ci: self-hosted Rust + dual Qodana + Docker/devcontainer + telemetry + qlty + Codacy - #1
Conversation
Run fmt, clippy (-D warnings), and workspace tests on the self-hosted Linux/X64/ryzen runner. Pin channel=stable via rust-toolchain.toml and dtolnay/rust-toolchain@stable. Include clippy cleanups needed for a green gate (WireMsg box, NodeHealthInput, lines map_while, etc.).
🤖 CodeAnt AI — Review Status
|
Thanks for using CodeAnt! 🎉We're free for open-source projects. if you're enjoying it, help us grow by sharing. Share on X · |
|
We've triggered an ultrareview automatically — This large refactor (778 lines across 25 files) touches core mining telemetry logic, data parsing, and adds critical CI infrastructure; subtle bugs in let-chain conversions or I/O handling could break production telemetry.. I'll post findings when complete. An ultrareview is cubic's deepest review, catching hard-to-find bugs in the most critical PRs. It runs a longer, multi-pass analysis using cubic's most capable review models, and typically takes around 30 minutes. It consumes your team's reviewed-lines allowance at 3× the standard rate. Automated ultrareviews are disabled by default. We triggered this run as part of your trial. Want cubic to do this for every high-risk PR? Enable auto-ultrareview in your settings. |
|
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:
📝 WalkthroughWalkthroughThe pull request adds Rust toolchain, container, and CI configuration, changes telemetry wire and node-health APIs, updates collectors and miners to use those APIs, and refactors process readers, supervisor logic, harvesting utilities, and development documentation. ChangesTelemetry and mining runtime
Estimated code review effort: 4 (Complex) | ~45 minutes Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 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 |
codeant-ai
Bot
added
the
size:L
![amazon-q-developer[bot]](https://avatars.github.com/in/1220912?s=60&v=4){kind=small}
There was a problem hiding this comment.
This PR adds GitHub Actions CI infrastructure and applies clippy/formatting fixes to make the codebase pass cargo fmt --check and cargo clippy -D warnings. The changes are appropriate for enabling CI gates on a self-hosted runner. All modifications are code quality improvements (import ordering, let-chain syntax, boxing large enum variants) that resolve clippy warnings without altering program logic.
You can now have the agent implement changes and create commits directly on your pull request's source branch. Simply comment with /q followed by your request in natural language to ask the agent to make changes.
![codeant-ai[bot]](https://avatars.github.com/in/646884?s=60&v=4){kind=small}
![chatgpt-codex-connector[bot]](https://avatars.github.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 9071d68d9f
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
![coderabbitai[bot]](https://avatars.github.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 5
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.github/workflows/ci.yml:
- Around line 20-23: Add least-privilege token permissions to the `check`
workflow job by declaring `permissions` with only `contents: read` access. Keep
the existing job steps and runner configuration unchanged unless they require an
explicitly documented additional permission.
- Line 29: Update the workflow’s third-party action references, including
actions/checkout, dtolnay/rust-toolchain, and Swatinem/rust-cache, to full
reviewed commit SHA pins, using Dependabot or Renovate for the pin updates.
Preserve the Rust stable channel as the rust-toolchain action’s
input/configuration value.
- Around line 9-10: Update the pull_request workflow configuration in ci.yml so
fork-originated pull requests do not execute on the persistent self-hosted ryzen
runner; route them to a GitHub-hosted ephemeral runner or require manual
approval before self-hosted execution, while preserving validation for trusted
pull requests.
- Around line 28-29: Update the Checkout step using actions/checkout@v4 to set
persist-credentials to false, unless a later workflow step explicitly requires
Git authentication; preserve the existing step order and behavior otherwise.
In `@crates/theseus-mining/src/bin/harvest_miners.rs`:
- Line 95: Update the line-reading loop in main so file read errors from
reader.lines() are not discarded by map_while(Result::ok). Propagate the Result
through the harvest flow or explicitly handle and report each error, ensuring
main returns failure when telemetry reading is incomplete rather than silently
succeeding.
🪄 Autofix (Beta)
❌ Autofix failed (check again to retry)
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: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 02c792ec-8827-408b-8f9f-315c4d90af32
📒 Files selected for processing (25)
.github/workflows/ci.ymlcrates/mining-telemetry-core/src/lib.rscrates/mining-telemetry-core/src/schema.rscrates/telemetry-collector/src/sources/dynex.rscrates/telemetry-collector/src/sources/hwmon.rscrates/telemetry-collector/src/sources/kaspa.rscrates/telemetry-collector/src/sources/monero.rscrates/telemetry-collector/src/sources/quai.rscrates/telemetry-collector/src/sources/qubic.rscrates/telemetry-collector/src/sources/rapl.rscrates/telemetry-collector/src/writer.rscrates/theseus-mining/src/bin/harvest_miners.rscrates/theseus-mining/src/bin/harvest_nodes.rscrates/theseus-mining/src/dynex_miner.rscrates/theseus-mining/src/gpu_scheduler.rscrates/theseus-mining/src/kaspa_miner.rscrates/theseus-mining/src/lib.rscrates/theseus-mining/src/main.rscrates/theseus-mining/src/miner.rscrates/theseus-mining/src/mining_supervisor.rscrates/theseus-mining/src/monero_miner.rscrates/theseus-mining/src/quai_miner.rscrates/theseus-mining/src/qubic_miner.rscrates/theseus-mining/src/verus_miner.rsrust-toolchain.toml
📜 Review details
⏰ Context from checks skipped due to timeout. (1)
- GitHub Check: cubic · AI code reviewer
🧰 Additional context used
🪛 actionlint (1.7.12)
.github/workflows/ci.yml
[error] 24-24: label "ryzen" is unknown. available labels are "windows-latest", "windows-latest-8-cores", "windows-2025", "windows-2025-vs2026", "windows-2022", "windows-11-arm", "ubuntu-slim", "ubuntu-latest", "ubuntu-latest-4-cores", "ubuntu-latest-8-cores", "ubuntu-latest-16-cores", "ubuntu-24.04", "ubuntu-24.04-arm", "ubuntu-22.04", "ubuntu-22.04-arm", "macos-latest", "macos-latest-xlarge", "macos-latest-large", "macos-26-intel", "macos-26-xlarge", "macos-26-large", "macos-26", "macos-15-intel", "macos-15-xlarge", "macos-15-large", "macos-15", "macos-14-xlarge", "macos-14-large", "macos-14", "self-hosted", "x64", "arm", "arm64", "linux", "macos", "windows". if it is a custom label for self-hosted runner, set list of labels in actionlint.yaml config file
(runner-label)
🪛 zizmor (1.28.0)
.github/workflows/ci.yml
[warning] 28-29: credential persistence through GitHub Actions artifacts (artipacked): does not set persist-credentials: false
(artipacked)
[error] 29-29: unpinned action reference (unpinned-uses): action is not pinned to a hash (required by blanket policy)
(unpinned-uses)
[error] 32-32: unpinned action reference (unpinned-uses): action is not pinned to a hash (required by blanket policy)
(unpinned-uses)
[error] 43-43: unpinned action reference (unpinned-uses): action is not pinned to a hash (required by blanket policy)
(unpinned-uses)
[info] 32-32: action functionality is already included by the runner (superfluous-actions): use rustup and/or cargo in a script step
(superfluous-actions)
🔇 Additional comments (25)
crates/mining-telemetry-core/src/lib.rs (1)
4-6: LGTM!Also applies to: 209-223, 386-397
crates/mining-telemetry-core/src/schema.rs (1)
110-124: LGTM!Also applies to: 182-297, 307-307, 346-374, 472-479, 516-520
crates/telemetry-collector/src/writer.rs (1)
1-1: LGTM!Also applies to: 50-58
crates/theseus-mining/src/miner.rs (1)
8-8: LGTM!Also applies to: 84-99, 157-157, 168-168, 189-189, 270-273, 303-364
crates/theseus-mining/src/dynex_miner.rs (1)
4-4: LGTM!Also applies to: 101-102, 119-119
crates/theseus-mining/src/kaspa_miner.rs (1)
4-4: LGTM!Also applies to: 95-95, 114-122
crates/theseus-mining/src/monero_miner.rs (1)
4-4: LGTM!Also applies to: 128-128, 149-156
crates/theseus-mining/src/qubic_miner.rs (1)
33-33: LGTM!Also applies to: 409-417, 495-498, 535-538, 589-599, 617-624, 648-657
crates/theseus-mining/src/verus_miner.rs (1)
4-4: LGTM!Also applies to: 151-158
crates/telemetry-collector/src/sources/dynex.rs (1)
2-2: LGTM!Also applies to: 26-30
crates/telemetry-collector/src/sources/kaspa.rs (1)
2-2: LGTM!Also applies to: 32-36
crates/telemetry-collector/src/sources/monero.rs (1)
2-3: LGTM!Also applies to: 44-52
crates/telemetry-collector/src/sources/quai.rs (1)
2-3: LGTM!Also applies to: 20-34
crates/telemetry-collector/src/sources/qubic.rs (1)
2-2: LGTM!Also applies to: 28-33
crates/telemetry-collector/src/sources/hwmon.rs (1)
1-1: LGTM!Also applies to: 17-20
crates/telemetry-collector/src/sources/rapl.rs (1)
1-1: LGTM!crates/theseus-mining/src/quai_miner.rs (1)
10-10: LGTM!Also applies to: 43-46, 248-248, 304-307
rust-toolchain.toml (1)
1-4: LGTM!.github/workflows/ci.yml (2)
24-24: 🩺 Stability & AvailabilityVerify the custom
ryzenrunner label.Ensure an online runner is registered with
self-hosted, Linux, x64, andryzenlabels; otherwise this job will remain queued. If actionlint is used in validation, add the custom label to its configuration.Source: Linters/SAST tools
1-8: LGTM!Also applies to: 12-18, 36-40, 47-54
crates/theseus-mining/src/mining_supervisor.rs (1)
82-87: LGTM!Also applies to: 209-209, 419-423
crates/theseus-mining/src/gpu_scheduler.rs (1)
16-20: LGTM!Also applies to: 171-180
crates/theseus-mining/src/lib.rs (1)
2-5: LGTM!crates/theseus-mining/src/main.rs (1)
23-28: LGTM!Also applies to: 132-139, 215-223, 363-363
crates/theseus-mining/src/bin/harvest_nodes.rs (1)
23-33: LGTM!Also applies to: 91-93, 113-113, 146-148, 232-239
![cubic-dev-ai[bot]](https://avatars.github.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
Ultrareview completed in 14m 21s
All reported issues were addressed across 25 files
Reply with feedback, questions, or to request a fix.
Fix all with cubic | Re-trigger cubic
Extend PR with source-only .devcontainer image, docker.yml (build + cargo test smoke on self-hosted), and README notes for ShipOfTheseus runner labels and svc.sh. Completes the single CI PR surface.
rmems
changed the title
rmems
added
area:ci
rmems
added
size:XL
|
Note Autofix is a beta feature. Expect some limitations and changes as we gather feedback and continue to improve it. The branch was updated while autofix was in progress. Please try again. |
|
I've fixed both issues from the PR review: Fixed Issues
Changes Made
Pushed commits to |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: f81da7f1c8
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
- Add assertion to detect_binary_env_override test to verify KASPA_MINER_CMD override - Handle stdout read errors explicitly and continue processing instead of stopping
There was a problem hiding this comment.
Actionable comments posted: 5
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.devcontainer/Dockerfile:
- Around line 22-29: Update the Dockerfile shell setup surrounding the rustup
installer pipeline to enable pipefail before the curl-to-sh command, ensuring a
curl failure causes the RUN step to fail. Preserve the existing rustup arguments
and version checks.
- Around line 6-9: Update the Dockerfile setup after Rust/Cargo installation to
recursively change ownership of the directories referenced by CARGO_HOME and
RUSTUP_HOME to vscode:vscode, ensuring both locations are writable by the
devcontainer user and raw Docker test users.
In @.github/workflows/docker.yml:
- Around line 45-58: Update the “Build dev image” and “Smoke — cargo test inside
image” workflow steps to clean up the tagged image, dangling layers, and build
cache after execution on the persistent runner. Add an explicit bounded
retention/prune policy while preserving the existing build and cargo test
behavior.
- Around line 39-40: Update the Checkout step’s actions/checkout reference to
the approved immutable 40-character commit SHA instead of the movable v4 tag,
preserving the existing workflow step and action behavior.
- Around line 39-40: Update the actions/checkout step to set persist-credentials
to false, and add a workflow-level permissions configuration granting only
contents: read. Preserve the existing checkout behavior and avoid adding broader
permissions or authenticated Git operations.
🪄 Autofix (Beta)
✅ Autofix completed
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 03220f65-57ff-436f-8d92-22e6b0aa5bfa
📒 Files selected for processing (4)
.devcontainer/Dockerfile.devcontainer/devcontainer.json.github/workflows/docker.ymlREADME.md
📜 Review details
⏰ Context from checks skipped due to timeout. (1)
- GitHub Check: cubic · AI code reviewer
⚠️ CI failures not shown inline (2)
GitHub Actions: CI / fmt · clippy · test: ci: Rust + Docker workflows, devcontainer, self-hosted runner
Conclusion: failure
ntal/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6grwvpq1uxvzdnpp74yqa95fw.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6hdd72qaydhusrx06avdavnl0.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6orpz5lge7jr3ftamjz3v67lg.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6p5tlpadp4vcx2pxpimoxlniu.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6t4v0hupntt3g08zy9o92bbik.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7316sb0du8k9j5xdvk5f4s6ik.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/747q3hc36rv6pg02oxc4bkhsm.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7jj85weswvfodnl1lqhpmvybo.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7l8wvq8c6d7uxoe93c6gr6jf7.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7ntf8kdm10jyargd0at9vhjp9.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7yfba0doit6a7scy4h1fawzhv.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_co...
GitHub Actions: CI / 0_fmt · clippy · test.txt: ci: Rust + Docker workflows, devcontainer, self-hosted runner
Conclusion: failure
ntal/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6grwvpq1uxvzdnpp74yqa95fw.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6hdd72qaydhusrx06avdavnl0.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6orpz5lge7jr3ftamjz3v67lg.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6p5tlpadp4vcx2pxpimoxlniu.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/6t4v0hupntt3g08zy9o92bbik.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7316sb0du8k9j5xdvk5f4s6ik.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/747q3hc36rv6pg02oxc4bkhsm.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7jj85weswvfodnl1lqhpmvybo.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7l8wvq8c6d7uxoe93c6gr6jf7.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7ntf8kdm10jyargd0at9vhjp9.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_collector-1ocfjh7x6uhx6/s-hku7khwuuq-1d5ap3i-7y8er3bj8ptg2u8385259hypu/7yfba0doit6a7scy4h1fawzhv.o: Permission denied
warning: failed to remove target/debug/incremental/telemetry_co...
🧰 Additional context used
🪛 actionlint (1.7.12)
.github/workflows/docker.yml
[error] 35-35: label "ryzen" is unknown. available labels are "windows-latest", "windows-latest-8-cores", "windows-2025", "windows-2025-vs2026", "windows-2022", "windows-11-arm", "ubuntu-slim", "ubuntu-latest", "ubuntu-latest-4-cores", "ubuntu-latest-8-cores", "ubuntu-latest-16-cores", "ubuntu-24.04", "ubuntu-24.04-arm", "ubuntu-22.04", "ubuntu-22.04-arm", "macos-latest", "macos-latest-xlarge", "macos-latest-large", "macos-26-intel", "macos-26-xlarge", "macos-26-large", "macos-26", "macos-15-intel", "macos-15-xlarge", "macos-15-large", "macos-15", "macos-14-xlarge", "macos-14-large", "macos-14", "self-hosted", "x64", "arm", "arm64", "linux", "macos", "windows". if it is a custom label for self-hosted runner, set list of labels in actionlint.yaml config file
(runner-label)
🪛 Checkov (3.3.8)
.devcontainer/Dockerfile
[low] 1-34: Ensure that HEALTHCHECK instructions have been added to container images
(CKV_DOCKER_2)
[low] 1-34: Ensure that a user for the container has been created
(CKV_DOCKER_3)
🪛 Hadolint (2.14.0)
.devcontainer/Dockerfile
[warning] 11-11: Pin versions in apt get install. Instead of apt-get install <package> use apt-get install <package>=<version>
(DL3008)
[warning] 22-22: Set the SHELL option -o pipefail before RUN with a pipe in it. If you are using /bin/sh in an alpine image or if your shell is symlinked to busybox then consider explicitly setting your SHELL to /bin/ash, or disable this check
(DL4006)
🪛 Trivy (0.72.0)
.devcontainer/Dockerfile
[error] 1-1: Image user should not be 'root'
Specify at least 1 USER command in Dockerfile with non-root user as argument
Rule: DS-0002
(IaC/Dockerfile)
[info] 1-1: No HEALTHCHECK defined
Add HEALTHCHECK instruction in your Dockerfile
Rule: DS-0026
(IaC/Dockerfile)
🪛 zizmor (1.28.0)
.github/workflows/docker.yml
[warning] 39-40: credential persistence through GitHub Actions artifacts (artipacked): does not set persist-credentials: false
(artipacked)
[error] 40-40: unpinned action reference (unpinned-uses): action is not pinned to a hash (required by blanket policy)
(unpinned-uses)
🔇 Additional comments (6)
.devcontainer/Dockerfile (1)
1-5: LGTM!Also applies to: 11-20, 31-34
.devcontainer/devcontainer.json (1)
1-33: LGTM!.github/workflows/docker.yml (3)
15-23: 🔒 Security & PrivacySecurity Misconfiguration (CWE-693)
Reachability: External
Verify that untrusted PRs are allowed on this self-hosted runner.
This
pull_requestworkflow executes PR-controlled Dockerfile and Rust code on the persistent[self-hosted, Linux, X64, ryzen]runner. If external contributors can open PRs, use an isolated/ephemeral runner or gate this job with approval; container isolation alone should not be treated as runner isolation.Also applies to: 32-36
1-14: LGTM!Also applies to: 25-30, 42-43
45-50: 🎯 Functional CorrectnessNo change needed for this cache concern.
GitHub Actions runners are ephemeral per job, and Docker layers are cache-invalidated when instructions or their inputs change;
rust-toolchain.tomlcontent changes propagate to laterrustup/check layers through normal Docker cache invalidation.--pulldoes not invalidate RUN layers, and--no-cachewould remove Docker’s normal build-speed benefit.> Likely an incorrect or invalid review comment.README.md (1)
82-93: LGTM!Also applies to: 95-100, 106-124
rmems
changed the title
There was a problem hiding this comment.
All reported issues were addressed across 2 files (changes from recent commits).
Tip: Review your code locally with the cubic CLI to iterate faster.
Fix all with cubic | Re-trigger cubic
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: baaddc7fbe
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
- kill_process_group probes the process group (not only the leader) so workers that outlive SIGTERM still get SIGKILL - Track native_kind/gpu_enabled on Qubic Running state; Yield/Resume only restart GPU-enabled qubic-core (qli-Client is CPU-only)
There was a problem hiding this comment.
All reported issues were addressed across 2 files (changes from recent commits).
Tip: Review your code locally with the cubic CLI to iterate faster.
Fix all with cubic | Re-trigger cubic
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 58be67d059
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
YieldForChat passes false to free VRAM, but spawn re-read AIGARTH_ENABLED from the environment and relaunched with --gpu. Use the argument for --gpu, thread defaults, and gpu_enabled state.
|
Receiving-code-review note (Grok Build: Grok 4.5) Verified cubic review-body P1 on
Fix in c75e6ef: Waiting for Codex on this head before any further push. |
There was a problem hiding this comment.
All reported issues were addressed across 1 file (changes from recent commits).
Tip: Review your code locally with the cubic CLI to iterate faster.
Fix all with cubic | Re-trigger cubic
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c75e6ef0c8
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Extract native_core_cli_args / native_gpu_enabled so aigarth=false omits --gpu and aigarth=true includes it without spawning a process.
|
@codex review Please review head — Grok Build: Grok 4.5 |
|
Codex Review: Didn't find any major issues. What shall we delve into next? Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
Keep neuromorphic/training design packages out of the mining-strict tree.
…detect Keep miner Running until the process group exits so shell wrappers cannot orphan workers under a premature Idle; require shebang/ELF headers for usable binaries; run qli-Client from its distribution directory; source cargo env only when present; preinstall rust-src and rust-analyzer in the devcontainer image.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7c939be0df
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
There was a problem hiding this comment.
5 issues found across 5 files (changes from recent commits).
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="crates/theseus-mining/src/miner.rs">
<violation number="1" location="crates/theseus-mining/src/miner.rs:64">
P2: A miner can remain permanently `Running` after its leader exits if a wrapper leaves a zombie in the process group: `kill(-pgid, 0)` still reports that group as present, but this reaper has no deadline or recovery path. A bounded group-drain policy (with explicit timeout handling/cleanup) would prevent a stale reaper thread and stale miner state when the group cannot disappear.</violation>
<violation number="2" location="crates/theseus-mining/src/miner.rs:180">
P3: Binary detection performs redundant placeholder parsing: every recognized placeholder is already rejected by `looks_like_executable_header`. Consider removing this call and `is_download_placeholder` to keep the validation path single-purpose and allocation-free.</violation>
<violation number="3" location="crates/theseus-mining/src/miner.rs:211">
P2: Miner startup can fail instead of falling back when a truncated download retains `\x7fELF`, because this four-byte check marks it usable and shadows later candidates. Validate the ELF class, encoding, version, header length, and `ET_EXEC`/`ET_DYN` type before accepting it.</violation>
</file>
<file name="crates/theseus-mining/src/qubic_miner.rs">
<violation number="1" location="crates/theseus-mining/src/qubic_miner.rs:706">
P1: Qubic fails to start when `qli-Client` is discovered through PATH: `Path::new("qli-Client").parent()` is an empty path, so `current_dir(parent)` attempts to chdir to `""` and `command.spawn()` fails. The launch directory adjustment could skip an empty parent, while resolving relative paths to an absolute executable path before changing directories would also preserve the intended adjacent-content behavior.</violation>
<violation number="2" location="crates/theseus-mining/src/qubic_miner.rs:804">
P2: After the process group fully exits and state transitions to Idle here, the previously tracked child_pid used by Stop/kill_native isn't cleared. If the OS reuses that PID as a process-group ID before the next Stop is issued, kill_native could send SIGTERM/SIGKILL to an unrelated process. Consider clearing the tracked PID as part of this reap path, or validate that state is still Running with a matching PID before signaling in Stop.</violation>
</file>
Tip: instead of fixing issues one by one fix them all with cubic
Tip: Review your code locally with the cubic CLI to iterate faster.
Re-trigger cubic
- Stop: only kill_native when state is still Running; clear stale child_pid - qli launch: skip empty parent; canonicalize PATH-only binaries for cwd - wait_process_group_exit: 30s bound + SIGKILL drain (no infinite reaper) - ELF detection: require class + ET_EXEC/ET_DYN (reject magic-only truncations) - devcontainer: cargo fetch/check --locked so hooks cannot rewrite Cargo.lock Grok Build: Grok 4.5
There was a problem hiding this comment.
2 issues found across 3 files (changes from recent commits).
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="crates/theseus-mining/src/miner.rs">
<violation number="1" location="crates/theseus-mining/src/miner.rs:75">
P1: Backgrounding launch wrappers now have their healthy miner worker terminated 30 seconds after the wrapper exits. `process_group_alive` cannot distinguish a live worker from a zombie/stuck worker, so SIGKILL should be reserved for an explicit stop or a liveness-aware cleanup path.</violation>
<violation number="2" location="crates/theseus-mining/src/miner.rs:237">
P3: On a big-endian deployment, executable detection rejects valid ELF miners because `e_type` is always decoded as little-endian. Decode bytes 16–17 according to `EI_DATA` and reject unknown encodings.</violation>
</file>
Tip: Review your code locally with the cubic CLI to iterate faster.
Fix all with cubic | Re-trigger cubic
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c470dff4df
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
- wait_process_group_exit returns bool; never SIGKILLs (Stop owns kill) - reapers leave Running when group still alive after timeout - which discovery returns absolute path; resolve_executable_path for qli cwd - ELF e_type decoded via EI_DATA (LE/BE) Grok Build: Grok 4.5
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 5afd85ef2a
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
There was a problem hiding this comment.
1 issue found across 3 files (changes from recent commits).
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="crates/theseus-mining/src/qubic_miner.rs">
<violation number="1" location="crates/theseus-mining/src/qubic_miner.rs:721">
P2: For qli-Client launches, `command.current_dir()` is set to the resolved binary's parent directory, but `Command::new(&binary)` is still given the original (relative) `binary` string. When `binary` is a relative path that includes a directory component (for example a `QUBIC_MINER_CMD` override such as `dist/qli-Client` or `bin/qli-Client`), the relative path is re-resolved against the new `current_dir`, i.e. the binary's own directory, so the directory component is applied twice and the spawned command resolves to a non-existent `dist/dist/qli-Client` — the miner fails to start. Absolute paths and bare PATH names are unaffected, so this only surfaces with relative-with-directory qli overrides. Use the resolved absolute path in `Command::new` (setting `current_dir` to its parent) so relative and PATH-only inputs both launch correctly.</violation>
</file>
Tip: Review your code locally with the cubic CLI to iterate faster.
Fix all with cubic | Re-trigger cubic
- .devin/blueprint: cargo fetch/clippy/test/build use --locked (match AGENTS.md) - qli: Command::new(resolved absolute) then current_dir(parent) so relative overrides like dist/qli-Client are not re-resolved as dist/dist/qli-Client Grok Build: Grok 4.5
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: d53c2e3d53
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| "{log_prefix} process group still alive after wait timeout \ | ||
| (PID {reaped_pid}); leaving Running so Stop can kill orphans" | ||
| ); | ||
| return; |
There was a problem hiding this comment.
When a supported shell wrapper exits while its worker remains alive for more than 30 seconds, this return permanently ends the only reaper while leaving the state Running; if the worker later exits naturally, subsequent Start commands are still ignored as “already running” even though the process group is gone. Fresh evidence beyond the prior reaper thread is that the timeout path now retains the PGID but never checks it again; keep monitoring asynchronously until the group disappears and then clear the matching state. The identical timeout return in the native Qubic reaper has the same problem.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
4 issues found across 4 files (changes from recent commits).
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="crates/theseus-mining/src/miner.rs">
<violation number="1" location="crates/theseus-mining/src/miner.rs:130">
P2: A miner whose wrapper exits first and whose worker runs past 30 seconds remains permanently `Running` after that worker later exits naturally, so subsequent `Start` commands are ignored. Keep a non-signaling watcher alive after timeout (in both generic and Qubic reapers) so state reaches `Idle` when the group disappears.</violation>
<violation number="2" location="crates/theseus-mining/src/miner.rs:237">
P2: A truncated ELF retaining only the first 18–51/63 bytes is accepted as usable because this check reads `e_type` without requiring a complete class-specific ELF header. Require at least 52 bytes for ELF32 or 64 for ELF64 so partial downloads do not win detection and then fail at spawn.</violation>
<violation number="3" location="crates/theseus-mining/src/miner.rs:293">
P3: When a relative binary path is supplied (e.g. `QUBIC_MINER_CMD=dist/qli-Client`) and `canonicalize` fails, `resolve_executable_path` falls back to returning the original relative path. The qli spawn path then runs `Command::new("dist/qli-Client")` after `current_dir("dist")`, so the child resolves it as `dist/dist/qli-Client` — the exact double-resolution failure this PR is meant to fix. The fallback should produce an absolute path (prepend the current working directory) so that returning a non-canonical path cannot be re-resolved against the new cwd.</violation>
</file>
<file name="crates/theseus-mining/src/qubic_miner.rs">
<violation number="1" location="crates/theseus-mining/src/qubic_miner.rs:830">
P2: A native miner whose leader exits while its process group survives the first 30 seconds remains `Running` forever after the workers later exit, so subsequent `Start` commands are ignored and `Stop` retains a stale PGID. Keep the reaper monitoring until the group disappears rather than returning after the first timeout.</violation>
</file>
Tip: Review your code locally with the cubic CLI to iterate faster.
Fix all with cubic | Re-trigger cubic
| if bytes.len() >= 18 && bytes[0..4] == [0x7f, b'E', b'L', b'F'] { | ||
| let class = bytes[4]; // 1 = ELFCLASS32, 2 = ELFCLASS64 | ||
| if class != 1 && class != 2 { | ||
| return false; | ||
| } |
There was a problem hiding this comment.
P2: A truncated ELF retaining only the first 18–51/63 bytes is accepted as usable because this check reads e_type without requiring a complete class-specific ELF header. Require at least 52 bytes for ELF32 or 64 for ELF64 so partial downloads do not win detection and then fail at spawn.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At crates/theseus-mining/src/miner.rs, line 237:
<comment>A truncated ELF retaining only the first 18–51/63 bytes is accepted as usable because this check reads `e_type` without requiring a complete class-specific ELF header. Require at least 52 bytes for ELF32 or 64 for ELF64 so partial downloads do not win detection and then fail at spawn.</comment>
<file context>
@@ -207,9 +232,22 @@ fn looks_like_executable_header(bytes: &[u8]) -> bool {
- return true;
+ // ELF: magic + class + e_type (ET_EXEC / ET_DYN). Rejects truncated
+ // downloads that only retain the 4-byte magic prefix.
+ if bytes.len() >= 18 && bytes[0..4] == [0x7f, b'E', b'L', b'F'] {
+ let class = bytes[4]; // 1 = ELFCLASS32, 2 = ELFCLASS64
+ if class != 1 && class != 2 {
</file context>
| if bytes.len() >= 18 && bytes[0..4] == [0x7f, b'E', b'L', b'F'] { | |
| let class = bytes[4]; // 1 = ELFCLASS32, 2 = ELFCLASS64 | |
| if class != 1 && class != 2 { | |
| return false; | |
| } | |
| if bytes.len() >= 18 && bytes[0..4] == [0x7f, b'E', b'L', b'F'] { | |
| let class = bytes[4]; // 1 = ELFCLASS32, 2 = ELFCLASS64 | |
| let min_header_len = match class { | |
| 1 => 52, | |
| 2 => 64, | |
| _ => return false, | |
| }; | |
| if bytes.len() < min_header_len { | |
| return false; | |
| } |
| // (setsid). Stay Running until the whole group is gone so Start cannot | ||
| // race a second miner and Stop can still kill orphans via the leader PGID. | ||
| // Do not SIGKILL here — that is reserved for explicit Stop. | ||
| let group_gone = wait_process_group_exit(reaped_pid); |
There was a problem hiding this comment.
P2: A miner whose wrapper exits first and whose worker runs past 30 seconds remains permanently Running after that worker later exits naturally, so subsequent Start commands are ignored. Keep a non-signaling watcher alive after timeout (in both generic and Qubic reapers) so state reaches Idle when the group disappears.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At crates/theseus-mining/src/miner.rs, line 130:
<comment>A miner whose wrapper exits first and whose worker runs past 30 seconds remains permanently `Running` after that worker later exits naturally, so subsequent `Start` commands are ignored. Keep a non-signaling watcher alive after timeout (in both generic and Qubic reapers) so state reaches `Idle` when the group disappears.</comment>
<file context>
@@ -109,7 +126,15 @@ pub fn reap_child(mut child: Child, state: Arc<Mutex<MinerState>>, log_prefix: &
// race a second miner and Stop can still kill orphans via the leader PGID.
- wait_process_group_exit(reaped_pid);
+ // Do not SIGKILL here — that is reserved for explicit Stop.
+ let group_gone = wait_process_group_exit(reaped_pid);
+ if !group_gone {
+ eprintln!(
</file context>
| "[qubic] process group still alive after wait timeout \ | ||
| (PID {reaped_pid}); leaving Running so Stop can kill orphans" | ||
| ); | ||
| return; |
There was a problem hiding this comment.
P2: A native miner whose leader exits while its process group survives the first 30 seconds remains Running forever after the workers later exit, so subsequent Start commands are ignored and Stop retains a stale PGID. Keep the reaper monitoring until the group disappears rather than returning after the first timeout.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At crates/theseus-mining/src/qubic_miner.rs, line 830:
<comment>A native miner whose leader exits while its process group survives the first 30 seconds remains `Running` forever after the workers later exit, so subsequent `Start` commands are ignored and `Stop` retains a stale PGID. Keep the reaper monitoring until the group disappears rather than returning after the first timeout.</comment>
<file context>
@@ -801,7 +820,15 @@ fn reap_child(mut child: Child, state: Arc<Mutex<QubicMinerState>>) {
+ "[qubic] process group still alive after wait timeout \
+ (PID {reaped_pid}); leaving Running so Stop can kill orphans"
+ );
+ return;
+ }
let mut s = state.lock().unwrap();
</file context>
| return; | |
| while !miner::wait_process_group_exit(reaped_pid) { | |
| eprintln!( | |
| "[qubic] process group remains alive (PID {reaped_pid}); continuing to monitor" | |
| ); | |
| } |
| pub fn resolve_executable_path(binary: &str) -> std::path::PathBuf { | ||
| let p = std::path::Path::new(binary); | ||
| if p.is_absolute() { | ||
| return std::fs::canonicalize(p).unwrap_or_else(|_| p.to_path_buf()); |
There was a problem hiding this comment.
P3: When a relative binary path is supplied (e.g. QUBIC_MINER_CMD=dist/qli-Client) and canonicalize fails, resolve_executable_path falls back to returning the original relative path. The qli spawn path then runs Command::new("dist/qli-Client") after current_dir("dist"), so the child resolves it as dist/dist/qli-Client — the exact double-resolution failure this PR is meant to fix. The fallback should produce an absolute path (prepend the current working directory) so that returning a non-canonical path cannot be re-resolved against the new cwd.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At crates/theseus-mining/src/miner.rs, line 293:
<comment>When a relative binary path is supplied (e.g. `QUBIC_MINER_CMD=dist/qli-Client`) and `canonicalize` fails, `resolve_executable_path` falls back to returning the original relative path. The qli spawn path then runs `Command::new("dist/qli-Client")` after `current_dir("dist")`, so the child resolves it as `dist/dist/qli-Client` — the exact double-resolution failure this PR is meant to fix. The fallback should produce an absolute path (prepend the current working directory) so that returning a non-canonical path cannot be re-resolved against the new cwd.</comment>
<file context>
@@ -234,18 +272,45 @@ pub fn detect_binary_paths(
+pub fn resolve_executable_path(binary: &str) -> std::path::PathBuf {
+ let p = std::path::Path::new(binary);
+ if p.is_absolute() {
+ return std::fs::canonicalize(p).unwrap_or_else(|_| p.to_path_buf());
+ }
+ if let Some(parent) = p.parent()
</file context>
| return std::fs::canonicalize(p).unwrap_or_else(|_| p.to_path_buf()); | |
| let abs = std::env::current_dir().unwrap_or_default().join(p); | |
| return std::fs::canonicalize(&abs).unwrap_or(abs); |
2 participants
User description
Summary
Single foundation PR for Theseus-Quarry (mining-strict multi-coin supervisor + ops telemetry JSONL): GitHub Actions, dual Qodana, Docker/devcontainer, local quality tooling (qlty + Codacy CLI), and mining/telemetry reliability fixes from review babysit.
.github/workflows/ci.yml— self-hosted[self-hosted, Linux, X64, ryzen](ShipOfTheseus):fmt,clippy -D warnings --locked,test --workspace --locked, workspacetarget/sanitize, local qodana · rust.github/workflows/code_quality.yml—JetBrains/qodana-actiononubuntu-latest+QODANA_TOKEN→https://qodana.cloud(fork-safe job gate)qodana.yaml—qodana-rust, excludesbinaries//target/.github/workflows/docker.yml— source-only build + non-root smoke (--user, named volume, pre-chown).devcontainer/*,.cursor/Dockerfile+environment.jsonrust-toolchain.toml(stable + rustfmt/clippy),scripts/setup-rust.sh.qlty/qlty.toml+ shellcheck/hadolint configs;.github/actionlint.yamlcustomryzenlabel.codacy/codacy.yaml(local CLI: lizard / opengrep / trivy) + root.codacy.ymlexcludesbinaries/**,target/**, etc.dotenv→dotenvy;reqwest0.11 → 0.12; openssl/anyhow bumpsNodeHealth(not zero-hashrateMinerPerf); TH/s ×1e6;is_usable_binary; harvest_nodes tilde + defaultdata/telemetry; stdout error resilience; env binary overridesNot in this PR (follow-ups): multi-GPU
GpuSchedulerdevice index; full stateful stdout parsers; Dependabot-specific Qodana skip (cubic P2); Codacy Cloud org connection (Membrane auth pending).Dual Qodana (important)
qodana · rustryzenjetbrains/qodana-rustimage — no Cloud tokenqodana/ Qodana for Rustubuntu-latestQODANA_TOKEN→ Qodana CloudCodacy
.codacy/codacy.yaml—mode: local, tools: lizard, opengrep, trivy.codacy.yml— excludesbinaries/**,target/**,.qodana/**, lockfile, markdown~/.cache/codacy/codacy-cli-v2/.../codacy-cli-v2—init/install/analyzecodacy-cli install codacy-cli analyze --tool trivy # skips gitignored binaries when .codacy.yml excludes applied by CloudNote: Local Trivy may still walk on-disk
binaries/unless skip-dirs is set in the local tools-configs (gitignored). Those paths are gitignored and must never be committed.Required secret
Repo Settings → Secrets and variables → Actions:
QODANA_TOKEN— from Qodana CloudWithout it, the Cloud Qodana workflow fails auth on GitHub-hosted runners.
Self-hosted runner
~/actions-runner/Theseus-Quarry-runnerself-hosted,Linux,X64,ryzenhead.repo.full_name == github.repository) — not for untrusted forksTest plan
cargo fmt/clippy -D warnings --locked/test --workspace --lockedubuntu-latest+ token)qlty checkclean after initcodacy-cli init+ slim tools +install+ trivy smokeReview / quality notes
config/**exclude scope, mine-*.sh error path text, hadolintDL3008— mostly P2/P3.enhancement,documentation,area:ci,area:devcontainer,priority:P1,size:XLAttribution
Commits and PR comments from babysit are signed Grok Build: Grok 4.5.
Source-only tree; no secrets/binaries in git.
.qodana/and largebinaries/remain gitignored. Telemetry is produced here for research consumers elsewhere (not neuromorphic reconfig).CodeAnt-AI Description
Make mining telemetry accurate and mining operations safer
What Changed
~, create output directories, use a usable default node output path, and continue when individual log lines cannot be read.Impact
✅ Correct hashrate units in telemetry✅ Fewer duplicate and zero-hashrate performance records✅ Safer GPU algorithm switching✅ Clearer miner startup failures💡 Usage Guide
Checking Your Pull Request
Every time you make a pull request, our system automatically looks through it. We check for security issues, mistakes in how you're setting up your infrastructure, and common code problems. We do this to make sure your changes are solid and won't cause any trouble later.
Talking to CodeAnt AI
Got a question or need a hand with something in your pull request? You can easily get in touch with CodeAnt AI right here. Just type the following in a comment on your pull request, and replace "Your question here" with whatever you want to ask:
This lets you have a chat with CodeAnt AI about your pull request, making it easier to understand and improve your code.
Example
Preserve Org Learnings with CodeAnt
You can record team preferences so CodeAnt AI applies them in future reviews. Reply directly to the specific CodeAnt AI suggestion (in the same thread) and replace "Your feedback here" with your input:
This helps CodeAnt AI learn and adapt to your team's coding style and standards.
Example
Retrigger review
Ask CodeAnt AI to review the PR again, by typing:
Check Your Repository Health
To analyze the health of your code repository, visit our dashboard at https://app.codeant.ai. This tool helps you identify potential issues and areas for improvement in your codebase, ensuring your repository maintains high standards of code health.