109 conflicted only with #33215: it addedtest/test_kas_subagent_targets.pyto the first cell of the section 5web_searchanduse_subagentrow and rewrote the KAS cell of the section 1 "Selection mechanism" row inagent-host-contract.md, and it added a KAS sub-agent paragraph toagent-spec-fields.mdjust before the mirrored-harnesses bullet this PR rewrites. The resolution keeps upstream's text and re-adds only the Antigravity cells and that bullet; those two rows are the only added or removed lines of the patch that changed, and the file set is the same. #33215 otherwise changes KAS and the shared runtime (kiro-cli, KAS and Codex), which Antigravity does not run on, #33595 changes MCP gateway, doctor and dashboard-notice code, and no test main added since b7b7b6c iterates over every harness. The rebase onto 45227df conflicted only with #34367, which added a sentence aboutkirocrew chatasking the spec's ownpreToolUsehooks to theagent-host-contract.mdparagraph where this PR adds Antigravity to theACP_BACKENDS_CREW_FIRES_SPEC_HOOKSlist; the resolution keeps that sentence and this PR's list, and that paragraph is the only added or removed line of the patch that changed. #34367 changeskirocrew chatand its channel gate, not harness code, and its new tests are KAS-only. The rebase onto 478d13a conflicted only with #34668, which renamed the KAS Settings path in the section 3sign_in_remedyrow ofagent-host-contract.md("Settings → Agent Harness → Kiro Agent → Kiro sign-in"), the row where this PR adds the Antigravity cell; the resolution keeps upstream's row and re-adds only that cell, and that row is the only added or removed line of the patch that changed. #34668 also changes_KAS_CARDinhost_auth.pyand adds a KAS-onlykas_in_useflag toacpBackend.ts, both of which merge with this PR's edits to those files without conflict; its test changes are KAS-only. The locale files main changed alongside this PR still parse, with no duplicate key. On 64b35ca and on 2adf1d2, the first Fork PR Description and PR Readiness runs found the description complete but could not post their result, because the repository bot's GitHub API rate limit was spent ("API rate limit exceeded for installation"); both re-run when the description is edited. On a7eceac and on 460ab00, Fork PR Description passed, and the first two PR Readiness runs stopped on the same spent limit before they could post a verdict. The rebase onto 06d61fe conflicted only in two rows ofagent-host-contract.md, and each resolution keeps upstream's row and re-adds only the Antigravity cell; those two rows are the only added or removed lines of the patch that changed. #34555 added to the CC cell of the section 10 slash-commands row (/context,/help,/agent...) that the/menu also lists what the chat's session advertised; the menu keeps that list only forACP_BACKENDS_HARNESS_OWNED_SLASH_COMMANDS(Claude alone), so Antigravity's cell (only/planand/usagereach the harness) stands, and its three newAcpClientmembers, whichtest_client_bindings.pylists beside this PR's five, share no name with them. #34475 added to the CC cell of the hook and deny-rule tool-name row that a crewmate worker's native-tool excludes ride an allow-list; its newACP_BACKENDS_MATE_WORKER_NATIVE_TOOL_LIMITSholds KAS and Claude only, Antigravity is in no mate-worker set (a worker is refused there before spawn,ACP_BACKENDS_MATE_WORKER_KIT), and the Antigravity mirror'sSessionProjectionleaves the newbuiltin_toolsfield at its default of None. Of the harness code, main changed onlyacp/harness/kas.pysince 478d13a, its only new backend set is #34475's, and the new real-adapter MCP probe (test_real_adapter_harness_probe.py) runs only the backends itsexpectations.jsonmeasured, which does not include Antigravity. The rebase onto 1bccaa1, 241 commits later, conflicted only inagent-host-contract.md. #35278 (the KAS cell of the section 1 selection-mechanism row), #29221 (the Codex cell of the section 8 additional-runtime row) and #34696 (the Codex cell of the section 10 slash-commands row) changed rows to which this PR only appends the Antigravity cell, so each resolution keeps upstream's row and re-adds that cell. #35268 added a section 10 row on a shipped agent's job tools staying out of tool-search deferral; its Antigravity cell readsunknown, as for every harness but KAS and kiro-cli, because the Antigravity code has no tool-search path and no signed-in capture. #34736 rewrote the cron sentence of the KAS spec-hooks paragraph, and a word-level merge keeps it beside this PR's twoantigravitylist entries, which share no word with it. Those rows and that paragraph are the only added or removed lines of the patch that changed; every other file main changed beside this PR took the PR's lines unchanged. Main's newACP_BACKENDS_CHAT_RUNTIME_SHARING(kiro-cli and KAS) andACP_BACKEND_PROMPT_HANDLER_COMMANDS(Codex) do not include Antigravity, #35278's new harness seamstart_mode_ran_servershas a base default, the two launch helpers the Antigravity harness calls (_run_preflight_bounded,_sandbox_preflight) are unchanged, and everykiro_crewname the PR's Python files import resolves on the new main. The rebase onto 048700a conflicted only in the section 8 failure-mode row, whose Codex cell #35485 extended with thekirocrew doctorrow; the resolution keeps upstream's row and re-adds the Antigravity cell. #35637's newACP_BACKENDS_CREW_LOADS_SPEC_STEERING(Claude and Codex) andACP_BACKENDS_NATIVE_PROJECT_AGENTS_MD(Codex) leave Antigravity out, which matches its mirror'swithheldruling onresources. The rebase onto fbf08dd conflicted in six Python files andagent-host-contract.md, all from #31950, which fires a spec's non-gating hooks on Codex sessions. #31950 passes the backend to the session-update parser asharness_backend, adds a Codex tool table and reads a frame's tool name throughstated_harness_tool_name. This PR had passed the same value asbackendinsession_update_parser.pyandsession_handle_dispatch.py; the resolution keeps main's code, so neither file is in the patch any more (92 files), andstated_harness_tool_namehands the backend on toharness_tool_name, so Antigravity'sRun <name>?title is still unwrapped on Antigravity only.harness_tool_names.pykeeps the Codex table and the Antigravity table side by side, both inHARNESS_TOOL_TABLES, and the two Antigravity test calls to the parser now useharness_backend=. #31950 also filled the Codex cell of the section 10 row on hook matchers written in kiro-cli tool names and changed the first and Codex cells of the row on a spec's own hooks, rows to which this PR only appends the Antigravity cell, so each resolution keeps upstream's row and re-adds that cell; its new Codex sentences in the spec-hooks paragraph share no word with this PR's twoantigravityentries. Antigravity was already inACP_BACKENDS_CREW_FIRES_SPEC_OBSERVER_HOOKSthroughACP_BACKENDS_CREW_FIRES_SPEC_HOOKS, #31950's new tool-id reader in the parser runs on Codex only, and everykiro_crewname the PR's Python files import resolves on de6219e. The rebase onto de6219e conflicted only inclient_permissions.py, where #29127 now reads the permission value throughpermission_value_for, which prefers a value the adapter advertises; its one preferred row is Codex'sexternal-sandbox, so Antigravity writes the same value as before, and the resolution keeps the Antigravity version check ahead of both calls. The rebase onto b3f274d conflicted only in the section 2 session-persistence table, where #35260 rewrote the Codex cells of the replay-store, store-root and directory-naming rows; the resolution keeps upstream's rows and re-adds the Antigravity cell. #35260's new harness seamdelete_disposable_recorddefaults to None, and #34763's newACP_BACKENDS_TOOL_SILENCE_TIMERholds kiro-cli and KAS only, so neither reaches Antigravity. The rebase onto 9e9de7b conflicted inagent-host-contract.mdandacp/client_lifecycle.py. #33578, which runs a trusted folder agent's own hooks on KAS, changed the KAS cell of the section 5 delivery-channel row, to which this PR only appends the Antigravity cell, and the KAS sentence of the spec-hooks paragraph, which shares no word with this PR's twoantigravityentries; each resolution keeps upstream's text. In_reset_state, #35698 now forgets the pictures a session already sent and this PR clears the unasked-call watch, so the resolution keeps both lines. #35698's newACP_BACKENDS_SENT_IMAGE_RECORDholds kiro-cli, KAS, Claude and Codex only, so Antigravity inlines pictures as before. The rebase onto 2cd247a conflicted only in the section 10 row on a spec with"tools": [], where #35508, which refuses Codex permission requests on such a spec, changed the first and Codex cells; the resolution keeps upstream's row and re-adds the Antigravity cell. #35508 changes only Codex's runtime session handle and leavesACP_BACKENDS_HONOR_ZERO_TOOL_BANas it was, so the Antigravity cell still holds. The rebase onto 0842788 conflicted only in the re-export lists ofacp/types.pyandacp_backends.py, where #35756 addsACP_BACKENDS_COMPACTION_REPORTEDbeside this PR'sACP_BACKENDS_CONFIG_MODEL_SELECT_IS_CANONICAL; the resolution keeps both names in order. That set isACP_BACKENDS_SENT_IMAGE_RECORD(kiro-cli, KAS, Claude and Codex), so Antigravity, outside it, is sent the reply-format rules on every message, as every other harness outside it is. The rebase onto 5dc219c met #24732, which onboards MiMo Code as an enforced backend and adds it at most of the places this PR adds Antigravity: 11 Python files and four docs conflicted, each where both sides add lines at the same spot. Each resolution keeps main's MiMo Code lines and this PR's Antigravity lines side by side (backend ids and sets, routing, models, host-auth declarations, the tool tables inharness_tool_names.py, theclient_class.pybindings,test_agent_sdk_capabilities.pyand_MCP_SEAM_HOOKSintest_harness_parity.py). In theagent-host-contract.mdtables main's MiMo Code column stays after OpenCode and the Antigravity column stays last, and the opening counts now include both (eleven backends, nine foreign hosts). #24732 also gave MiMo Code a provider label inacp/types.py, whose label block this PR moves toacp/provider_labels.py;PROVIDER_LABEL_MIMOCODEand itsPROVIDER_LABEL_BY_BACKENDrow now sit there with the others, andacp/types.pystill re-exports it. Seven section 10 rows in which main's MiMo Code cell and this PR's Antigravity cell hold the same text (unknownor agap) had merged without a conflict but one cell short; they now carry both cells. MiMo Code's newACP_BACKENDS_UNASKED_NATIVE_TOOLS,HARNESS_UNASKED_TOOL_IDSandHARNESS_PARAM_ALIASEShold MiMo Code only, and its unasked-call tripwire inclient_permissions.pyand this PR's unasked-call watch inclient_unasked_watch.py(ACP_BACKEND_MUST_ASK_TOOL_KINDS, Antigravity only) each run on their own backend. Every capability set and backend-keyed table holds the same backends other than Antigravity as on main, and the only added or removed Python lines of the patch that changed are the MiMo Code provider-label lines (moved with the block) and"mimocode"in_MCP_SEAM_HOOKS. The rebase onto 2a8daa3 met #36462: the client now keeps the process adapter for the life of the process and asks it for the host's ownsession/new/session/loadentries (ProcessAdapter.session_mcp_servers, read through one_adapter_session_mcp_serverssplice) instead of one gated splice per harness. This PR's three Antigravity splices inclient_start.pyare therefore gone:AntigravityLaunchoverridessession_mcp_serversto returnsession._antigravity_session_mcp_servers()and callssuper().__init__()for the adapter's newread_back, theProcessSessionprotocol inacp/harness/base.pynames the Antigravity hook beside the others, and_ADAPTER_MCP_SEAMSintest_harness_parity.pydeclaresAntigravityLaunch. Theacp-client.mdadapter row keeps main's new text with this PR's file list (Antigravity and Copilot added). A check after that rebase found thatCOMPACTION_SEENintest_reply_format_once.py(from #35756), which must name every selectable harness, did not list Antigravity, sotest_the_table_names_every_selectable_harnesscould not pass on b7be5a8; it now lists Antigravity asFalse, since Antigravity is outsideACP_BACKENDS_COMPACTION_REPORTED. Withacp/harness/base.pyand that test, the patch touches 94 files. The rebase onto c000f31 had no conflict and leaves the patch unchanged (samegit patch-id). #36579 there addstest_every_value_crew_writes_reads_back_as_no_drift, which reads everyACP_BACKEND_FORBIDDEN_MODESrow, Antigravity's included: Crew writesmode=defaultwith or without the option advertised, andsession_config_drift_issuereads that back as no drift. The rebase onto 911bde8 conflicted in oneagent-host-contract.mdparagraph, the one on the spec'shooksfield, where #36829 rewrote the sentence on a checkout's own hook files (the chat now shows that notice once); the resolution keeps main's sentence and this PR's two Antigravity mentions in that paragraph (theACP_BACKENDS_CREW_FIRES_SPEC_HOOKSmembers and the spec-key notice). #36550's newACP_BACKENDS_CWD_BOUND_SESSIONSholds opencode only, and Antigravity is not added to it: nothing measured shows that itssession/loadties a session to the folder it was created in. Apart from that paragraph, the patch's added and removed lines are the same as 56c81aa's. The rebase onto f9ebf3a conflicted in the same paragraph, where #36955 adds a sentence (the other session-start spec notices now show once per chat too); it was resolved the same way, main's text with this PR's two Antigravity mentions, and the patch's other lines are unchanged. #36983 now rulesautoApprovewithheld on a broker-only harness (pi), as every mirror already does; Antigravity is a mirror, and its card already listsautoApproveas not taking effect. The rebase onto d9840be conflicted in two places, both from #37105: it updated the Pi cell of the section 8 "Failure mode when missing" row (PI_MIN_VERSIONis now 0.99.2), and it dropped theharness-parity.mdintro sentence aboutsession_pid_orphan_scan.py::_BROWSER_PLAUSIBLE_OWNER_NAMES, a set main no longer has. Each was resolved to main's text with the Antigravity column or name kept. #36993 now names a dropped remote MCPoauthblock at session start on every harness outsideACP_BACKENDS_REMOTE_MCP_OAUTH, which includes Antigravity; section 10 already lists that sign-in as a gap for Antigravity. The rebase onto 3887f88 conflicted in three files. #36118 added Copilot toACP_BACKENDS_MODEL_VIA_CONFIG_OPTIONbeside this PR's Antigravity line, and #36083 rewrote the kiro-cli and KAS rows ofNATIVE_ALLOW_STORES_NONEbeside this PR's Antigravity row; both resolutions keep main's lines and this PR's. Inagent-host-contract.md#36118 changed the Copilot cell of two rows, "Entitlement discovery, model side" and "The model picker lists the harness's models"; both tables conflicted whole because this PR appends the Antigravity column to every row. Every row now holds main's text plus this PR's Antigravity cell, and every data row of the PR matched its base row except for that cell. The patch's added and removed line counts are unchanged. Two CI findings on 1398028 are fixed in the same push: the portability gate read the newis_shell = Trueas a subprocessshell=True, so the branch now assigns the computed flag, and a test query spelled the product name in lower case.#30616 then made Crew expand
${VAR}and${env:VAR}in the shared session projection, which the Antigravity mirror uses. The Antigravity cell of the section 5 "Env expansion" row therefore changes from "literal pairs, not measured" to: Crew expands both forms before the element is built; whether Antigravity writes the array anywhere itself is not measured.test_session_mcp_env_refs.pynow lists Antigravity among the expanding backends (4 new cases: the three value spellings resolve, and a credential-named variable is never dereferenced).git range-diffshows no other change.#30874 then added a sentence to the KAS cell of the section 5 "Per-tool MCP deny" row in
agent-host-contract.md(the switched-off tools the dashboard writes to the globalmcp.json), the row where this PR adds the Antigravity cell. The resolution keeps upstream's row and re-adds only the Antigravity cell;git range-diff f065d86e e89e2d36shows no other change. #30874 changes only KAS code, so Antigravity's behaviour is unchanged.#30308 then reworded the CC cells of the section 7 "Auto mode" and "Inherited-config hazard" rows in
agent-host-contract.md, and the claude bullet inacp-client.mdthat the Antigravity launch bullet follows. The resolution keeps upstream's text and re-adds only the Antigravity cells and bullet;git range-diff e89e2d36 2d323b3fshows no other change, and the PR's other 90 file patches are identical. #31016 giveskirocrew-corean agent-socket pickup under an enforced harness. Antigravity's routing (SESSION_CONFIG) is enforced, so its session array gets the pickup with no change here; checked locally, its credential mask leaves the agent socket reachable and keepsrun/and.local_secrethidden, and onlykirocrew-corereceives a pickup. Whether the Antigravity runtime hands that element'senvto the stdio server unchanged has not been measured (the signed-in capture did not test it).f065d86 differs from 12f22c1 in two things. The watch bound answers the fork AI review's blocking finding on 12f22c1 (
a-bound-bounds-every-field-it-retains): it changesclient_permissions.pyand the Antigravity cell of the host contract, and adds 11 cases totest_acp_antigravity_backend.py. Thehost_auth.pycomment now records the maintainer's acceptance of the own-token exclusion. The new cases cover a must-ask call with an over-long id (stated, asked first, MCP-marked, relabelled fromread), an id of exactly 512 characters, an over-long id that can never trip, a 1 MiBkind, and the overflow row beside an over-long id. Six of the 11 fail on 12f22c1's code; the other five pin behaviour the bound must not change.a95e158 differs from 2d323b3 only in where the unasked-call tripwire lives.
UNASKED_WATCH_LIMIT,_watched_kind,_watch_tool_calland_tripwire_unasked_callmove unchanged fromacp/client_permissions.pyinto a new owner module,acp/client_unasked_watch.py, whichAcpClientbinds like its other owners and_CLIENT_OWNERSlists.client_permissions.pyis now 1,469 lines (1,456 at base), under the 1,600-line working target thatcheck_file_line_cap.pyreports (#30770). The binding inventory intest_client_bindings.pyrecords the new owner of the two methods, theacp-client.mdowner table and the Antigravity cell of the host contract name the new file, the watch-limit tests import the limit from it, and the id-log scan intest_deny_bounded_write.pyand the redact-before-bound scan, which covered this code inclient_permissions.py, now list it too.Since a95e158, the PR also bounds Antigravity's MCP identity. This answers the fork AI review's blocking finding on a95e158 (
a-bound-bounds-every-field-it-retains, at the_meta.mcprow inacp/_dispatch_parts/tool_call_identity.py).AcpClientcached atool_callframe's_meta.mcp.serverand_meta.mcp.toolper open call as sent, so 256 open calls naming a 1 MiB tool held 256 MiB. That row of_MCP_IDENTITY_META_CHANNELSis now bounded like the KAS row, by the 512-character bound of Crew's own MCP tool surface (mcp_identity_name). A half over the bound is never cut: it is retained as empty and reported unreadable. For Antigravity,AcpClientrecords that mark per call (a later readabletool_callunder the same id clears it, as it rewrites the identity caches), and_build_permission_eventsetsmcp_identity_unreadableon that call's permission event, which the gate already refuses on every path (gate_tiers,_resolve_permissionand the auto-approve floor). The client sets the flag itself rather than handing the mark to the shared parser as its unreadable store, because that store also turns on the KAS built-in id fold. A newrequires_serverfield keeps the KAS row's server-present rule on that row alone, so a frame naming only an oversized tool is bounded too, andclassify_tool_callno longer reads the codexrawInputpair for a frame a bounded channel marked unreadable: Antigravity stampsis_mcp_tool_callbeside_meta.mcp, and itsrawInputholds the tool's own arguments. No other client records the mark, and the kiro-cli, goose and codex channels and KAS's behaviour are unchanged.test_acp_antigravity_backend.pygains 12 cases (an oversized tool, server, both or tool-only half, each with and without the MCP marker; 512-character names kept; the mark cleared by a later readable frame; no mark on goose or opencode), and the channel pin intest_tool_call_classification_kas.pynow lists the Antigravity row as bounded. Each of the five parts of the fix was reverted in turn, and each revert fails at least one new case.client_permissions.pyis 1,477 lines.On 2d323b3, targeted tests were run on a Windows laptop (
-n 8) over 200 files: the same selection as on e89e2d3 (the PR's test files plus the test files of #30086, #30108, #30237, #30616, #30670, #30674, #30241 and #29882,test_strands_mirror,test_tools_settings_noticeandtest_slash_command_no_channel; every test file main changed between bf9b611 and a104344; every test that readsbackend_installor the KAS bundle route; and the host-contract parity, file line cap, host auth, tool gate, harness contract, crewmate harness and KAS disabled-tools tests), plus the test files of #30308 and #31016, and withouttest_slack_code_channel_workspace.py, whose git-subprocess tests timed out under the parallel load on that machine; neither this PR nor main has changed that file since a104344. 11,879 passed, 220 skipped, 1 xfailed, 35 failed and 8 errors. Each failure, and the collection error behind the 8 errors, was rerun alone at base 1e990f8 and at 2d323b3. 30 fail at both: five Copilot tool-gate tests and twotest_pid_lifecyclereclaim tests that fail on that host, five tests that need symlink privilege (WinError 1314), 15test_decisions_sagemaker_providertests, twotest_app_update_swap_leftoverscases, andtest_sandbox_argv_launcher_plan, which callsos.geteuidand does not collect on Windows. The other six (test_memory_no_regression,test_dashboard_approval_modes,test_browser_harness_supervisorandtest_dashboard_server_composition_contract_reach) pass alone at both commits; they failed on file-lock and timing errors under the load. None fails only at 2d323b3. On a95e158, the tests for the move (21 files, among them the client binding and facade tests,test_acp_antigravity_backend, the tool gate, harness contract, harness parity, host-contract parity and file line cap tests, the log, redaction and security posture scans, and the Copilot, DeepSeek, pi, goose and Claude permission tests) gave 2,657 passed, 7 skipped and 5 failed, the same five Copilot tool-gate tests that fail on that host at base. Before the rebase, with the MCP identity bound applied on a95e158, the tests for the bound (93 files: the 21 files for the move, every test file that reads the MCP identity channels, tool-call classification or permission-event code, the ACP frame tests, and the hooks and MCP tool surface tests) gave 7,126 passed, 424 skipped, 6 xfailed and 9 failed, and all 9 also fail alone at a95e158: the five Copilot tool-gate tests, a symlink-privilege test (WinError 1314), the protected-process case oftest_platform_compat_windows_tree, the priming case oftest_acp_client_stale_turnand the KASrun_commandcase oftest_side_readonly_kas. On 3041371, after the rebase onto bab2387, those 93 files plus the PR's test files and the 145 test files main changed since 1e990f8 that read the ACP client, backend, host auth, harness parity or mirror code (235 files) gave 16,079 passed, 837 skipped, 9 xfailed and 13 failed. All 13 also fail alone at bab2387: the same nine, two more Copilot cases intest_acp_launch_goldens, and the twotest_pid_lifecyclereclaim tests that fail on that host. 2d323b3 also merges without conflicts onto main 665a0e4; on that local merge, the PR's test files plus the host-contract parity, file line cap, sandbox governance mask, harness contract, tool gate, host auth, agent-socket and harness parity tests (28 files) gave 2,948 passed, 310 skipped and 7 failed, the same five Copilot and twotest_pid_lifecyclehost failures. On e89e2d3 the 197-file selection gave 11,915 passed, 197 skipped and 31 failed, all 31 also failing at base a104344, and on f065d86 the 45-file part gave 3,132 passed, 42 skipped and 7 failed, all 7 also failing at base. black, isort and flake8 pass on the 65 Python files the PR changes at 3041371, and mypy ontool_call_identity.py,client_tool_events.py,client_permissions.py,client_unasked_watch.py,client_class.pyandclient.py. On 650551b,check_harness_parity.py(--testand plain),docs_lint.py(--testand plain),gen-pseudolocale.mjs --checkand five targeted test files (test_acp_harness_contract.py,test_acp_tool_gate.py,test_acp_antigravity_backend.py,test_agent_sdk_host_auth.pyandtest_spec_hook_kiro_cli_payload.py,-n 4) were run on a Windows laptop. The checks pass; the tests gave 805 passed and 2 failed, both Copilot cases refused because that laptop has a.mcp.jsonabove pytest's temp folder (copilot_repo_config_issuechecks every parent folder), which this PR does not touch. 616cb8b's patch differs from 650551b's only in the two #33215 rows, the #34367 paragraph, the #34668 row, the #34555 and #34475 rows and the #35278, #29221, #34696, #35268, #34736, #35485, #31950, #35260, #33578, #35508, #35756, #24732 and #36462, #36829, #36955 and #37105 changes and theCOMPACTION_SEENrow above. 650551b's patch differs from 3041371's only inagent-host-contract.md, the two lines inacp/harness/antigravity.pythat wire upadapter_expose_files, the Antigravity sign-in texts inagent_sdk/host_auth.py, and thefind_file/search_directoryrows inacp/harness_tool_names.pywith their assertion intest_acp_antigravity_backend.py. CI on b4e6fb9 finished backend shards 1 to 4 on Linux and Windows: shards 2 and 3 passed, and shards 1 and 4 each failed only the one test named above; shards 5 to 8 were still running when 650551b replaced it.Full run on 6167f32 (an earlier head, base 4b820ae; its diff against its base differs from 3041371's only by the #30616, #30874, #30308, #31812 and #31571 resolutions, the watch bound, the tripwire's move to its own module, the MCP identity bound and the
host_auth.pycomment above, while main itself moved from 4b820ae to bab2387), on Linux (x86_64, Python 3.12.16, Node 24.22.1) with the CI commands:-n 12 --timeout=120 -m "not ipv6_required and not real_venv"): 248,856 passed, 24 failed. Every failure was rerun alone at head and at base 4b820ae and fails at both (at base the generated UI index test ran only oncewebsite/node_moduleswas provided, since without it the test skips; it then fails the same assertion as at head): the test host's timezone data is out of date, sodoctorexits 1 (the 10doctoranddoctor stttests), it lacks ripgrep (the two file_grep engine tests),/usr/bin/sleepthere is a shebang script (process identity), the gateway-lock fork-orphan and process-tree kill tests depend on the host, five app install and registry tests fail on base's undefinedwas_installedinapps/routes_registry.py, and a few tests already fail upstream (ops_mission_control GitHub truncation, ci_kernel_owner_routing junit, the generated UI index "Continue with GitHub" breadcrumb, the grep sensitive-glob derivation).docs_lint.py --testanddocs-lint.sh) pass. flake8 and mypy report only the same undefinedwas_installedinapps/routes_registry.py, identically at base 4b820ae; this PR does not touch that file.websiteandwebsite/electron, same run):tsc, ESLint--max-warnings 0, jscpd, the i18n new-key check and the diff-scoped render gate (both withI18N_BASE_REFresolved at base), phantom classes, the restyle ratchet,npm run build, the analyze build, bundle size, chunk cycles and the render bench (--fail-on dispatches,selectorCalls) pass. Vitest with coverage: 4,026 files, 64,347 tests passed, 1 expected fail, 0 failed. Electronnpm test: 3,237 passed, 0 failed, 4 skipped. The PR'swebsitepatch (16 files) makes the same changes in 3041371, 16d11ce, 9386ca2, 75347f2, f2cd8c4, b4e6fb9, 650551b, 4ffb5fa, 64b35ca, 2adf1d2, a7eceac, d9367bf, 460ab00, 7810a68, b4674eb, 62e9656, 019eaf7, b7be5a8, 36d3aa60, 56c81aa, a6bbabe, d17eec5 and 616cb8b (samegit patch-idat zero context lines; with default context onlyen-XA.jsondiffers, because feat(crew): a Crew bot's harness follows Settings -> Agent Harness when unset #29509's new keys now sit beside theantigravitykey)._dispatchfacade was missing the type-checking namestool_call_identityuses, and the bare_session_mcp_servers()splice broketest_strands_mirror.Not run locally: Windows and macOS CI lanes, the sandbox Sensitive Change Review, and a second signed-in Antigravity run.
Manual verification
The existing 1.4.4 live fixture records the signed-out initialize/session/load and MCP-startup exchange. One signed-in session (
turn-live-*) confirms the shell, edit, read and MCP argument names on the wire. Compatibility with 1.4.5 is not verified.Checked on Linux with the official 1.4.4 archive, signed out with an invalid API key:
initializereports version 1.4.4 and protocol 1; a server launched with Crew's spawn argv has a/proc/<pid>/cmdlineof its absolute path and one NUL, and_is_managed_agent_processaccepts that live pid; asession/newnaming a missing stdio command still creates the session and nothing reports the dropped server. The binary needs an IPv6 loopback, so it ran in a network namespace that provides one.NOT CHECKED: 1.4.5 wire behavior; an enterprise policy tenant; whether a sub-agent's own tool calls reach
session/request_permission(the capture refusedinvoke_subagent, and Crew refuses it until one shows it). Sensitive Change Review needs a maintainer-owned in-repository branch.Screenshots / video
None attached. The visible change is an Antigravity row in the backend picker and its backend card, which shows the installed, missing-executable and missing-helper states. Local captures used mocked probe data, not a signed-in session.
Related Issues
Supersedes #26171 (in-repo move; author LuisBrel).
N/A: no existing issue tracked this contribution. It continues #25980, which is closed and was not merged.
App repo: KiroCrewCaptain/kirocrew-app-aws-control#10
Checklist
Contribution License Agreement