* Bump uuid and googleapis in /quickstarts/file-api (#1212)

Removes [uuid](https://github.com/uuidjs/uuid). It's no longer used after updating ancestor dependency [googleapis](https://github.com/googleapis/google-api-nodejs-client). These dependencies need to be updated together.


Removes `uuid`

Updates `googleapis` from 134.0.0 to 171.4.0
- [Release notes](https://github.com/googleapis/google-api-nodejs-client/releases)
- [Commits](googleapis/google-api-nodejs-client@googleapis-v134.0.0...googleapis-v171.4.0)

---
updated-dependencies:
- dependency-name: uuid
  dependency-version: 
  dependency-type: indirect
- dependency-name: googleapis
  dependency-version: 171.4.0
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Flash-Lite 3.1 goes GA (#1221)

* Create README.md for the prompting_techniques folder (#1230)



---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* Added new notebook Basic_Code_Review to examples (#689)

---------

Co-authored-by: kkorpal <kkorpal@google.com>
Co-authored-by: Shipra <Shi-pra-19@users.noreply.github.com>

* Add Basic_Code_Review example to README (#1218)

* Add Basic_Code_Review example to README

* Update examples/prompting/README.md

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* Added example for gemini api used to extract insights from github #923 #887 (#1150)

* added example for gemini api used to extract insights from github


---------

Co-authored-by: kkorpal <kkorpal@google.com>

* Add example: EU AI Act compliance checking with Gemini function calling + Agent Module (#1167)

* Add EU AI Act compliance example with Gemini function calling + Agent Module

* style: use triple-quoted string per review feedback

* fix: correct API schema + formatting per review

- status["ethics"] -> status["ai_compliance"] (v0.9.21 schema rename; was
  the KeyError that blocked the reviewer run)
- Remove unnecessary backslash line-continuations in the compliance_run
  prompt string; indent body; newline before closing """
- Replace static 22-row module table with dynamic discovery pointer
  (/api/status, /api/demo, /llms.txt) so the snapshot never goes stale
- Branding: "ethics modules" -> "AI Compliance modules" in human-facing
  markdown; vertical slug documented as ai-compliance with ethics as
  legacy alias (both still accepted by the API)
- Correct ETH_001 EU AI Act mapping (Art. 9 + 10, not 10 + 13)

* fix: prevent trial key collision on reruns

Follow-up to the schema/formatting fixes. Colab testing surfaced a
runtime bug: the Agent Module API returns a masked preview of an
existing trial key (e.g. `am_trial_841...f660`) if you request a new
one while the old one is still active, and the original notebook
wrapper blindly stored the preview — corrupting _trial_key and
breaking every downstream retrieve_compliance_logic call.

Changes:
- Generate a unique per-run agent_id (uuid suffix) so reruns within
  24 hours do not collide with a still-active trial on the server
- Make get_trial_key idempotent (short-circuit if _trial_key already
  set in this session) so Gemini tool loops cannot re-trigger it
- Detect status=="already_active" in the MCP response and refuse to
  store the masked preview; surface a clear error instead
- Remove get_trial_key from the tools list passed to Gemini. Trial
  bootstrap is a setup step, not a runtime tool — the model should
  only see retrieve_compliance_logic and submit_proof_of_value
- Reframe the cell 27 preamble to explain the setup/runtime split

* fix: pass both token and trial_key to submit_pov MCP tool

* fix: print full chat history so cell 30 shows the complete compliance report

* chore: save executed notebook with cell outputs

* fix: add Colab button + README link for CI compliance

- Add Colab badge to notebook title cell (tfo-notebook-buttons CI check)
- Add notebook entry to examples/README.md table (new-example-links CI check)

* chore: retrigger CI checks

* Fix notebook lint (inclusive_language) + nbfmt format

- Rewords 'Agent-native' to 'Purpose-built for autonomous agents' in the branding cell to clear google::inclusive_language lint flag
- Applies tensorflow_docs.tools.nbfmt formatting pass to clear Notebook format check
- No other content changes; all 21 cell outputs preserved

* Fix colab.name metadata + cell 30 prompt (third-person) to clear nbfmt + second_person checks

---------

Co-authored-by: Guillaume Vernade <Giom-V@users.noreply.github.com>

* add gemini-3.5-flash (#1232)

* New agent notebook (#1233)

* Fixing typos

* Adding links to the agents notebooks (#1234)

* docs: fix typos and capitalization consistency in README (#1240)

* docs: fix typos and capitalization consistency in README

* docs: apply gemini suggestion

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* Bump qs from 6.15.1 to 6.15.2 in /quickstarts/file-api (#1238)

Bumps [qs](https://github.com/ljharb/qs) from 6.15.1 to 6.15.2.
- [Changelog](https://github.com/ljharb/qs/blob/main/CHANGELOG.md)
- [Commits](ljharb/qs@v6.15.1...v6.15.2)

---
updated-dependencies:
- dependency-name: qs
  dependency-version: 6.15.2
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Fix scale= command in Lyria realtime quickstart (#1236)

The scale= parser compared the raw prompt (which still contains the
'scale=' prefix) against enum names like A_FLAT_MAJOR_F_MINOR, so the
match never succeeded and the command always printed 'Matching enum
not found.'

Strip the 'scale=' prefix before comparing, matching how the sibling
bpm= and top_k= handlers already work.

* update live api ws cookbook (#1223)

* Interactions steps (#1237)

* Merge origin/main into interaction-steps and resolve conflict

* steps

* Add environment support

* work

* cleanup

* format

* cleanup

* Add back execution_count

* Standardize Colab buttons and fix URLs across edited notebooks

* feat: update visual model names to GA and add video-to-image example (#1244)

* feat: update visual model names to GA and add video-to-image example

- Updated gemini-3-pro-image-preview to gemini-3-pro-image (Nano Banana Pro GA)
- Updated gemini-3.1-flash-image-preview to gemini-3.1-flash-image (Nano Banana 2 GA)
- Added a new video-to-image example in Get_Started_Nano_Banana.ipynb
- Formatted modified notebooks with nbfmt

* feat(batch): add gemini-3.5-flash to model selector

* style: format banana notebook to clean up PR diff

* style: trim thought signature in Get_Started_Nano_Banana notebook

To reduce file size and prevent git/diff hanging on massive cryptographically signed binary thoughts.

* refactor: update Live API configuration, transcription support, and input handling for model version gemini-3.1-flash-live-preview (#1224)

* Update Get_started_LiveAPI (#1222)

* Update Get_started_LiveAPI

* remove interactivity.

* session resumption update.

* run.

* nbfmt

* Resizing the NB notebook (#1245)

* feat: add example for custom FPS in Grounding notebook (#1243)

* feat: add example for custom FPS in Grounding notebook

* Format custom frame rate explanation in Grounding.ipynb

* Fix formatting of YouTube link and response generation

* Fix formatting issues in Grounding.ipynb

* Fix YouTube link formatting in Grounding.ipynb

* docs: fix typographical and spelling errors in styleguide and quickstarts (#1253)

* docs: fix typographical and spelling errors in styleguide.md

* docs: fix typo in Image_out notebook header

* fix: remove leftover google-generativeai imports from two notebooks (#1246)

Two notebooks had leftover `import google.generativeai as genai` lines
from a prior partial migration. Both notebooks otherwise use the new
`google-genai` SDK correctly via `from google import genai`, and
neither notebook's `%pip install` cell installs `google-generativeai`.
On a clean Colab kernel the dead imports raise `ModuleNotFoundError`;
on a kernel where the legacy package happens to be pre-installed, the
dead imports silently shadow the working `genai` namespace.

- quickstarts/Spatial_understanding.ipynb cell 19: delete the dead
  `import google.generativeai as genai` line; the rest of the cell
  (PIL.Image, io, os, requests, BytesIO) is genuinely used downstream
- examples/Animated_Story_Video_Generation_gemini.ipynb cell 7:
  delete the cell entirely. The cell holds only the dead import

No behavioural change beyond removing dead code that would otherwise
fail or shadow at notebook runtime.

* fix(examples): replace deprecated Live API session.send in Animated Story notebook (#1249)

Use session.send_client_content(turns=..., turn_complete=True) instead of the
deprecated session.send(input=..., end_of_turn=True), which emits a
DeprecationWarning in google-genai (removal not before Q3 2025).

Co-authored-by: Sri Ujwal <sbeeredd04@users.noreply.github.com>

* fix(quickstarts): correct case-sensitive links to Search_Grounding/Code_Execution (#1248)

Three cross-notebook links used lowercase filenames (Search_grounding.ipynb,
Code_execution.ipynb) that 404 on case-sensitive file systems like GitHub. Point
them at the actual files: Search_Grounding.ipynb and Code_Execution.ipynb.

Co-authored-by: Sri Ujwal <sbeeredd04@users.noreply.github.com>

* fix(quickstarts): correct broken Contributing guide link in Template.ipynb (#1247)

The template linked the contributing guide as `Contributing.mg`, which is both a
typo (`.mg`) and a path that does not exist next to the notebook. Point it at the
repo's CONTRIBUTING.md using the same absolute GitHub URL the notebook already
uses elsewhere.

Co-authored-by: Sri Ujwal <sbeeredd04@users.noreply.github.com>

* fix: align error handling notebook with google-genai retries (#1229)

* docs: fix broken/incomplete links and remove duplicate entry in quickstarts README (#1257)

* docs: fix broken/incomplete links and remove duplicate entry in quickstarts README

* Update quickstarts/README.md

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* feat: add Live Translation quickstart tutorial and examples (#1259)

* feat: add Live Translation quickstart tutorial and examples

* chore: clean up notebook metadata and reorder cell output attributes

* refactor: Live Translation notebook and script from cookbook (#1261)

* Prohibit yt-dlp usage for YouTube content (#1264)

Added a restriction against using yt-dlp for downloading or streaming YouTube content due to terms of service violations.

* Sketch2Paint using Gemini (#790)



---------

Co-authored-by: Guillaume Vernade <Giom-V@users.noreply.github.com>

* Add service account auth section with IAM roles for Gemini, File, and… (#1258)

* Add service account auth section with IAM roles for Gemini, File, and Vertex AI APIs

* Remove service account section, add link to GCP auth docs instead

* Add Vertex AI authentication documentation link

* Fix embedding types & casing  (#1032)

* Fix embedding types & casing (fixes #1030)

* Fix query task_type and indentation style violations

* fix indentation style

* fixed the formatting and linting issue

* update model ID

* fix formatting

* Update styleguide with API key and crypto restrictions

Added guidelines for API key usage and restrictions on crypto topics.

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: kkorpal <kkorpal@google.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Shipra <ships3040@gmail.com>
Co-authored-by: Shipra <Shi-pra-19@users.noreply.github.com>
Co-authored-by: Rohan Dwivedi <165134541+ROHANDWIVEDI2005@users.noreply.github.com>
Co-authored-by: AgentModuleAdmin <0agentmodule@gmail.com>
Co-authored-by: Patrick Loeber <50772274+patrickloeber@users.noreply.github.com>
Co-authored-by: Irfaan Mansoori <irfaanmansoori100@gmail.com>
Co-authored-by: Aryan Motgi <85900811+aryanmotgi@users.noreply.github.com>
Co-authored-by: Thor 雷神 Schaeff <5748289+thorwebdev@users.noreply.github.com>
Co-authored-by: Mark Daoust <markdaoust@google.com>
Co-authored-by: August Cayzer <august@cayzer.me>
Co-authored-by: Sri Ujwal <113922053+sbeeredd04@users.noreply.github.com>
Co-authored-by: Sri Ujwal <sbeeredd04@users.noreply.github.com>
Co-authored-by: qianzhu / Lucien <2729478828@qq.com>
Co-authored-by: Naveen Kumar G <naveen13524g@gmail.com>
Co-authored-by: Nitin Tiwari <37960279+NSTiwari@users.noreply.github.com>
Co-authored-by: Anika Islam <172253577+Surjasa@users.noreply.github.com>