Integrity verified v7.61 #26
Merged
Merged
Conversation
Co-authored-by: aider (gemini/gemini-2.5-flash) <aider@aider.chat>
…ol spec Co-authored-by: aider (gemini/gemini-2.5-flash) <aider@aider.chat>
Co-authored-by: aider (gemini/gemini-2.5-flash) <aider@aider.chat>
Co-authored-by: aider (gemini/gemma-4-31b-it) <aider@aider.chat>
Co-authored-by: aider (gemini/gemma-4-31b-it) <aider@aider.chat>
Co-authored-by: aider (gemini/gemma-4-31b-it) <aider@aider.chat>
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (6)
💤 Files with no reviewable changes (2)
✅ Files skipped from review due to trivial changes (2)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughThis PR upgrades the Intent Protocol to version 2.1, hardening the Discord worker script with improved reliability and validation, expanding worker security standards, aligning server implementation with specification changes (7KB payload limit, new version header), and updating infrastructure/test configuration to support the changes. ChangesProtocol v2.1 Upgrade and Worker Hardening
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3 | ❌ 2❌ Failed checks (1 warning, 1 inconclusive)
✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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 |
Owner
Author
|
@coderabbitai review |
Contributor
✅ Actions performedReview triggered.
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 5
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
Examples/discord_worker.sh (1)
201-204:⚠️ Potential issue | 🟠 Major | ⚡ Quick winURL-encode
GOALandNAMESPACEin the claim request.Line 201 builds the query string by concatenation. If either env var contains
&,?,=, spaces, or other reserved characters, the worker will claim the wrong queue or fail to claim at all.Suggested fix
- RESPONSE=$(curl -sS \ + RESPONSE=$(curl -sS \ --connect-timeout 5 \ --max-time "$CURL_TIMEOUT" \ -D - \ -w "\n__HTTP_CODE__:%{http_code}" \ - -X POST \ - "$BASE_URL/claim?goal=$GOAL&namespace=$NAMESPACE" \ + -X POST \ + --get \ + --data-urlencode "goal=$GOAL" \ + --data-urlencode "namespace=$NAMESPACE" \ + "$BASE_URL/claim" \ -H "X-API-KEY: $API_KEY" \ -H "X-Worker-ID: $WORKER_ID" \ -H "X-Worker-Capabilities: $CAPABILITIES")🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@Examples/discord_worker.sh` around lines 201 - 204, The claim request builds a query string by concatenating GOAL and NAMESPACE which must be URL-encoded; update the script so GOAL and NAMESPACE are URL-encoded before they are interpolated into the curl URL (e.g. create encoded variables like ENCODED_GOAL and ENCODED_NAMESPACE using a URL-encode helper or a short python/printf invocation) and then use those encoded variables in the curl GET (the section that constructs "$BASE_URL/claim?goal=$GOAL&namespace=$NAMESPACE"). Ensure the helper preserves empty values and uses percent-encoding for reserved characters.
🧹 Nitpick comments (2)
flask_app.py (1)
1582-1583: 💤 Low valueVerify that the result field size limit is documented in the specification.
The code enforces a 7KB limit on the
resultfield (usingMAX_PAYLOAD), but the SPEC.md only explicitly documents the size limit for thepayloadfield at line 139. Theresultfield description at SPEC.md line 164 does not mention a size constraint.Consider adding the size limit to the result field documentation in SPEC.md for completeness, or verify that line 717's "Payload field content limit: 7KB" is intended to cover both payload and result.
🤖 Prompt for 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. In `@flask_app.py` around lines 1582 - 1583, The code enforces MAX_PAYLOAD on the result content (check the len(result_text.encode()) > MAX_PAYLOAD check returning api_error("result_too_large")), but SPEC.md only documents the payload size; update SPEC.md to explicitly state that the 7KB MAX_PAYLOAD limit also applies to the "result" field (or clarify that the existing "Payload field content limit: 7KB" covers both payload and result), and reference the MAX_PAYLOAD constraint and the "result" field name so readers can correlate the spec with the runtime check.SPEC.md (1)
320-320: ⚡ Quick winClarify the two distinct scenarios that return HTTP 413.
The specification uses HTTP 413 for two different limits:
- Line 320: Total request body exceeding 8KB (Flask's
MAX_CONTENT_LENGTH)- Line 658: The
payloadfield exceeding 7KB (application'sMAX_PAYLOAD)Line 320's description currently only mentions the total request body limit. Consider updating it to note that HTTP 413 may also indicate a payload field violation, or adding a note that clients should parse the error response body to determine which limit was exceeded.
📝 Suggested clarification
Update line 320's description:
-| `413 Payload Too Large` | Total request body exceeds 8KB limit | +| `413 Payload Too Large` | Total request body exceeds 8KB limit, or payload field exceeds 7KB limit |Also applies to: 658-658
🤖 Prompt for 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. In `@SPEC.md` at line 320, The spec's HTTP 413 entry currently only describes Flask's MAX_CONTENT_LENGTH (total request body >8KB) but the codebase also returns 413 when the application's MAX_PAYLOAD (the JSON `payload` field >7KB) is exceeded; update the `413 Payload Too Large` description to mention both cases (total request body exceeding Flask's MAX_CONTENT_LENGTH and the JSON `payload` field exceeding application MAX_PAYLOAD), and add a note instructing clients to inspect the error response body to determine which limit was violated (reference the constants/limits named MAX_CONTENT_LENGTH and MAX_PAYLOAD and the `payload` field to locate the related checks).
🤖 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/codeql.yml:
- Line 30: Replace the version-tagged GitHub Action reference
"github/codeql-action/analyze@v3" with a pinned commit SHA to mitigate
supply-chain risk: locate the workflow step that uses the CodeQL analyze action
(the uses: line referencing github/codeql-action/analyze@v3) and change it to
the corresponding full commit SHA for that action release, updating any nearby
comments to reflect the pinned SHA and optionally add a short note with the
original tag/version for maintainability.
- Around line 25-27: Replace the tagged action reference
"github/codeql-action/init@v3" with a pinned commit SHA: update the uses line to
"github/codeql-action/init@<commit-sha>" (use the latest stable commit SHA from
the action's repository) so the workflow is pinned to a specific immutable
revision; apply the same SHA-pinning approach to any other CodeQL action
references in the workflow to remove the supply-chain risk.
In `@Examples/discord_worker.sh`:
- Around line 216-223: The current extraction uses grep which can match the
marker inside the publisher-controlled JSON; instead explicitly read the trailer
as the last line and strip it from the payload: for HTTP_CODE, take only the
final line of RESPONSE (e.g., pipe RESPONSE into tail -n1 and then parse
'^__HTTP_CODE__:' to get the code) and for RAW_RESPONSE remove that final line
(e.g., sed '$d' on RESPONSE) so the body cannot spoof the trailer; update the
HTTP_CODE and RAW_RESPONSE assignments that currently reference RESPONSE,
HTTP_CODE, and RAW_RESPONSE accordingly.
In `@SPEC.md`:
- Line 139: Update the docs to consistently state the payload field content
limit is 7KB (serialized UTF-8) and clarify that 8KB refers to the total HTTP
request body: change the phrase "Default payload size: 8KB per intent/result" in
README.md to "Default payload field content: 7KB; total request body limit: 8KB"
(or equivalent), update SECURITY.md's "Payload size: 8KB" to "Payload field
content: 7KB (8KB total request body)" and ensure the "payload_too_large"
description references the 7KB payload field limit rather than 8KB; search for
mentions of "payload", "payload_too_large", and "8KB" to adjust all occurrences
accordingly.
In `@WORKER_SECURITY.md`:
- Around line 79-83: Update the "Required Fields" section to include claim_token
as a mandatory field alongside intent id so worker authors know the claimed job
must include claim_token; mention that /fulfill and /fail require this token and
align the text with the server-side validation that rejects missing tokens (the
claim validation logic that enforces presence of claim_token), ensuring the
contract matches runtime behavior for worker implementations.
---
Outside diff comments:
In `@Examples/discord_worker.sh`:
- Around line 201-204: The claim request builds a query string by concatenating
GOAL and NAMESPACE which must be URL-encoded; update the script so GOAL and
NAMESPACE are URL-encoded before they are interpolated into the curl URL (e.g.
create encoded variables like ENCODED_GOAL and ENCODED_NAMESPACE using a
URL-encode helper or a short python/printf invocation) and then use those
encoded variables in the curl GET (the section that constructs
"$BASE_URL/claim?goal=$GOAL&namespace=$NAMESPACE"). Ensure the helper preserves
empty values and uses percent-encoding for reserved characters.
---
Nitpick comments:
In `@flask_app.py`:
- Around line 1582-1583: The code enforces MAX_PAYLOAD on the result content
(check the len(result_text.encode()) > MAX_PAYLOAD check returning
api_error("result_too_large")), but SPEC.md only documents the payload size;
update SPEC.md to explicitly state that the 7KB MAX_PAYLOAD limit also applies
to the "result" field (or clarify that the existing "Payload field content
limit: 7KB" covers both payload and result), and reference the MAX_PAYLOAD
constraint and the "result" field name so readers can correlate the spec with
the runtime check.
In `@SPEC.md`:
- Line 320: The spec's HTTP 413 entry currently only describes Flask's
MAX_CONTENT_LENGTH (total request body >8KB) but the codebase also returns 413
when the application's MAX_PAYLOAD (the JSON `payload` field >7KB) is exceeded;
update the `413 Payload Too Large` description to mention both cases (total
request body exceeding Flask's MAX_CONTENT_LENGTH and the JSON `payload` field
exceeding application MAX_PAYLOAD), and add a note instructing clients to
inspect the error response body to determine which limit was violated (reference
the constants/limits named MAX_CONTENT_LENGTH and MAX_PAYLOAD and the `payload`
field to locate the related checks).
🪄 Autofix (Beta)
✅ Autofix completed
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 2f1d2eb2-e050-4bf7-bb93-15768e8d9230
📒 Files selected for processing (10)
.github/workflows/codeql.yml.gitignoreDockerfileExamples/discord_worker.shSPEC.mdWORKER_SECURITY.mdflask_app.pytests/stest_ui.pytests/test_server_advanced.pytests/test_server_basic.py
Comment on lines
+25
to
+27
| uses: github/codeql-action/init@v3 # Action to initialize CodeQL for the specified languages | ||
| with: | ||
| languages: python | ||
| languages: python # Configure CodeQL to analyze Python code |
Contributor
There was a problem hiding this comment.
Pin action to commit SHA.
The github/codeql-action/init@v3 action is referenced by version tag rather than commit SHA, creating a supply chain security risk.
🔒 Proposed fix
- name: Initialize CodeQL
- uses: github/codeql-action/init@v3 # Action to initialize CodeQL for the specified languages
+ uses: github/codeql-action/init@aa578102511db1f4524ed59b8cc2bae4f6e88195 # v3.27.9
with:
languages: python # Configure CodeQL to analyze Python code📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| uses: github/codeql-action/init@v3 # Action to initialize CodeQL for the specified languages | |
| with: | |
| languages: python | |
| languages: python # Configure CodeQL to analyze Python code | |
| uses: github/codeql-action/init@aa578102511db1f4524ed59b8cc2bae4f6e88195 # v3.27.9 | |
| with: | |
| languages: python # Configure CodeQL to analyze Python code |
🧰 Tools
🪛 zizmor (1.25.2)
[error] 25-25: unpinned action reference (unpinned-uses): action is not pinned to a hash (required by blanket policy)
(unpinned-uses)
🤖 Prompt for 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.
In @.github/workflows/codeql.yml around lines 25 - 27, Replace the tagged action
reference "github/codeql-action/init@v3" with a pinned commit SHA: update the
uses line to "github/codeql-action/init@<commit-sha>" (use the latest stable
commit SHA from the action's repository) so the workflow is pinned to a specific
immutable revision; apply the same SHA-pinning approach to any other CodeQL
action references in the workflow to remove the supply-chain risk.
|
|
||
| - name: Perform CodeQL Analysis | ||
| uses: github/codeql-action/analyze@v3 | ||
| uses: github/codeql-action/analyze@v3 # Action to perform the actual CodeQL analysis |
Contributor
There was a problem hiding this comment.
Pin action to commit SHA.
The github/codeql-action/analyze@v3 action is referenced by version tag rather than commit SHA, creating a supply chain security risk.
🔒 Proposed fix
- name: Perform CodeQL Analysis
- uses: github/codeql-action/analyze@v3 # Action to perform the actual CodeQL analysis
+ uses: github/codeql-action/analyze@aa578102511db1f4524ed59b8cc2bae4f6e88195 # v3.27.9📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| uses: github/codeql-action/analyze@v3 # Action to perform the actual CodeQL analysis | |
| uses: github/codeql-action/analyze@aa578102511db1f4524ed59b8cc2bae4f6e88195 # v3.27.9 |
🧰 Tools
🪛 zizmor (1.25.2)
[error] 30-30: unpinned action reference (unpinned-uses): action is not pinned to a hash (required by blanket policy)
(unpinned-uses)
🤖 Prompt for 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.
In @.github/workflows/codeql.yml at line 30, Replace the version-tagged GitHub
Action reference "github/codeql-action/analyze@v3" with a pinned commit SHA to
mitigate supply-chain risk: locate the workflow step that uses the CodeQL
analyze action (the uses: line referencing github/codeql-action/analyze@v3) and
change it to the corresponding full commit SHA for that action release, updating
any nearby comments to reflect the pinned SHA and optionally add a short note
with the original tag/version for maintainability.
| |---|---|---|---| | ||
| | `goal` | string | required | The task type. 1–256 characters. | | ||
| | `payload` | any | required | Arbitrary JSON value passed to the worker. | | ||
| | `payload` | any | required | Arbitrary JSON value passed to the worker. Max 7KB (serialized UTF-8). | |
Contributor
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Search for payload size references in documentation files
rg -n "8KB|8 KB|8 KiB" README.md SECURITY.md --context 2Repository: dsecurity49/Intent-Bus
Length of output: 578
🏁 Script executed:
#!/bin/bash
set -euo pipefail
rg -n --hidden --no-ignore-vcs "8KB|8 KB|8 KiB" . --context 2 || true
echo "----"
rg -n --hidden --no-ignore-vcs "7KB|7 KB|7 KiB" SPEC.md --context 2 || true
echo "----"
rg -n --hidden --no-ignore-vcs "payload.*(8KB|8 KB|8 KiB)" . --context 2 || trueRepository: dsecurity49/Intent-Bus
Length of output: 2721
Align documented payload size limits (7KB payload vs 8KB total body)
SPEC.mddefines thepayloadfield content limit as 7KB (payloadmax 7KB / “Payload field content limit: 7KB. Total request body limit: 8KB.”), butSECURITY.mdstill lists Payload size: 8KB.README.mdlikewise says “Default payload size: 8KB per intent/result”, even though the “payload_too_large” description uses the 7KB limit.
Update README.md and SECURITY.md wording to consistently document 7KB for the payload field (and clarify 8KB is the total request body if applicable).
🤖 Prompt for 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.
In `@SPEC.md` at line 139, Update the docs to consistently state the payload field
content limit is 7KB (serialized UTF-8) and clarify that 8KB refers to the total
HTTP request body: change the phrase "Default payload size: 8KB per
intent/result" in README.md to "Default payload field content: 7KB; total
request body limit: 8KB" (or equivalent), update SECURITY.md's "Payload size:
8KB" to "Payload field content: 7KB (8KB total request body)" and ensure the
"payload_too_large" description references the 7KB payload field limit rather
than 8KB; search for mentions of "payload", "payload_too_large", and "8KB" to
adjust all occurrences accordingly.
Contributor
|
Note Autofix is a beta feature. Expect some limitations and changes as we gather feedback and continue to improve it. Fixes Applied SuccessfullyFixed 6 file(s) based on 5 unresolved review comments. Files modified:
Commit: The changes have been pushed to the Time taken:
Lines 22–30 uses: actions/checkout@v4 # Action to checkout the repository code
- name: Initialize CodeQL
- uses: github/codeql-action/init@v3 # Action to initialize CodeQL for the specified languages
+ uses: github/codeql-action/init@6bb031afdd8eb862ea3fc1848194185e078aa78a # v3 - Action to initialize CodeQL for the specified languages
with:
languages: python # Configure CodeQL to analyze Python code
- name: Perform CodeQL Analysis
- uses: github/codeql-action/analyze@v3 # Action to perform the actual CodeQL analysis
+ uses: github/codeql-action/analyze@6bb031afdd8eb862ea3fc1848194185e078aa78a # v3 - Action to perform the actual CodeQL analysis |
Fixed 6 file(s) based on 5 unresolved review comments. Co-authored-by: CodeRabbit <noreply@coderabbit.ai>
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
1 participant
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.
Summary by CodeRabbit
New Features
Improvements
Documentation