4 Commits
Author SHA1 Message Date
AshpreetandClaude Fable 5 5cf1ed7f94 chore: update model guidance to gpt-5.5 (#8383)
## Summary

CLAUDE.md's "Don't" section still pointed cookbook authors at `gpt-5.4`,
but the current cookbooks have standardized on `gpt-5.5` (50 uses across
`cookbook/08_learning/` and `cookbook/01_demo/`, the most recently
refreshed folders). This PR updates the guidance and fixes the same
staleness in `.cursorrules`:

- **CLAUDE.md**: "use `gpt-5.4` instead" → "use `gpt-5.5` instead"
- **.cursorrules**: all 8 example snippets used
`OpenAIChat(id="gpt-4o")` — both the banned model *and* the banned class
per CLAUDE.md's own rules. Updated to `OpenAIResponses(id="gpt-5.5")`
(matching the import convention used in the cookbooks).

Checked but intentionally not changed:
- `.github/` CI prompts: no stale model references found.
- The 2 remaining `gpt-5.2` mentions in
`cookbook/08_learning/TEST_LOG.md` are historical test-log records (one
documents the gpt-5.2 → gpt-5.5 migration itself), so they were left
as-is.
- Older cookbook folders (e.g. `90_models/`, `02_agents/`) still use
`gpt-5.2`/`gpt-5.4` widely (~830 references); migrating those is out of
scope for this guidance-only chore.

## Type of change

- [ ] Bug fix
- [ ] New feature
- [ ] Breaking change
- [x] Improvement
- [ ] Model update
- [x] Other: docs/tooling guidance chore

---

## Checklist

- [x] Code complies with style guidelines
- [x] Ran format/validation scripts (`./scripts/format.sh` and
`./scripts/validate.sh`)
- [x] Self-review completed
- [x] Documentation updated (comments, docstrings)
- [ ] Examples and guides: Relevant cookbook examples have been included
or updated (if applicable)
- [ ] Tested in clean environment
- [ ] Tests added/updated (if applicable)

### Duplicate and AI-Generated PR Check

- [x] I have searched existing [open pull requests](../../pulls) and
confirmed that no other PR already addresses this issue
- [ ] If a similar PR exists, I have explained below why this PR is a
better approach
- [x] Check if this PR was entirely AI-generated (by Copilot, Claude
Code, Cursor, etc.)

---

## Additional Notes

No runtime code changes — only `CLAUDE.md` and `.cursorrules`. Both
format and validate scripts pass.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Fable 5 <[email protected]>
2026-06-13 18:53:25 +01:00
+2 a5e392808a feat: v2.4.0 (#5818)
## New Features:

- **Knowledge Protocol:** Introduced `KnowledgeProtocol` The main
Knowledge implementation now satisfies this interface. Any other
implementation may be used with Agent/Team. Note - Only the main Agno
Knowledge implementation of this protocol currently supports AgentOS
Knowledge management.
- **Agent/Workflow Builder: …**
- **New Events:** Added new events for Model, compression and memory.
    - `ModelRequestStarted` and `ModelRequestCompleted`
    - `CompressionStarted` and `CompressionCompleted`
    - Update `MemoryUpdateCompleted` to contain the memory content.

## Improvements:

- **Default DB on `AgentOS`:** Add `db` to the `AgentOS` class. If
populated, it propagates to all
agents, teams and workflows without db. It is also used as tracing db.
- Deprecated `enable_user_memories` : Introduced `update_memory_on_run`
for the same behavior.
- **Knowledge config endpoint**: Improved checking for available readers
without needing instantiation of the reader classes. Reduced unnecessary
warnings and improved response times.
- **Unify dates format on OS API layer:** Unify the format of all dates
we send via the OS API. Everything is now a UTC datetime
- **Pass instructions as is without XML tags:**
- **Agent & Team**: Instructions are now added directly to the system
message without `<instructions>` tags by default
- Added `add_instruction_tags=True` option to restore the previous
behavior for users who prefer structured prompts

## Bug Fixes:

- **LanceDB:** Fixed a bug for duplicate embeddings during async insert
and upsert operations.

## Breaking changes:

- **Remove all deprecated fields:**
- `session_state, dependencies` etc in tool functions and hooks where
`RunContext` has replaced it
    - `stream_intermediate_steps` → `stream_events`
    - `yield_run_response` → `yield_run_output`
    - `delegate_task_to_all_members` removed from Team class
- **Add WebSearchTools:** Replacing DDG websearch tool with a Generic
web search tool which will be the default on for any websearch related
cookbooks & docs.
- **Knowledge add_content() renamed to insert():** The `add_content()`
method and its variants have been renamed to `insert()` `insert_many`
Old method names are still supported, but all examples and docs will
soon only reference the new methods.

---------

Co-authored-by: manuhortet <[email protected]>
Co-authored-by: Dirk Brand <[email protected]>
Co-authored-by: Yash Pratap Solanky <[email protected]>
Co-authored-by: Ashpreet <[email protected]>
Co-authored-by: harshsinha03 <[email protected]>
Co-authored-by: Uzair Ali <[email protected]>
Co-authored-by: Claude Opus 4.5 <[email protected]>
Co-authored-by: Willem Carel de Jongh <[email protected]>
Co-authored-by: Priti <[email protected]>
Co-authored-by: ayuss <[email protected]>
Co-authored-by: Mustafa Esoofally <[email protected]>
2026-01-19 15:56:54 +05:30
b8b994d76e feat: background tasks for AgentOS (#5550)
## Summary

This adds background task execution for agents/teams in AgentOS. I.e.
pre/post hooks will be run as FastAPI background tasks instead of normal
tasks

## Type of change

- [ ] Bug fix
- [x] New feature
- [ ] Breaking change
- [ ] Improvement
- [ ] Model update
- [ ] Other:

---

## Checklist

- [ ] Code complies with style guidelines
- [ ] Ran format/validation scripts (`./scripts/format.sh` and
`./scripts/validate.sh`)
- [ ] Self-review completed
- [ ] Documentation updated (comments, docstrings)
- [ ] Examples and guides: Relevant cookbook examples have been included
or updated (if applicable)
- [ ] Tested in clean environment
- [ ] Tests added/updated (if applicable)

---

## Additional Notes

Add any important context (deployment instructions, screenshots,
security considerations, etc.)

---------

Co-authored-by: manu <[email protected]>
Co-authored-by: Harsh Sinha <[email protected]>
2025-12-03 09:50:42 +02:00
Nancy Chauhan 12798658e5 chore: add comprehensive .cursorrules (#4864)
## Summary

Describe key changes, mention related issues or motivation for the
changes.

Add comprehensive `.cursorrules` file for AI-assisted development with
Cursor

## Type of change

- [ ] Bug fix
- [x] New feature
- [ ] Breaking change
- [x] Improvement
- [ ] Model update
- [ ] Other:

---

## Checklist

- [ ] Code complies with style guidelines
- [ ] Ran format/validation scripts (`./scripts/format.sh` and
`./scripts/validate.sh`)
- [ ] Self-review completed
- [ ] Documentation updated (comments, docstrings)
- [ ] Examples and guides: Relevant cookbook examples have been included
or updated (if applicable)
- [ ] Tested in clean environment
- [ ] Tests added/updated (if applicable)

---

## Additional Notes

Add any important context (deployment instructions, screenshots,
security considerations, etc.)
2025-10-02 22:35:25 +02:00