Repository navigation
Conversation
jamesbxwu
commented
Oct 2, 2026
Comment on lines
+38
to
+39
| Create a project using LangGraph (the default framework). Use `--framework openai` instead to | ||
| create an **OpenAI Agents SDK** project. This chooses the agent framework, not the model provider; |
Contributor
Author
There was a problem hiding this comment.
Suggested change
| Create a project using LangGraph (the default framework). Use `--framework openai` instead to | |
| create an **OpenAI Agents SDK** project. This chooses the agent framework, not the model provider; | |
| Create your new agent project (with default framework of LangGraph). Use `--framework openai` instead to | |
| create an **OpenAI Agents SDK** project. This chooses the agent framework, not the model provider; |
Comment on lines
+96
to
+102
| ```sh | ||
| SESSION_ID=$(python3 -c 'import uuid; print(uuid.uuid4())') | ||
| INVOCATION_ID=$(python3 -c 'import uuid; print(uuid.uuid4())') | ||
| agentbricks endpoint invoke --url http://localhost:8000 \ | ||
| --path /api/invocations \ | ||
| --json "{\"id\":\"$INVOCATION_ID\",\"session_id\":\"$SESSION_ID\",\"input\":{\"messages\":[{\"role\":\"user\",\"content\":\"Use count_words to count the words in: the quick brown fox\"}]}}" | ||
| ``` |
Contributor
Author
There was a problem hiding this comment.
It feels weird that we're introducing the invoke command for the first time only down here in the tool section. Should it be moved up after you do dev or deploy?
| output for access or tracing warnings. `deployments get` prints the App URL and status; open the URL | ||
| and send a message to verify the deployed agent. | ||
|
|
||
| ## Add a custom tool |
Contributor
Author
There was a problem hiding this comment.
Why should the custom tool here be in the quick start instead of later on?
| memory = memory.update(content="The user prefers very concise answers.") | ||
| memory.delete() | ||
| ``` | ||
| ## Project ownership and upgrades |
Contributor
Author
There was a problem hiding this comment.
is this more about a dev guide and less of a user guide?
Contributor
Author
There was a problem hiding this comment.
in general I still and we need to be very hard to follow. I see this as a combination of helping the user to get started and teaching them how to do things, but then there's also a combination of how developers could iterate on this. I feel like the split is not exactly clear. Is there a better way that we can structure?
jamesbxwu
changed the title
jamesbxwu
marked this pull request as draft
October 15, 2026 07:16
jamesbxwu
changed the title
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The Agent Bricks README put architecture and API details ahead of setup, customization, and maintenance. Move a complete framework-specific Quickstart and working Python tool example to the top, then link to focused guides for deployment, resources, upgrades, memory/sessions, tools, migration, and coding-agent skills.
The deployment guide distinguishes the Runtime Store, conversation state, and memory; explains create/reuse/delete behavior; and documents dependency inputs and the excluded local lockfile. The upgrade guide separates installed library updates from copied template changes, with version checks and a comparison workflow that preserves custom code.
Refresh the guides against current main: managed Runtime Store defaults, automatic store detach, UC request-user tools, volume-only sandbox scopes, memory put/four-tool behavior, and persisted OpenAI approval checkpoints. The approval section explicitly identifies the fix as newer than PyPI 0.5.1 and explains the copied-harness adoption requirements. Keep the existing telemetry disclosure and workflow/cleanup documentation accessible after the reorganization.
Validation:
git diff --checkpassed.Tracking: ML-70356
Public CI baseline: the framework job fails the same six memory-backed parallel-history ordering cases as current main (expected last/first, observed first/last). Confirmed independently against main run https://github.com/databricks/databricks-ai-bridge/actions/runs/38662891535/job/116188048864; no forced skips. Other checks are tracked separately.
Bug-bash integration validation
The test-only combined branch at
be2fa8ee8d6d3b3e011ecfa285e6455b90f9433acontains 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 at53f9db8passed 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.