fix(deep-report): switch to claude engine and fix memory path#23807
Merged
fix(deep-report): switch to claude engine and fix memory path#23807
Conversation
Agent-Logs-Url: https://github.com/github/gh-aw/sessions/25965d10-64b5-4784-b7b3-c0ab26920b6d Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Agent-Logs-Url: https://github.com/github/gh-aw/sessions/25965d10-64b5-4784-b7b3-c0ab26920b6d Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Fix deep report to switch to Claude engine and resolve memory path
fix(deep-report): switch to claude engine and fix memory path
Apr 1, 2026
pelikhan
approved these changes
Apr 1, 2026
Contributor
There was a problem hiding this comment.
Pull request overview
Switches the DeepReport agent workflow from OpenAI Codex to Anthropic Claude Code to avoid recurring safety-classifier blocks, and corrects the repo-memory path so persisted insights are actually reused across runs.
Changes:
- Update DeepReport workflow engine from
codextoclaude(including secret validation, CLI install/exec, log parsing, and concurrency naming). - Fix DeepReport repo-memory instructions to use
/tmp/gh-aw/repo-memory/default/memory/deep-report/(matching the workflow’s repo-memory configuration). - Bump the pinned
github/gh-aw-actions/setupaction version and extend actions lock metadata for artifact actions.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| pkg/workflow/data/action_pins.json | Bumps github/gh-aw-actions/setup pin to v0.65.2 (new SHA). |
| .github/workflows/deep-report.md | Switches engine to Claude and corrects repo-memory read/write path in the prompt instructions. |
| .github/workflows/deep-report.lock.yml | Updates the compiled workflow to run Claude Code CLI (secrets, parsing, domains, concurrency, MCP config usage). |
| .github/aw/actions-lock.json | Adds lock entries for actions/download-artifact@v4 and actions/upload-artifact@v4. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The DeepReport workflow was failing due to OpenAI's safety classifier blocking cybersecurity-adjacent content, and agent memory writes were silently discarded due to a wrong path in the prompt instructions.
Changes
codex→claude— eliminates recurring OpenAI blocks triggered by phrases like "Detect suspicious patterns" / "Suspicious activity"/tmp/gh-aw/repo-memory-default/memory/default/→/tmp/gh-aw/repo-memory/default/memory/deep-report/— aligns with the compiled lock file'sGH_AW_MEMORY_DIRandFILE_GLOB_FILTER, so insights are actually persisted and reused across runs