Skip to content

fix(docs): update stale env var and script refs from PR #67 feedback#68

Merged
jeremylongshore merged 1 commit intomainfrom
fix/doc-env-var-refs
Feb 20, 2026
Merged

fix(docs): update stale env var and script refs from PR #67 feedback#68
jeremylongshore merged 1 commit intomainfrom
fix/doc-env-var-refs

Conversation

@jeremylongshore
Copy link
Copy Markdown
Collaborator

@jeremylongshore jeremylongshore commented Feb 20, 2026

Summary

Addresses Qodo and Gemini feedback from PR #67:

Historical AARs (130, 131, 159) left unchanged as they document the state at time of writing.

Test plan

  • CI passes
  • grep -r BOB_AGENT_ENGINE_NAME_DEV .env.example 000-docs/000-DR-STND-inline-* returns zero
  • grep -r smoke_test_bob_agent_engine_dev 000-docs/000-DR-STND-inline-* returns zero

🤖 Generated with Claude Code

Summary by CodeRabbit

  • Documentation

    • Updated deployment documentation to reflect current configuration naming conventions and testing procedures.
  • Chores

    • Updated environment variable naming conventions for deployment configuration.
    • Refined development testing workflow and scripts.

- .env.example: BOB_AGENT_ENGINE_NAME_DEV → AGENT_ENGINE_BOB_ID_DEV
- 000-DR-STND-inline-source-deployment: update all references from
  BOB_AGENT_ENGINE_NAME_DEV → AGENT_ENGINE_BOB_ID_DEV and
  smoke_test_bob_agent_engine_dev.py → run_agent_engine_dev_smoke.py
- Makefile: add explicit --agent bob to smoke target (per Gemini review)

Historical AARs (130, 131, 159) left unchanged as they document
the state at time of writing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@qodo-code-review
Copy link
Copy Markdown

Review Summary by Qodo

Update stale environment variable and script references

🐞 Bug fix 📝 Documentation

Grey Divider

Walkthroughs

Description
• Updated stale environment variable references from BOB_AGENT_ENGINE_NAME_DEV to
  AGENT_ENGINE_BOB_ID_DEV
• Renamed smoke test script reference from smoke_test_bob_agent_engine_dev.py to
  run_agent_engine_dev_smoke.py
• Added explicit --agent bob flag to Makefile smoke test target
• Simplified environment variable format from full resource path to agent ID only
Diagram
flowchart LR
  A["Legacy env var<br/>BOB_AGENT_ENGINE_NAME_DEV"] -->|"Update to"| B["New env var<br/>AGENT_ENGINE_BOB_ID_DEV"]
  C["Old script name<br/>smoke_test_bob_agent_engine_dev.py"] -->|"Rename to"| D["New script name<br/>run_agent_engine_dev_smoke.py"]
  E["Makefile target"] -->|"Add flag"| F["--agent bob parameter"]
Loading

Grey Divider

File Changes

1. .env.example 📝 Documentation +1/-1

Update Bob Agent Engine env variable reference

• Updated environment variable name from BOB_AGENT_ENGINE_NAME_DEV to AGENT_ENGINE_BOB_ID_DEV
• Simplified variable format from full resource path to agent ID only
• Updated comment to reflect new variable name

.env.example


2. 000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md 📝 Documentation +11/-11

Update stale env var and script references

• Updated all references from BOB_AGENT_ENGINE_NAME_DEV to AGENT_ENGINE_BOB_ID_DEV throughout
 document
• Changed smoke test script path from smoke_test_bob_agent_engine_dev.py to
 run_agent_engine_dev_smoke.py
• Simplified environment variable format from full resource path to agent ID
• Updated troubleshooting section to reflect new variable name and format
• Updated deployment checklist and usage examples

000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md


3. Makefile ⚙️ Configuration changes +1/-1

Add explicit agent flag to smoke target

• Added explicit --agent bob flag to smoke test target command
• Ensures resilience against potential default parameter changes

Makefile


Grey Divider

Qodo Logo

@gemini-code-assist
Copy link
Copy Markdown

Summary of Changes

Hello @jeremylongshore, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refines the project's configuration and documentation by addressing outdated references and enhancing a critical development workflow. It ensures consistency in environment variable naming, updates script paths to reflect current practices, and fortifies a Makefile command for agent-specific smoke testing, thereby improving the developer experience and reducing potential confusion.

Highlights

  • Environment Variable Renaming: Updated the BOB_AGENT_ENGINE_NAME_DEV environment variable to the canonical AGENT_ENGINE_BOB_ID_DEV in .env.example and all relevant documentation.
  • Script Reference Update: Replaced references to the archived smoke_test_bob_agent_engine_dev.py script with the new run_agent_engine_dev_smoke.py in the documentation.
  • Makefile Target Enhancement: Added an explicit --agent bob flag to the smoke-bob-agent-engine-dev Makefile target for improved resilience and clarity.
Changelog
  • .env.example
    • Updated the BOB_AGENT_ENGINE_NAME_DEV environment variable to AGENT_ENGINE_BOB_ID_DEV.
  • 000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md
    • Updated the smoke test script location from smoke_test_bob_agent_engine_dev.py to run_agent_engine_dev_smoke.py.
    • Replaced all mentions of BOB_AGENT_ENGINE_NAME_DEV with AGENT_ENGINE_BOB_ID_DEV.
    • Modified the example usage for direct script execution to include --agent bob.
    • Updated the troubleshooting section for missing environment variables to reflect the new variable name and error message.
  • Makefile
    • Added --agent bob to the smoke-bob-agent-engine-dev target command.
Activity
  • Addressed feedback from PR fix(config): align AGENT_ENGINE env var convention to _ID_ pattern #67, specifically from Qodo and Gemini.
  • Updated .env.example and standards documentation based on Qodo's bug reports.
  • Incorporated Gemini's suggestion to add an explicit agent flag to the Makefile target.
  • The author has outlined a test plan including CI checks and grep commands to verify the changes.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

@coderabbitai
Copy link
Copy Markdown

coderabbitai Bot commented Feb 20, 2026

📝 Walkthrough

Walkthrough

Environment variable BOB_AGENT_ENGINE_NAME_DEV is renamed to AGENT_ENGINE_BOB_ID_DEV with a simplified identifier format. Related references in documentation and build configuration are updated accordingly to reflect the new naming convention and script parameters.

Changes

Cohort / File(s) Summary
Configuration & Environment
.env.example
Environment variable renamed from BOB_AGENT_ENGINE_NAME_DEV to AGENT_ENGINE_BOB_ID_DEV; value format changed from full resource name path to simple numeric ID.
Documentation
000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md
Updated environment variable references from BOB_AGENT_ENGINE_NAME_DEV to AGENT_ENGINE_BOB_ID_DEV; smoke test script path updated from smoke_test_bob_agent_engine_dev.py to run_agent_engine_dev_smoke.py throughout usage examples, Makefile targets, and troubleshooting sections.
Build Configuration
Makefile
smoke-bob-agent-engine-dev target updated to pass --agent bob argument to the smoke test script invocation.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

  • PR #67: Implements the same AGENT_ENGINE_BOB_ID_DEV environment variable naming pattern across config, docs, and smoke-test references in parallel.
  • PR #65: Updates the smoke-bob-agent-engine-dev Makefile target with --agent bob argument and modifies related smoke-test script references.

Poem

🐰 A little hop, a name so new,
AGENT_ENGINE_BOB shines through—
From verbose paths to IDs neat,
The config change is crisp and sweet! ✨
Documentation dancing in sync,
No broken links, not even a chink! 🎉

🚥 Pre-merge checks | ✅ 3
✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title accurately and concisely captures the main change: updating stale environment variable and script references based on prior feedback.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch fix/doc-env-var-refs

Comment @coderabbitai help to get the list of available commands and usage tips.

@greptile-apps
Copy link
Copy Markdown

greptile-apps Bot commented Feb 20, 2026

Greptile Summary

Addresses Qodo and Gemini feedback from PR #67 by updating stale documentation and configuration references to use canonical naming conventions. The changes ensure consistency across .env.example, standards documentation, and the Makefile by replacing legacy BOB_AGENT_ENGINE_NAME_DEV with AGENT_ENGINE_BOB_ID_DEV (aligning with the _ID_ pattern established in PR #67) and updating the archived script reference from smoke_test_bob_agent_engine_dev.py to run_agent_engine_dev_smoke.py.

Key changes:

  • .env.example: Updated env var comment to canonical AGENT_ENGINE_BOB_ID_DEV pattern
  • Standards doc: Updated 10 references to reflect current env var and script naming
  • Makefile: Added explicit --agent bob flag to smoke test target for resilience

Intentionally unchanged: Historical AARs (130, 131, 159) remain as-is since they document the state at time of writing, per project standards.

Confidence Score: 5/5

  • This PR is safe to merge with no risk
  • Documentation-only changes that fix stale references with no code logic impact. Changes are straightforward, consistent, and align perfectly with established conventions from PR fix(config): align AGENT_ENGINE env var convention to _ID_ pattern #67. The updates improve accuracy without affecting runtime behavior.
  • No files require special attention

Important Files Changed

Filename Overview
.env.example Updated deprecated BOB_AGENT_ENGINE_NAME_DEV to canonical AGENT_ENGINE_BOB_ID_DEV pattern
000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md Updated 10 references: deprecated env var and archived script path to current conventions
Makefile Added explicit --agent bob flag for resilience against default changes

Last reviewed commit: 49d57ef

Copy link
Copy Markdown

@greptile-apps greptile-apps Bot left a comment

Choose a reason for hiding this comment

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

3 files reviewed, no comments

Edit Code Review Agent Settings | Greptile

@jeremylongshore jeremylongshore merged commit a6b10b7 into main Feb 20, 2026
14 of 15 checks passed
@jeremylongshore jeremylongshore deleted the fix/doc-env-var-refs branch February 20, 2026 00:40
@qodo-code-review
Copy link
Copy Markdown

Code Review by Qodo

🐞 Bugs (2) 📘 Rule violations (1) 📎 Requirement gaps (0)

Grey Divider


Action required

1. Env example contradicts ID format 🐞 Bug ✓ Correctness
Description
.env.example now references AGENT_ENGINE_BOB_ID_DEV, but the surrounding comments still instruct
users to paste a full Agent Engine resource name (projects/.../reasoningEngines/...). The runtime
config treats this value as an ID and will blindly concatenate it into a full path/URL, producing an
invalid resource name if a full path is supplied.
Code

.env.example[R41-43]

# Bob (Global Orchestrator) - Dev instance
# Required for: make smoke-bob-agent-engine-dev
-# BOB_AGENT_ENGINE_NAME_DEV=projects/205354194989/locations/us-central1/reasoningEngines/1234567890123456789
+# AGENT_ENGINE_BOB_ID_DEV=1234567890123456789
Evidence
The template text still describes “full Agent Engine resource identifiers” in projects/... format,
but the config module explicitly defines the value as “just the ID” and constructs the full resource
name by string concatenation; thus supplying a full resource name in AGENT_ENGINE_BOB_ID_DEV would
create a doubled/invalid path.

.env.example[28-44]
agents/config/agent_engine.py[37-64]
agents/config/agent_engine.py[166-193]
service/a2a_gateway/agent_engine_client.py[162-165]

Agent prompt
The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

### Issue description
`.env.example` now points users to `AGENT_ENGINE_BOB_ID_DEV`, but the surrounding comments still describe pasting a *full* resource name (`projects/.../reasoningEngines/...`). The code treats the env var as an ID and concatenates it into a full resource path, so using a full resource name will create an invalid/doubled resource name.

### Issue Context
- `agents/config/agent_engine.py` documents `reasoning_engine_id` as **ID-only** and constructs the full name via string formatting.
- `.env.example` still claims the values are “full resource identifiers”.

### Fix Focus Areas
- .env.example[28-44]
- agents/config/agent_engine.py[37-64]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools


2. Smoke-test standard doc is stale 🐞 Bug ✓ Correctness
Description
The standards doc was updated to reference scripts/run_agent_engine_dev_smoke.py, but the
surrounding content still describes the archived smoke script behavior (Vertex SDK usage, [SMOKE]
expected output format, different exit codes) and lists env vars (GCP_LOCATION) that the current
config code does not read. This can lead to incorrect setup and mis-troubleshooting.
Code

000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md[R510-517]

+**Location**: `scripts/run_agent_engine_dev_smoke.py`

**Purpose**: Validates that the inline-deployed Bob agent on Vertex AI Agent Engine is responding correctly to basic health check queries.

**Requirements**:
- Run AFTER a successful dev deployment via inline source
-- Requires `BOB_AGENT_ENGINE_NAME_DEV` environment variable set to full Agent Engine resource name
+- Requires `AGENT_ENGINE_BOB_ID_DEV` environment variable set to the Agent Engine ID
- Uses Vertex AI Agent Engine SDK for connectivity
Evidence
The doc now points to run_agent_engine_dev_smoke.py, but it still claims the script uses the
Vertex Agent Engine SDK, shows an expected output format that doesn’t exist in the referenced
script, omits the script’s exit code 2 (not configured), and instructs setting GCP_LOCATION even
though runtime config reads LOCATION/VERTEX_LOCATION. These mismatches were made more acute by
changing the referenced script without updating the semantics around it.

000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md[508-524]
000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md[526-561]
scripts/run_agent_engine_dev_smoke.py[16-31]
scripts/run_agent_engine_dev_smoke.py[50-52]
scripts/run_agent_engine_dev_smoke.py[113-120]
agents/config/agent_engine.py[104-113]

Agent prompt
The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

### Issue description
The standards doc now points to `scripts/run_agent_engine_dev_smoke.py`, but the rest of the section still describes the old archived smoke script (different output, different flow, different exit codes) and recommends env vars (`GCP_LOCATION`) that the current config module doesn’t read.

### Issue Context
- `scripts/run_agent_engine_dev_smoke.py` is an AE3 smoke test that routes via `service/a2a_gateway/agent_engine_client.call_agent_engine` and requires `DEPLOYMENT_ENV=dev`.
- `agents/config/agent_engine.py` reads `LOCATION`/`VERTEX_LOCATION` (not `GCP_LOCATION`).

### Fix Focus Areas
- 000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md[508-561]
- scripts/run_agent_engine_dev_smoke.py[16-31]
- scripts/run_agent_engine_dev_smoke.py[113-120]
- agents/config/agent_engine.py[104-113]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools



Remediation recommended

3. Real ID in .env.example 📘 Rule violation ⛨ Security
Description
.env.example now contains a concrete-looking AGENT_ENGINE_BOB_ID_DEV numeric value, which can
leak internal identifiers and encourage copying real values into tracked files. Use a clear
placeholder value instead (e.g., YOUR_AGENT_ENGINE_ID).
Code

.env.example[43]

+# AGENT_ENGINE_BOB_ID_DEV=1234567890123456789
Evidence
Compliance requires sensitive data to be handled securely and not exposed in files/config examples;
the added .env.example line includes a specific Agent Engine ID value rather than a placeholder.

Rule 6: Generic: Security-First Input Validation and Data Handling
.env.example[43-43]

Agent prompt
The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
`.env.example` includes a concrete-looking `AGENT_ENGINE_BOB_ID_DEV` value. Even if commented, this can expose internal identifiers and leads to accidental reuse of real IDs.

## Issue Context
Example env files should use placeholders (e.g., `YOUR_AGENT_ENGINE_ID`) instead of values that could be mistaken for real resources.

## Fix Focus Areas
- .env.example[43-43]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools


Grey Divider

ⓘ The new review experience is currently in Beta. Learn more

Grey Divider

Qodo Logo

Comment thread .env.example
Comment on lines 41 to +43
# Bob (Global Orchestrator) - Dev instance
# Required for: make smoke-bob-agent-engine-dev
# BOB_AGENT_ENGINE_NAME_DEV=projects/205354194989/locations/us-central1/reasoningEngines/1234567890123456789
# AGENT_ENGINE_BOB_ID_DEV=1234567890123456789
Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Action required

1. Env example contradicts id format 🐞 Bug ✓ Correctness

.env.example now references AGENT_ENGINE_BOB_ID_DEV, but the surrounding comments still instruct
users to paste a full Agent Engine resource name (projects/.../reasoningEngines/...). The runtime
config treats this value as an ID and will blindly concatenate it into a full path/URL, producing an
invalid resource name if a full path is supplied.
Agent Prompt
### Issue description
`.env.example` now points users to `AGENT_ENGINE_BOB_ID_DEV`, but the surrounding comments still describe pasting a *full* resource name (`projects/.../reasoningEngines/...`). The code treats the env var as an ID and concatenates it into a full resource path, so using a full resource name will create an invalid/doubled resource name.

### Issue Context
- `agents/config/agent_engine.py` documents `reasoning_engine_id` as **ID-only** and constructs the full name via string formatting.
- `.env.example` still claims the values are “full resource identifiers”.

### Fix Focus Areas
- .env.example[28-44]
- agents/config/agent_engine.py[37-64]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

Comment on lines +510 to 517
**Location**: `scripts/run_agent_engine_dev_smoke.py`

**Purpose**: Validates that the inline-deployed Bob agent on Vertex AI Agent Engine is responding correctly to basic health check queries.

**Requirements**:
- Run AFTER a successful dev deployment via inline source
- Requires `BOB_AGENT_ENGINE_NAME_DEV` environment variable set to full Agent Engine resource name
- Requires `AGENT_ENGINE_BOB_ID_DEV` environment variable set to the Agent Engine ID
- Uses Vertex AI Agent Engine SDK for connectivity
Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Action required

2. Smoke-test standard doc is stale 🐞 Bug ✓ Correctness

The standards doc was updated to reference scripts/run_agent_engine_dev_smoke.py, but the
surrounding content still describes the archived smoke script behavior (Vertex SDK usage, [SMOKE]
expected output format, different exit codes) and lists env vars (GCP_LOCATION) that the current
config code does not read. This can lead to incorrect setup and mis-troubleshooting.
Agent Prompt
### Issue description
The standards doc now points to `scripts/run_agent_engine_dev_smoke.py`, but the rest of the section still describes the old archived smoke script (different output, different flow, different exit codes) and recommends env vars (`GCP_LOCATION`) that the current config module doesn’t read.

### Issue Context
- `scripts/run_agent_engine_dev_smoke.py` is an AE3 smoke test that routes via `service/a2a_gateway/agent_engine_client.call_agent_engine` and requires `DEPLOYMENT_ENV=dev`.
- `agents/config/agent_engine.py` reads `LOCATION`/`VERTEX_LOCATION` (not `GCP_LOCATION`).

### Fix Focus Areas
- 000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md[508-561]
- scripts/run_agent_engine_dev_smoke.py[16-31]
- scripts/run_agent_engine_dev_smoke.py[113-120]
- agents/config/agent_engine.py[104-113]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

Copy link
Copy Markdown

@coderabbitai coderabbitai Bot left a comment

Choose a reason for hiding this comment

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

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (2)
000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md (1)

579-585: ⚠️ Potential issue | 🟡 Minor

Clarify “resource name” vs “ID” to avoid misconfiguration.

Step 6 says to copy the full resource name, while Step 7 uses the *_ID_* variable. Please clarify that the ID is the final segment of the resource name.

✅ Proposed wording fix
-6. Copy Agent Engine resource name from workflow output
-7. Set `AGENT_ENGINE_BOB_ID_DEV` environment variable
+6. Copy Agent Engine ID from workflow output (last segment of the resource name)
+7. Set `AGENT_ENGINE_BOB_ID_DEV` to that ID
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md`
around lines 579 - 585, Update the docs to clarify that Step 6 requires copying
the full Agent Engine resource name but Step 7's AGENT_ENGINE_BOB_ID_DEV expects
only the resource ID (the final segment of the full resource name); explicitly
show an example full resource name and highlight extracting the last path
segment as the ID (e.g., show full: projects/.../agentEngines/AGENT_ENGINE_ID
and then AGENT_ENGINE_ID used for AGENT_ENGINE_BOB_ID_DEV) and update the Step
6/7 wording to state this extraction clearly.
.env.example (1)

31-43: ⚠️ Potential issue | 🟡 Minor

Clarify that AGENT_ENGINE_BOB_ID_DEV expects the ID, not the full resource name.

The comments still describe full resource identifiers, which conflicts with the new “ID” variable naming and example. This can cause users to paste the wrong value.

✅ Proposed doc fix
-# These are the full Agent Engine resource identifiers from Vertex AI
-# Format: projects/PROJECT_ID/locations/LOCATION/reasoningEngines/AGENT_ID
+# These are the numeric Agent Engine IDs (final segment of the resource name)
+# Resource name format: projects/PROJECT_ID/locations/LOCATION/reasoningEngines/AGENT_ID
+# Use only the trailing AGENT_ID value here.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In @.env.example around lines 31 - 43, Update the .env example comments to make
it explicit that AGENT_ENGINE_BOB_ID_DEV expects just the agent ID (e.g., the
numeric AGENT_ID) and not the full Vertex AI resource name; change or add text
near the AGENT_ENGINE_BOB_ID_DEV example to say "Enter only the AGENT_ID
(numeric ID), not the full resource name like projects/.../reasoningEngines/..."
and remove or separate the earlier "full resource identifier" instructions so
they don't conflict with the AGENT_ENGINE_BOB_ID_DEV variable naming.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Outside diff comments:
In @.env.example:
- Around line 31-43: Update the .env example comments to make it explicit that
AGENT_ENGINE_BOB_ID_DEV expects just the agent ID (e.g., the numeric AGENT_ID)
and not the full Vertex AI resource name; change or add text near the
AGENT_ENGINE_BOB_ID_DEV example to say "Enter only the AGENT_ID (numeric ID),
not the full resource name like projects/.../reasoningEngines/..." and remove or
separate the earlier "full resource identifier" instructions so they don't
conflict with the AGENT_ENGINE_BOB_ID_DEV variable naming.

In `@000-docs/000-DR-STND-inline-source-deployment-for-vertex-agent-engine.md`:
- Around line 579-585: Update the docs to clarify that Step 6 requires copying
the full Agent Engine resource name but Step 7's AGENT_ENGINE_BOB_ID_DEV expects
only the resource ID (the final segment of the full resource name); explicitly
show an example full resource name and highlight extracting the last path
segment as the ID (e.g., show full: projects/.../agentEngines/AGENT_ENGINE_ID
and then AGENT_ENGINE_ID used for AGENT_ENGINE_BOB_ID_DEV) and update the Step
6/7 wording to state this extraction clearly.

Copy link
Copy Markdown

@gemini-code-assist gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

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

Code Review

The pull request successfully addresses stale references to environment variables and script names in the documentation and .env.example, following feedback from PR #67. The transition from full resource names to simple IDs for Agent Engine configuration is correctly reflected across the modified files. I have one minor suggestion regarding the accuracy of an error message in the troubleshooting documentation to ensure it matches the actual script output.

1. **"Missing required environment variable: BOB_AGENT_ENGINE_NAME_DEV"**
- Cause: Environment variable not set
- Fix: Export variable with full Agent Engine resource name
1. **"Agent not configured"**
Copy link
Copy Markdown

Choose a reason for hiding this comment

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

medium

The error message string here doesn't exactly match the output from scripts/run_agent_engine_dev_smoke.py. For better searchability in the troubleshooting guide, it's best to use the actual string printed by the script.

Suggested change
1. **"Agent not configured"**
1. **"Agent 'bob' is NOT configured for dev"**

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