Skip to content

feat(agent-harness): hand coding work to authorized Cloud Agent sessions - #5733

Closed
iscekic wants to merge 3 commits into
shared-agent-harness-3bb0-s22from
shared-agent-harness-3bb0-s23
Closed

feat(agent-harness): hand coding work to authorized Cloud Agent sessions#5733
iscekic wants to merge 3 commits into
shared-agent-harness-3bb0-s22from
shared-agent-harness-3bb0-s23

Conversation

@iscekic

@iscekic iscekic commented Aug 29, 2026

Copy link
Copy Markdown
Contributor

No new behavior — this change does not make new session actions available to users.


Summary

executeHarnessCloudAgent adds authorized kilo.sessions.start, kilo.sessions.continue, and kilo.sessions.stop mutations for personal and organization scopes using ordered dispatch identity.
Starts initiate automatically in code mode; continuation preserves the session's model, mode, and variant, and continuation or stop refreshes authorization before dispatch.
Authoritative admission rejections remain terminal and sanitized; uncertain ToolOutcome results retain outcome_unknown and the operation identifier instead of exposing provider details.

Files
  • apps/web/src/lib/agent-harness/cloud-agent.ts — Source, A (added), 171 insertions, no deletions; reuses the existing scoped routers and request schemas. Starts pass the requested prompt, model, and repository with stable operation and message identifiers. Validates continuation response identifiers and requires successful interruption replies; exposes only the linked Kilo session reference, never stream tickets. Preserves pre-dispatch CONFLICT errors and delegates kilo.sessions.search, kilo.sessions.attach, and kilo.sessions.progress during execution and reconciliation.

reconcileHarnessCloudAgent validates stored Reference records, ownership, scope, and session linkage; creation succeeds only with a completed ledger or nonterminal evidence plus an exact user turn.
Continuation recovery requires the exact message identifier, user role, and joined text; missing evidence, failed terminal records, and lost stop replies remain unknown.
The scheduler must execute once and reconcile without redispatch, even after ledger expiry; session allocation, idle status, or disappearance cannot prove completion.

Files
  • apps/web/src/lib/agent-harness/cloud-agent.test.ts — Test, A (added), 265 insertions, no deletions; covers both scopes, private output, admission errors, revoked membership and grants, scope mismatches, and model eligibility. Exercises preparation, admission, and response loss, ledger states, exact user turns, mismatched replies, and empty read delegation without repeated effects.

Tests: 1 test file added, cloud-agent.test.ts, with 265 insertions and no deletions.
Generated: 0 files changed.


Visual Changes

Visual Changes: N/A

Verification

This level has no reported manual tests because the adapter does not activate the harness.
Live provider verification belongs to A32 and bot-e2e.

Reviewer Notes

  • Worktree for Kilo-Org/cloud: /Users/igor/Projects/.worktrees/shared-agent-harness-3bb0.
  • Review range: shared-agent-harness-3bb0-s22...shared-agent-harness-3bb0-s23.
  • The handoff reports three passed checks: oxlint, oxfmt --check, and Jest. The mutation and consumed context suites report 122 passing tests.
  • These tests use router and authorization doubles; they do not prove live service behavior.
  • Continuous integration (CI) owns repository-wide types and builds.

Human steps: None required before merge or after merge.

Runtime verification remains pending at the stack tip. This level adds mutation adapters without activating the harness.

Stacked PRs — merge bottom to top. Each level shows only its own diff.

Runtime verification (E2E, user advocacy, simplify) runs on the tip PR over every level.
Every level keeps its own checks, its own bot review, and its own threads; each one is answered on its own PR.
Each level is its own deliverable: it builds and passes its own checks alone.
A finding on a level is repaired on that level, then carried upward with stack.sh forward.

  1. shared-agent-harness-3bb0chore(agent-harness): register workspaces and enforce CI boundaries #5632
  2. shared-agent-harness-3bb0-s2feat(agent-harness): define portable domain and snapshots #5637
  3. shared-agent-harness-3bb0-s3feat(agent-harness): define commands tools and permission policy #5639
  4. shared-agent-harness-3bb0-s4feat(agent-harness): share client state and cursor recovery #5643
  5. shared-agent-harness-3bb0-s5feat(agent-harness): persist command intents and execution receipts #5647
  6. shared-agent-harness-3bb0-s6feat(db): add harness ingress grants and retirement fences #5655
  7. shared-agent-harness-3bb0-s7feat(agent-harness): deliver legacy history and project durable text #5659
  8. shared-agent-harness-3bb0-s8feat(agent-harness): authorize durable grants and registered clients #5662
  9. shared-agent-harness-3bb0-s9feat(agent-harness): fence retirement and retry payload cleanup #5667
  10. shared-agent-harness-3bb0-s10feat(agent-harness): persist authoritative state in SQLite #5675
  11. shared-agent-harness-3bb0-s11feat(agent-harness): admit durable runs and revisioned commands #5678
  12. shared-agent-harness-3bb0-s12feat(agent-harness): recover queued runs and stream checkpointed steps #5688
  13. shared-agent-harness-3bb0-s13feat(agent-harness): resolve interactions and dispatch tools sequentially #5693
  14. shared-agent-harness-3bb0-s14feat(agent-harness): fence designated client tool execution #5697
  15. shared-agent-harness-3bb0-s15feat(agent-harness): synchronize durable snapshots and legacy history #5701
  16. shared-agent-harness-3bb0-s16feat(agent-harness): reuse authorized invitations with durable replay #5704
  17. shared-agent-harness-3bb0-s17feat(integrations): bound repository transport for harness reads #5710
  18. shared-agent-harness-3bb0-s18feat(integrations): expose bounded authorized repository reads #5714
  19. shared-agent-harness-3bb0-s19feat(agent-harness): expose named authorized resource reads #5718
  20. shared-agent-harness-3bb0-s20feat(sessions): bound history transport for harness reads #5724
  21. shared-agent-harness-3bb0-s21feat(agent-harness): read scoped Cloud Agent context and progress #5726
  22. shared-agent-harness-3bb0-s22fix(agent-harness): preserve ordered Cloud Agent dispatch identity #5731
  23. shared-agent-harness-3bb0-s23feat(agent-harness): hand coding work to authorized Cloud Agent sessions #5733 ← this PR
  24. shared-agent-harness-3bb0-s24feat(agent-harness): authorize scoped MCP gateway connections #5737
  25. shared-agent-harness-3bb0-s25feat(agent-harness): bound MCP gateway transport in the Worker #5740
  26. shared-agent-harness-3bb0-s26feat(agent-harness): execute validated remote MCP tools #5743
  27. shared-agent-harness-3bb0-s27refactor(exa): share provider dispatch and usage recording #5746
  28. shared-agent-harness-3bb0-s28feat(agent-harness): authorize bounded web provider requests #5747
  29. shared-agent-harness-3bb0-s29feat(agent-harness): normalize web sources and preserve citations #5749
  30. shared-agent-harness-3bb0-s30feat(agent-harness): define closed internal operation contracts #5753
  31. shared-agent-harness-3bb0-s31feat(agent-harness): authorize internal maintenance operations #5754
  32. shared-agent-harness-3bb0-s32feat(agent-harness): authorize named Kilo operation dispatch #5755
  33. shared-agent-harness-3bb0-s33feat(agent-harness): authorize internal provider operations #5757
  34. shared-agent-harness-3bb0-s34feat(agent-harness): secure the internal operations endpoint #5758
  35. shared-agent-harness-3bb0-s35feat(agent-harness): bound and sanitize model streams #5767
  36. shared-agent-harness-3bb0-s36feat(agent-harness): secure billed model inference #5776
  37. shared-agent-harness-3bb0-s37test(agent-harness): cover model gateway security boundaries #5777 (tip)

const prepared = basePrepareSessionNextSchema.parse({
prompt: request.arguments.prompt,
model: request.arguments.modelId,
githubRepo: request.arguments.repository,

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

WARNING: Start with no repository throws an unsanitized ZodError

kilo.sessions.start treats repository as optional, and in-repo harness fixtures omit it. This always assigns that value to githubRepo and parses basePrepareSessionNextSchema, which requires exactly one repository source. A valid start call without repository (or with a non-owner/repo value) throws a raw ZodError before dispatched is set, so it is neither a sanitized BAD_REQUEST admission nor outcome_unknown.


Reply with @kilocode-bot fix it to have Kilo Code address this issue.

@kilo-code-bot

kilo-code-bot Bot commented Aug 29, 2026

Copy link
Copy Markdown
Contributor

Code Review Summary

Status: 1 Issue Found | Recommendation: Address before merge

Overview

Severity Count
CRITICAL 0
WARNING 1
SUGGESTION 0
Issue Details (click to expand)

WARNING

File Line Issue
apps/web/src/lib/agent-harness/cloud-agent.ts 85 Start with no repository throws an unsanitized ZodError
Files Reviewed (2 files)
  • apps/web/src/lib/agent-harness/cloud-agent.ts - 1 issue
  • apps/web/src/lib/agent-harness/cloud-agent.test.ts - 0 issues

Fix these issues in Kilo Cloud


Reviewed by grok-4.6 · Input: 472.4K · Output: 28.7K · Cached: 1.5M

Review guidance: REVIEW.md from base branch shared-agent-harness-3bb0-s22

This was referenced Aug 29, 2026
@iscekic

iscekic commented Aug 31, 2026

Copy link
Copy Markdown
Contributor Author

Closing: the owner stopped this workflow section. The branch is retained.

@iscekic iscekic closed this Aug 31, 2026
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.

1 participant