NO-ISSUE: Implement analyze-ci-create-bugs-for-release Claude command#6386
NO-ISSUE: Implement analyze-ci-create-bugs-for-release Claude command#6386ggiguash wants to merge 14 commits intoopenshift:mainfrom
Conversation
openshift-ci-robot
added
the
jira/valid-reference
|
@ggiguash: This pull request explicitly references no jira issue. DetailsIn response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository. |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: ggiguash The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
openshift-ci
bot
added
the
approved
|
/verified by @ggiguash |
|
Important Review skippedAuto reviews are limited based on label configuration. 🚫 Review skipped — only excluded labels are configured. (1)
Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Repository YAML (base), Organization UI (inherited) Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughRefactored CI analysis workflow to centralize temporary files under Changes
Estimated code review effort🎯 4 (Complex) | ⏱️ ~50 minutes ✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment |
|
@ggiguash: This PR has been marked as verified by DetailsIn response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository. |
openshift-ci-robot
added
the
verified
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
🧹 Nitpick comments (1)
.gitignore (1)
5-6: Use consistent trailing slashes for directory patterns.Lines 4-5 use trailing slashes (
.work/,_output/), but line 6 lacks it. Add/to__pycache__for consistency.♻️ Consistency fix
_output/ -__pycache__ +__pycache__/🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.gitignore around lines 5 - 6, Update the .gitignore directory pattern for consistency by appending a trailing slash to the __pycache__ entry so it reads as a directory pattern (i.e., change "__pycache__" to "__pycache__/"); ensure the other directory patterns like ".work/" and "_output/" remain with trailing slashes to keep the file consistent.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In @.gitignore:
- Around line 5-6: Update the .gitignore directory pattern for consistency by
appending a trailing slash to the __pycache__ entry so it reads as a directory
pattern (i.e., change "__pycache__" to "__pycache__/"); ensure the other
directory patterns like ".work/" and "_output/" remain with trailing slashes to
keep the file consistent.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Organization UI (inherited)
Review profile: CHILL
Plan: Pro
Run ID: 59b66b7a-339b-421b-9650-07d8da67f163
📒 Files selected for processing (2)
.claude/agents/openshift-ci-analysis.md.gitignore
ggiguash
force-pushed
the
claude-settings-update
branch
from
72efe4c to
5684c6d
Compare
openshift-ci-robot
removed
the
verified
|
/verified by @ggiguash |
openshift-ci-robot
added
the
verified
|
@ggiguash: This PR has been marked as verified by DetailsIn response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository. |
openshift-ci-robot
removed
the
verified
There was a problem hiding this comment.
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 @.claude/commands/analyze-ci-for-release-manager.md:
- Line 86: Step 6 contradicts Step 5's order; update the text in Step 6 so it
matches Step 5 by describing that the agent should present the summary first and
then display the file path (i.e., change any phrasing in "Step 6" that currently
says "path first then summary" to "summary first then path"), ensuring both
steps consistently require the file path be shown after the summary.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Organization UI (inherited)
Review profile: CHILL
Plan: Pro
Run ID: 30242711-cd88-4207-898a-82a81f9401bd
📒 Files selected for processing (1)
.claude/commands/analyze-ci-for-release-manager.md
|
@ggiguash: This pull request explicitly references no jira issue. DetailsIn response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the openshift-eng/jira-lifecycle-plugin repository. |
ggiguash
force-pushed
the
claude-settings-update
branch
from
0277e95 to
d66153c
Compare
ggiguash
changed the title
openshift-ci
bot
added
the
do-not-merge/work-in-progress
|
@coderabbitai perform full review |
|
✅ Actions performedFull review triggered. |
There was a problem hiding this comment.
🧹 Nitpick comments (1)
.claude/commands/file-bugs-for-analyze-ci.md (1)
38-49: Add language identifiers to fenced code blocks (MD040).Multiple fenced blocks are unlabeled; this is tripping markdownlint and hurts editor rendering/tooling.
Proposed pattern (apply similarly to all unlabeled fences)
-``` +```text --- STRUCTURED SUMMARY --- SEVERITY: <1-5> ... --- END STRUCTURED SUMMARY ----
+json
{
severity: number,
...
}-``` +```text DRY-RUN SUMMARY Total job files parsed: N ...</details> Also applies to: 78-91, 125-130, 134-140, 163-173, 178-191, 205-248, 279-313, 316-345, 365-370 <details> <summary>🤖 Prompt for AI Agents</summary>Verify each finding against the current code and only fix it if needed.
In @.claude/commands/file-bugs-for-analyze-ci.md around lines 38 - 49, Add
explicit language identifiers to all unlabeled fenced code blocks in the
markdown (e.g., the block starting with "--- STRUCTURED SUMMARY ---", the
JSON-like example block, and the "DRY-RUN SUMMARY" block) so markdownlint MD040
is satisfied and editors render correctly; replace plainwith appropriate fences such astext for plain summaries and ```json for JSON-like examples,
and apply the same change to the other unlabeled fences referenced (blocks
around lines that include STRUCTURED SUMMARY, DRY-RUN SUMMARY and the other
similar examples).</details> </blockquote></details> </blockquote></details> <details> <summary>🤖 Prompt for all review comments with AI agents</summary>Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In @.claude/commands/file-bugs-for-analyze-ci.md:
- Around line 38-49: Add explicit language identifiers to all unlabeled fenced
code blocks in the markdown (e.g., the block starting with "--- STRUCTURED
SUMMARY ---", the JSON-like example block, and the "DRY-RUN SUMMARY" block) so
markdownlint MD040 is satisfied and editors render correctly; replace plainwith appropriate fences such astext for plain summaries and ```json for
JSON-like examples, and apply the same change to the other unlabeled fences
referenced (blocks around lines that include STRUCTURED SUMMARY, DRY-RUN SUMMARY
and the other similar examples).</details> --- <details> <summary>ℹ️ Review info</summary> <details> <summary>⚙️ Run configuration</summary> **Configuration used**: Repository YAML (base), Organization UI (inherited) **Review profile**: CHILL **Plan**: Pro **Run ID**: `c2938ac2-a96a-4798-ad12-1cd8d120f3a2` </details> <details> <summary>📥 Commits</summary> Reviewing files that changed from the base of the PR and between 9935fb87ed99da496524271cc87e3379e7f054ef and 809301ffe6b33a869dab5f2078179ded728246f0. </details> <details> <summary>📒 Files selected for processing (4)</summary> * `.claude/agents/openshift-ci-analysis.md` * `.claude/commands/analyze-ci-for-release-manager.md` * `.claude/commands/file-bugs-for-analyze-ci.md` * `.gitignore` </details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
ggiguash
force-pushed
the
claude-settings-update
branch
from
809301f to
a88b549
Compare
openshift-ci
bot
removed
the
do-not-merge/work-in-progress
|
@coderabbitai perform full review |
|
✅ Actions performedFull review triggered. |
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (3)
.claude/commands/create-bugs-for-analyze-ci.md (1)
118-147: LGTM! Comprehensive duplicate search strategy.The dual test-ID search (lines 133-140) accounts for Jira's tokenization quirks. Lines 141-142's explanation prevents future simplification that would miss duplicates. Parallel execution note (line 147) aids performance.
Optional: "run ALL of the following" (line 120) → "run ALL the following" for conciseness.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/commands/create-bugs-for-analyze-ci.md around lines 118 - 147, Change the phrase "run ALL of the following" to the more concise "run ALL the following" in the Step 5 header/intro text; locate the string "run ALL of the following searches. Each search is MANDATORY — do not skip any." and update it to the shorter wording while keeping the surrounding emphasis and mandatory instruction intact (Search A / Search B sections and the note about parallel execution remain unchanged)..claude/commands/analyze-ci-for-release-manager.md (1)
68-75: LGTM! Checkpoint ensures proper synchronization.The explicit wait instruction prevents race conditions when collecting agent artifacts. Numbering updated correctly.
Optional refinement: "analyses" (line 69) uses British spelling while the command and skill names use American "analyze". Consider "After all analyses complete" → "After all analysis tasks complete" for consistency.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/commands/analyze-ci-for-release-manager.md around lines 68 - 75, Replace the phrase "After all analyses complete" with "After all analysis tasks complete" to match the American "analyze" naming used elsewhere and ensure consistency across the command/skill wording; update the sentence in the checklist entry that currently reads "After all analyses complete" (the checklist step following the IMPORTANT wait) to read "After all analysis tasks complete"..claude/agents/openshift-ci-analysis.md (1)
107-127: LGTM! Machine-readable contract enables downstream automation.The STRUCTURED SUMMARY block (lines 108-121) provides the required fields for
.claude/commands/create-bugs-for-analyze-ci.mdto filter and deduplicate bugs. ERROR_SIGNATURE guidance (lines 123-127) with examples ensures consistent formatting.Optional: Add language spec to fenced block at line 110 (
textorproperties) to satisfy markdown linters, though the generic format is clear.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/agents/openshift-ci-analysis.md around lines 107 - 127, Append the required machine-readable STRUCTURED SUMMARY block at the very end of the report (after all prose) and ensure it contains the exact fields SEVERITY, STACK_LAYER, STEP_NAME, ERROR_SIGNATURE, INFRASTRUCTURE_FAILURE, JOB_URL, JOB_NAME, and RELEASE as shown in the diff; populate ERROR_SIGNATURE with a concise one-line root-cause identifier suitable for deduplication (e.g., "greenboot timeout waiting for MicroShift to start"), set INFRASTRUCTURE_FAILURE to true only when STACK_LAYER is "AWS Infra" or the failure is CI/infrastructure-related, ensure JOB_URL is the full prow URL and JOB_NAME and RELEASE are extracted from that URL, and optionally tag the fenced block with a language like "text" or "properties" to satisfy markdown linters.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/commands/create-bugs-for-analyze-ci.md:
- Around line 227-229: The markdown contains a nested fenced code block where
the inner triple-backticks prematurely close the outer ```text fence; update the
inner fence to use four backticks (````) or otherwise escape it so it doesn't
terminate the outer block—specifically change the inner "```" instance (the
block labelled "<error details extracted...>") to "````" so the outer "```text"
fence remains intact and rendering is fixed.
---
Nitpick comments:
In @.claude/agents/openshift-ci-analysis.md:
- Around line 107-127: Append the required machine-readable STRUCTURED SUMMARY
block at the very end of the report (after all prose) and ensure it contains the
exact fields SEVERITY, STACK_LAYER, STEP_NAME, ERROR_SIGNATURE,
INFRASTRUCTURE_FAILURE, JOB_URL, JOB_NAME, and RELEASE as shown in the diff;
populate ERROR_SIGNATURE with a concise one-line root-cause identifier suitable
for deduplication (e.g., "greenboot timeout waiting for MicroShift to start"),
set INFRASTRUCTURE_FAILURE to true only when STACK_LAYER is "AWS Infra" or the
failure is CI/infrastructure-related, ensure JOB_URL is the full prow URL and
JOB_NAME and RELEASE are extracted from that URL, and optionally tag the fenced
block with a language like "text" or "properties" to satisfy markdown linters.
In @.claude/commands/analyze-ci-for-release-manager.md:
- Around line 68-75: Replace the phrase "After all analyses complete" with
"After all analysis tasks complete" to match the American "analyze" naming used
elsewhere and ensure consistency across the command/skill wording; update the
sentence in the checklist entry that currently reads "After all analyses
complete" (the checklist step following the IMPORTANT wait) to read "After all
analysis tasks complete".
In @.claude/commands/create-bugs-for-analyze-ci.md:
- Around line 118-147: Change the phrase "run ALL of the following" to the more
concise "run ALL the following" in the Step 5 header/intro text; locate the
string "run ALL of the following searches. Each search is MANDATORY — do not
skip any." and update it to the shorter wording while keeping the surrounding
emphasis and mandatory instruction intact (Search A / Search B sections and the
note about parallel execution remain unchanged).
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Organization UI (inherited)
Review profile: CHILL
Plan: Pro
Run ID: 5dd433ac-ca5b-4be4-bf08-662b1343562c
📒 Files selected for processing (4)
.claude/agents/openshift-ci-analysis.md.claude/commands/analyze-ci-for-release-manager.md.claude/commands/create-bugs-for-analyze-ci.md.gitignore
|
@coderabbitai perform full review |
|
✅ Actions performedFull review triggered. |
There was a problem hiding this comment.
Actionable comments posted: 5
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/agents/openshift-ci-analysis.md:
- Around line 53-56: The mktemp -d invocations (e.g., "mktemp -d
/tmp/analyze-ci-claude-workdir/openshift-ci-analysis-XXXX") can fail if the
parent directory doesn't exist; add an explicit mkdir -p
/tmp/analyze-ci-claude-workdir immediately before each mktemp -d call (both the
occurrence around the openshift-ci-analysis tempdir and the later similar
occurrence) so the parent workdir is created first, then call mktemp -d as
currently written.
- Around line 110-121: Add a language tag to the fenced code block containing
the STRUCTURED SUMMARY (the block that currently starts with ``` and the lines
beginning "--- STRUCTURED SUMMARY ---"); change the opening fence to include a
language such as "text" (i.e., use ```text) so the markdown linter accepts the
block.
In @.claude/commands/analyze-ci-for-release-manager.md:
- Around line 299-305: The doc contains conflicting notes about execution
ordering: remove the stale sequential-execution statements and keep the single
parallel model. Edit the section that mentions analyze-ci-for-release and
analyze-ci-for-pull-requests --rebase so it only states that all agents
(releases + PR analysis) are launched in parallel and remove the sentence(s)
claiming releases are analyzed sequentially or that the rebase PR analysis runs
after releases; ensure the text still notes that each release analysis launches
analyze-ci-for-release as an Agent (not a Skill) and that rebase PR analysis
uses analyze-ci-for-pull-requests --rebase.
In @.claude/commands/analyze-ci-for-release.md:
- Line 127: Update the summary filename example so both occurrences are
consistent: replace the plain "...summary.txt" example with the timestamped form
"analyze-ci-release-<release>-summary.<timestamp>.txt" so it matches the earlier
example "analyze-ci-release-<release>-summary.<timestamp>.txt"; ensure every
example of the summary filename (the one shown as "...summary.txt" and the
earlier line showing the timestamped example) uses the same "<timestamp>"
placeholder and formatting so they are identical across the document.
In @.claude/commands/create-bugs-for-analyze-ci.md:
- Line 383: Update the note that currently reads "This command does NOT run CI
analysis — it only consumes existing analysis files from
`/tmp/analyze-ci-claude-workdir/analyze-ci-claude-workdir`" to remove the
duplicated directory segment so the path becomes
`/tmp/analyze-ci-claude-workdir`; edit the string in the
.claude/commands/create-bugs-for-analyze-ci.md file where that exact sentence
appears.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Organization UI (inherited)
Review profile: CHILL
Plan: Pro
Run ID: d72aa923-95a0-4c25-9676-16aed6ef3404
📒 Files selected for processing (6)
.claude/agents/openshift-ci-analysis.md.claude/commands/analyze-ci-for-pull-requests.md.claude/commands/analyze-ci-for-release-manager.md.claude/commands/analyze-ci-for-release.md.claude/commands/create-bugs-for-analyze-ci.md.gitignore
|
@coderabbitai perform full review |
|
✅ Actions performedFull review triggered. |
|
@coderabbitai perform full review |
|
✅ Actions performedFull review triggered. |
There was a problem hiding this comment.
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 (1)
.claude/commands/analyze-ci-for-release-manager.md (1)
16-16:⚠️ Potential issue | 🟡 MinorDescription still says Skill-based flow, but steps are Agent-based.
Please update the Description to match the current Agent orchestration; otherwise readers get conflicting execution guidance.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/commands/analyze-ci-for-release-manager.md at line 16, The Description currently says "Skill-based flow" but the steps are orchestrated by an Agent; update the description text in the analyze-ci-for-release-manager document to state "Agent-based flow" (or equivalent Agent orchestration wording) and make the wording consistent with the commands referenced: analyze-ci-for-release and analyze-ci-for-pull-requests --rebase, and that the output is a consolidated HTML report with tabs for Periodics (per-release) and Pull Requests; ensure any remaining "skill" terminology is replaced with "agent" to avoid conflicting execution guidance.
♻️ Duplicate comments (1)
.claude/commands/create-bugs-for-analyze-ci.md (1)
235-237:⚠️ Potential issue | 🟡 MinorAdd a language tag to the nested inner fence to satisfy markdown lint.
The inner
````block under “Actual results” is unlabeled; make it````textto clear MD040 cleanly.Proposed diff
- ```` + ````text <error details extracted from the analysis text — the specific error message and relevant log context> ````🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/commands/create-bugs-for-analyze-ci.md around lines 235 - 237, The markdown inner fenced block under the "Actual results" section uses an unlabeled four-backtick fence; update that inner fence in .claude/commands/create-bugs-for-analyze-ci.md to include a language tag (e.g., change the opening ```` to ````text) so the block becomes ````text ... ```` and satisfies MD040; locate the inner fence by searching for the nested four-backtick block shown in the diff and add the "text" tag to the opening fence.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/commands/analyze-ci-for-release-manager.md:
- Around line 41-44: The steps are inconsistent: remove any implicit “wait” in
Step 2 and Step 3 so launching agents (Step 2) and noting their per-agent
summary paths (Step 3) are allowed to run concurrently, and move the global
synchronization point exclusively to Step 4 (“Wait until all the parallel agents
are complete”); update the same pattern in the other occurrences referenced (the
blocks around lines 54–59 and 68–69) so only Step 4 performs the join/await and
Steps 2–3 explicitly state parallel execution and per-agent reporting without
waiting.
---
Outside diff comments:
In @.claude/commands/analyze-ci-for-release-manager.md:
- Line 16: The Description currently says "Skill-based flow" but the steps are
orchestrated by an Agent; update the description text in the
analyze-ci-for-release-manager document to state "Agent-based flow" (or
equivalent Agent orchestration wording) and make the wording consistent with the
commands referenced: analyze-ci-for-release and analyze-ci-for-pull-requests
--rebase, and that the output is a consolidated HTML report with tabs for
Periodics (per-release) and Pull Requests; ensure any remaining "skill"
terminology is replaced with "agent" to avoid conflicting execution guidance.
---
Duplicate comments:
In @.claude/commands/create-bugs-for-analyze-ci.md:
- Around line 235-237: The markdown inner fenced block under the "Actual
results" section uses an unlabeled four-backtick fence; update that inner fence
in .claude/commands/create-bugs-for-analyze-ci.md to include a language tag
(e.g., change the opening ```` to ````text) so the block becomes ````text ...
```` and satisfies MD040; locate the inner fence by searching for the nested
four-backtick block shown in the diff and add the "text" tag to the opening
fence.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Organization UI (inherited)
Review profile: CHILL
Plan: Pro
Run ID: 470b0c6f-b4bb-49b7-b462-2ab56fa08329
📒 Files selected for processing (6)
.claude/agents/openshift-ci-analysis.md.claude/commands/analyze-ci-for-pull-requests.md.claude/commands/analyze-ci-for-release-manager.md.claude/commands/analyze-ci-for-release.md.claude/commands/create-bugs-for-analyze-ci.md.gitignore
ggiguash
changed the title
|
@coderabbitai perform full review |
|
✅ Actions performedFull review triggered. |
There was a problem hiding this comment.
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 @.claude/commands/analyze-ci-for-release-manager.md:
- Line 113: Update the sentence that lists "Finished" among parsed structured
fields to clarify that the Finished value is not part of the structured summary
block but is extracted from a separate "Finished:" line elsewhere in the per-job
file; reference the structured fields (SEVERITY, INFRASTRUCTURE_FAILURE,
ERROR_SIGNATURE, JOB_NAME, JOB_URL) and the token "Finished:" so readers know
Finished is parsed separately (as already noted earlier in the document).
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Organization UI (inherited)
Review profile: CHILL
Plan: Pro
Run ID: 5eb8b183-f829-4047-a98f-3cb64f8591f7
📒 Files selected for processing (6)
.claude/agents/openshift-ci-analysis.md.claude/commands/analyze-ci-create-bugs-for-release.md.claude/commands/analyze-ci-for-pull-requests.md.claude/commands/analyze-ci-for-release-manager.md.claude/commands/analyze-ci-for-release.md.gitignore
|
@ggiguash: all tests passed! Full PR test history. Your PR dashboard. DetailsInstructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here. |
openshift-ci
bot
added
the
do-not-merge/work-in-progress
2 participants
Summary
Implement a new
analyze-ci-create-bugs-for-releaseClaude skill, which uses the output ofopenshift-ci-analysisagent and creates bugs in the USHIFT project. The default mode isdry-rununless the--createflag is specified.Example
The USHIFT-6740 bug was created using the
/create-bugs-for-analyze-ci main --createcommand.The USHIFT-6741 bug was created using the
/create-bugs-for-analyze-ci 4.22 --createcommand.Additional enhancements
@openshift-ci-analysisagent needs allowed tools to run smoothly.@openshift-ci-analysisagent so that is can be used by other skills..workdirectory which is created by/jira:resolveClaude command fromai-helpersanalyze-ci-for-release-managerwaits with HTML generation until all agents finish/tmp/analyze-ci-claude-workdir