[jamesbxwu]

Creating a session or memory store directly through the CLI or AgentKit SDK currently surfaces a bare PERMISSION_DENIED, while deploy already adds Lakebase permission guidance. The existing deploy guidance also recommends the removed --no-create-stores flag.

Share the creation diagnostic at the API transport boundary so all three paths explain how to check Lakebase project permissions. Creation and existing-store access errors now point to the current agentbricks memory bind or agentbricks sessions bind command. The hint describes Lakebase policy as a possible cause rather than inferring it from every permission denial.

Validation: reproduced both missing creation hints before the change; 148 client, deployment, error-rendering, memory CLI, and sessions CLI tests pass. Ruff and type checks pass. No live restricted-user policy was changed or tested.

Jira: ML-69282. Also refreshes stale recovery guidance related to ML-69292.

CI framework limitation: the only failing test cases are the six memory-backed test_history_orders_parallel_pending_messages variants, with pending-write order ["first", "last"] instead of ["last", "first"]. The identical six cases also fail on base commit a8d55f4 in main run 38662891535. They are pre-existing; no skips or forced passes were applied.

Bug-bash integration validation

The test-only combined branch at be2fa8ee8d6d3b3e011ecfa285e6455b90f9433a contains this exact PR head and eleven other reviewed heads. Its Agent Bricks unit suite passed 2,154 tests, 24 skipped. This is combined-source validation, not an isolated run of this PR; the branch must not be merged into main.

Private run 38698567494 passed all 20 live Claude cache tests at e231ca2 (OpenAI 8, LangGraph 4, generated adapters 8). Run 38701390693 at 53f9db8 passed OpenAI 8, LangGraph 4 and 3 adapter cases; the remaining 5 adapter cases returned HTTP403 because the shared test-workspace Gateway budget reached its $10 limit. Production source is identical across those runs and the final combined source; later changes affect only matrix fixtures, cleanup, regression tests and documentation. The rerun is not all green, and no budgets were changed.

The corrected Apps test passed 20/20 matrix rows, two grant snapshots, transitive-permission controls and repeat-deploy idempotency. Its evidence confirms clean source and wheel/source matching. That live run predates the final cleanup correction: the harness recorded twelve successful cleanup operations but omitted the implicit Runtime Store/role for direct-authoring Apps. #752 now includes ownership-checked cleanup for every App and safe retry/evidence handling, covered by focused regressions and the final unit suite. No new full model matrix was run for those cleanup-only changes.

Independent read-only run 38708044949 confirmed all 13 exact prior-run resources absent, including three consecutive typed404 observations for the omitted Runtime Store, dedicated database and role. One separate current-window database/role pair remains present and unattributed: SCIM did not recover its App identity and one bounded audit SELECT failed. That pair was left intact; full cleanup of the current matrix run is not established. No resources were deleted using name/time correlation alone.

The Apps matrix covers LangGraph, CLI/direct authoring, dev/deployed runtime and five tool kinds. Separate cache tests cover both LangGraph and OpenAI Agents. These checks do not establish fresh-account provisioning rights or freshly consented deployed Genie OBO acceptance.

All public checks finished. #694/#727 have 54 green; the other ten PRs have 53 green and the same framework job red. Its six memory-backed parallel-history ordering failures also occur on current main. No forced skips or weakened grant assertions were applied.