Add canary job

[mernst]

No description provided.

[coderabbitai]

📝 Walkthrough

Walkthrough

Three Azure Pipeline files were changed to add a synthetic orchestration job and make downstream jobs wait for it. A new canary_jobs job was added to .azure/azure-pipelines.yml and .azure/azure-pipelines.yml.m4 (depends on build_jdk and build_jdk21u). Multiple downstream jobs in .azure/azure-pipelines.yml, .azure/azure-pipelines.yml.m4, and .azure/defs.m4 were updated to include dependsOn: [canary_jobs] at the job level; YAML indentation/structure for several jobs was adjusted. A new M4 macro jdku_version = 21u was added to .azure/defs.m4.

🚥 Pre-merge checks | ✅ 1

✅ Passed checks (1 passed)

Check name	Status	Explanation
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

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

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

[coderabbitai]

Actionable comments posted: 1

Caution

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

⚠️ Outside diff range comments (2)

.azure/defs.m4 (2)

79-88: ⚠️ Potential issue | 🟠 Major

Missing dependsOn for inference_part2_jdk$1.

Unlike inference_part1_jdk$1 which depends on canary_jobs, inference_part2_jdk$1 has no dependsOn clause. This means it will start immediately without waiting for the build jobs to complete, which appears inconsistent with the orchestration pattern established in this PR.

🔧 Proposed fix

   - job: inference_part2_jdk$1
+    dependsOn:
+      - canary_jobs
     pool:
       vmImage: 'ubuntu-latest'

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In @.azure/defs.m4 around lines 79 - 88, Add a dependsOn clause to the job
inference_part2_jdk$1 so it mirrors the orchestration of inference_part1_jdk$1;
specifically, update the job definition for inference_part2_jdk$1 to include
dependsOn: canary_jobs (or the same dependency list used by
inference_part1_jdk$1) so the job waits for the build/canary jobs to finish
before running.

---

136-143: ⚠️ Potential issue | 🟠 Major

Missing dependsOn for typecheck_part2_jdk$1.

Same issue as inference_part2_jdk$1 — this job has no dependsOn clause while typecheck_part1_jdk$1 (lines 125-127) explicitly depends on canary_jobs. This creates an inconsistency where part2 can start before builds complete.

🔧 Proposed fix

   - job: typecheck_part2_jdk$1
+    dependsOn:
+      - canary_jobs
     pool:
       vmImage: 'ubuntu-latest'

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In @.azure/defs.m4 around lines 136 - 143, Add a dependsOn to the job definition
for typecheck_part2_jdk$1 so it cannot start before the preceding
typecheck_part1_jdk$1 (which currently depends on canary_jobs); specifically,
update the job block for typecheck_part2_jdk$1 to include a dependsOn:
typecheck_part1_jdk$1 entry to enforce correct ordering (similar to how
inference_part2_jdk$1 was fixed).

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In @.azure/defs.m4:
- Line 10: The macro `jdku_version` is defined but unused; either delete the
define([jdku_version], [21u])dnl line to remove dead code, or if you intend to
keep it for future use, replace it with the same definition plus a clear TODO
comment on its purpose and planned usage (e.g., TODO: reserved for future JDK/U
versioning) so reviewers know it’s intentional; locate the `jdku_version`
definition in the M4 definitions file and apply one of these two changes.

---

Outside diff comments:
In @.azure/defs.m4:
- Around line 79-88: Add a dependsOn clause to the job inference_part2_jdk$1 so
it mirrors the orchestration of inference_part1_jdk$1; specifically, update the
job definition for inference_part2_jdk$1 to include dependsOn: canary_jobs (or
the same dependency list used by inference_part1_jdk$1) so the job waits for the
build/canary jobs to finish before running.
- Around line 136-143: Add a dependsOn to the job definition for
typecheck_part2_jdk$1 so it cannot start before the preceding
typecheck_part1_jdk$1 (which currently depends on canary_jobs); specifically,
update the job block for typecheck_part2_jdk$1 to include a dependsOn:
typecheck_part1_jdk$1 entry to enforce correct ordering (similar to how
inference_part2_jdk$1 was fixed).

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: 3838c6bc-9668-4028-be68-79fea80db082

📥 Commits

Reviewing files that changed from the base of the PR and between 7d26e2d and 8fd7a26.

📒 Files selected for processing (3)

• .azure/azure-pipelines.yml
• .azure/azure-pipelines.yml.m4
• .azure/defs.m4

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In @.azure/defs.m4:
- Around line 180-195: The macro plume_lib_job declares a parameter ($1) but
never uses it; either remove the parameter from invocations of
plume_lib_job(canary_version) or use $1 inside the macro (for example substitute
it into the container image tag like container: mdernst/cf-ubuntu-jdk17:$1) so
the passed version is applied, or add an explicit comment inside the
plume_lib_job macro body noting that $1 is intentionally unused for consistency;
update the macro definition (plume_lib_job) and all its call sites to match the
chosen approach.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: 24aeea9d-ce99-4727-adb2-c071f1d402f3

📥 Commits

Reviewing files that changed from the base of the PR and between 8fd7a26 and 6ee41a6.

📒 Files selected for processing (1)

• .azure/defs.m4