Repository navigation
feat(acp): default new installs to KAS - #20359
Conversation
cae35d0 to
78027e9
Compare
78027e9 to
1d2a081
Compare
|
Rebased: onto main 64ece1a and folded in fixes for the head 78027e9 reds (Frontend Tests (4) |
First Principles Review (Opus 5.5) — ✅ human override accepted@iamwhatever overrode this lane for |
UX Review (Opus 5.5) — 🟡 CONCERNSUX-level review of UX-Verdict: CONCERNS Upgrading silently moves users who picked Kiro CLI over to KAS, and nothing in the product tells them their harness changed or how to switch back. Watch
Suggestions
[UX-REVIEWED] b23d5a9 Description read[DESCRIPTION-READ] 1f751825086d06823111d0c97b8f000f791b035fafba969cc8454aa27fb5be2d That sha256 names everything this verdict read: the PR description, plus the 6 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) — 🟡 CONCERNSDesign-level review of Design-Verdict: CONCERNS Upgrading silently moves every stored Watch
Suggestions
[DESIGN-REVIEWED] b23d5a9 Description read[DESCRIPTION-READ] 3bda2b4aa6f0ec57e2b7f4da0e0197b23a6c6139ec5f756b8b0d098c21f12b22 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 |
Opus 5.5 Review — ✅ human override acceptedReviewed Human judgment by @iamwhatever overrides the Opus 5.5 finding for [OPUS-OVERRIDE] b23d5a9 Verdict recorded from an authorized human decision 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: |
1d2a081 to
ece1f97
Compare
|
|
|
|
|
|
|
|
|
|
|
|
|
/ai-review override first-principles b23d5a9: agent: posted at @zejiangg's direction; making KAS the default harness (absent or "" stored value) is a decision by the org leaders, so no RFC is required. |
|
|
/ai-review override fable b23d5a9: posted at @zejiangg's direction; moving stored "" installs (including past Kiro CLI picks) to KAS, unconfined on Windows, is @zejiangg's accepted decision, documented in docs/guides/windows-install.md and the PR's Breaking lines. |
Human judgment recorded@iamwhatever marked the first-principles AI finding as false positive, not applicable, or explicitly accepted for
This decision applies only to this commit. A new push requires a new judgment. |
Human judgment recorded@iamwhatever marked the fable AI finding as false positive, not applicable, or explicitly accepted for
This decision applies only to this commit. A new push requires a new judgment. |
Problem / Motivation
Goal: Every install with no stored Kiro CLI choice uses KAS; Kiro CLI is used only when
config.jsonstores"kiro".Today
agent.acp_backend: ""means Kiro CLI, and that is also what every full save writes. So config cannot tell "the user picked Kiro CLI" apart from "the user never picked", and nearly every existing install holds"". A default change keyed on an absent key alone would leave almost all existing installs on Kiro CLI.Why it matters
KAS is the harness the org has decided every user should start on. Without a stored value that means "Kiro CLI" and nothing else, the default cannot move existing installs, and a real Kiro CLI pick cannot be told apart from no choice.
Not a goal
agent.provider, which staysacp.What changed (motivation → approach → change)
The stored harness value now has one meaning per spelling, and
""joins "absent" as "no choice":agent.acp_backend/agent.member_acp_backendon disk"""kiro"(user picked Kiro CLI)"kiro""kas","claude", ...The runtime id for Kiro CLI stays
""(ACP_BACKEND_KIRO). Only the config boundary translates.agent_sdk/backends.pyaddsSTORED_BACKEND_KIRO = "kiro"(equal to the policy id) and two helpers:backend_from_storedfor loads, andbackend_to_storedfor everything that shows or writes the setting.config/loader.pyreads both keys through_read_backend_choice.to_dict()emits the stored spelling, sokirocrew config get, the dashboard config response and the schemaenumValuesall say"kiro".save()writes both keys back exactly as the file holds them, so it never invents a choice and never replaces a policy-denied"kas"with the floor.config/validation.pymaps a present non-string to"kiro"with a warning.On boot,
platform/bootstrap.pyre-resolves an undeclared value as absent.knowledge/llm_pool.pyreads the stored value through the same helper. The dashboard PATCH allowlist (dashboard/handlers/core.py), the agent schema enum (dashboard/handlers/agents.py), the/api/acp-backendsrows (acp_backend_status.py) and the error text inacp/runtime.pyanddashboard/chat_runner.pyall use"kiro".acp_backends.pyre-exports the new names.validation.pyleaves.github/black-baseline.txtbecause it is now black-clean.In the website,
acpBackend.tssetsACP_BACKEND_KIRO = 'kiro', and a newconfiguredAcpBackend()reads''/absent as KAS.KiroPrerequisiteGate.tsxandAgentBackendTab.tsxfollow it: KAS is listed first and reads "Default.", Kiro CLI has no Experimental badge, and picking Kiro CLI PATCHes"kiro".config-baseline.json,configuration.md,agent-spec-fields.md,harness-parity.md(H1, H3),agent-host-contract.mdandconfig.mdstate these rules.The org leaders decided the KAS default; there is no RFC.
Backwards compatibility
Breaking: a stored
agent.acp_backend: ""oragent.member_acp_backend: ""changes meaning from Kiro CLI to "no choice", which resolves to KAS. On the base, every full save wrote"", so almost every existing install moves to KAS on upgrade. That includes users who explicitly picked Kiro CLI, because that pick was stored as the same"". They pick Kiro CLI again (stored as"kiro") to go back. This is intended.Breaking: on native Windows the default chat moves from Kiro CLI's built-in sandbox to KAS, which runs unconfined under the platform default (it can read
.awsand.ssh). Withsandbox_allow_unsandboxed_exec=falsedeclared, a KAS chat is refused with a message naming that setting. Picking Kiro CLI keeps the sandboxed path. This tradeoff is accepted by @zejiangg;docs/guides/windows-install.mdstates it, andcli_doctor.pydescribes KAS as the default.Breaking:
/api/acp-backendsrow ids and the dashboard/CLI config surfaces report Kiro CLI as"kiro"instead of"". The backend recheck still accepts"". Inside this repo only the dashboard reads these ids, and it is updated.Reader:
KiroCrewConfig.save()no longer persists an in-memory harness assignment; nothing insrc/relies on that (grep), and harness picks go through the key-level writers (config set, dashboard PATCH).Writer sweep re-run on fresh
origin/main(37fa963): no other writer ofagent.acp_backend/agent.member_acp_backendfound.Tests
test/test_acp_backend_kas.py: stored""and absent load as KAS with no warning, for both keys;"kiro"loads Kiro CLI andto_dict()returns"kiro";config set agent.acp_backend kirostores"kiro"andconfig getprints it; a fullsave()keeps the file's values; the dashboard response and PATCH speak"kiro".test/test_agent_backend_governance.py: under a KAS-denying policy, absent or""takes the floor silently on load, on a home with no config file, and on the boot re-resolve; a stored denied"kas"warns and stays"kas"aftersave(); recheck with"kiro"probes Kiro CLI.test/test_harness_parity.py: H1 default is KAS; H3 bad explicit values degrade to Kiro; the stored token equals the policy id.website/src/api/acpBackend.test.ts,website/src/test/AgentBackendTab.test.tsxandwebsite/src/test/KiroPrerequisiteGate.agentChoice.test.tsx:''/absent shows KAS in use, "Default." sits on KAS only, picking Kiro CLI PATCHes'kiro'. The other gate and harness frontend test files (17 in all) use'kiro'for a Kiro CLI pick.acp_backend: "kiro"throughpin_kiro_cli_harness()intest/chat_test_helpers.py. This coverstest_eager_spawn.py,test_cli.py,test_agent_capabilities_stop_following.py,test_crew_fired_spec_hooks.py,test_crew_log_order.py,test_dashboard_chat.py,test_dashboard_chat_turn_wiring.py,test_discord_resumed_busy.py,test_recovery_l1_chat_runner.py,test_todo_pill_resync.py,test_agent_welcome_message.py,test_manual_compact_gate.pyandtest_chat_runner_coverage.py.website/electron/test/packaging.test.js: the installer-copy pin checks thatDEFAULT_ACP_BACKENDnames KAS or Kiro and is the field default. The installer's "requires Kiro CLI" copy stays true because KAS runs over the kiro-cli ACP relay.tsc, isort, flake8, mypy, black and the comment-history gate pass.Manual verification
Rendered Settings > Agent Harness from this branch on a loopback dev server with stubbed APIs. With
agent.acp_backend: "", KAS is listed first, marked In use and reads "Default.". With"kiro", Kiro CLI is In use and reads "Kiro CLI is installed and ready to use." with no Default or Experimental label.Screenshots / video
Config holds
agent.acp_backend: ""(an existing install after upgrade, or a new install):Config holds
agent.acp_backend: "kiro"(the user picked Kiro CLI):First run on a fresh home with no
agent.acp_backendand Kiro CLI not signed in. The default resolves to KAS, so the Kiro CLI setup gate (KiroPrerequisiteGate) is not shown; the app opens straight to the dashboard and its first-run Privacy step. The gate appears only when KAS cannot start (old kiro-cli, missing agent spec, or no sandbox). A""home looks the same. Captured on an isolated loopback gateway withsandbox_allow_unsandboxed_exec: true, because the capture host cannot nest a sandbox.Related Issues
Closes #20171
Checklist
feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...)