Examples/cbam calculator#570
Closed
Subhajitdas99 wants to merge 5 commits into
Closed
Conversation
EU CBAM agent that calculates carbon border adjustment costs for importers of iron/steel, aluminium, cement, fertilizers, hydrogen and electricity. Covers applicability check, 50-tonne exemption threshold, cost estimate using EU ETS price, compliance requirements and documentation checklist. Verified locally: 200t aluminium from Turkey = 82,680 EUR CBAM cost. Part of Bindu's trade compliance toolchain.
📝 WalkthroughWalkthroughAdds a CBAM (Carbon Border Adjustment Mechanism) calculator example: env placeholder, comprehensive README, a new agent script with INSTRUCTIONS and OpenRouter-configured Agent, Bindu config and handler, and a CBAM compliance skill YAML. ChangesCBAM Calculator Example Agent
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (2)
examples/cbam-calculator/cbam_calculator.py (2)
185-186: ⚡ Quick winPrefer
get_logger(__name__)overprint()for startup output.♻️ Proposed change
+from bindu.utils.logging import get_logger + +logger = get_logger(__name__) + if __name__ == "__main__": - print("🌍 CBAM Carbon Calculator running at http://localhost:3773") - print("♻️ Example: Calculate CBAM cost for 200 tonnes of aluminium from Turkey") + logger.info("🌍 CBAM Carbon Calculator running at http://localhost:3773") + logger.info("♻️ Example: Calculate CBAM cost for 200 tonnes of aluminium from Turkey") bindufy(config, handler)As per coding guidelines: "Use
get_logger(__name__)frombindu/utils/logging.pyinstead ofprint()for logging".🤖 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/cbam-calculator/cbam_calculator.py` around lines 185 - 186, Replace the two startup print() calls with a module logger: import and instantiate logger = get_logger(__name__) from bindu.utils.logging and replace the prints in cbam_calculator.py (the two lines printing startup URL and example) with logger.info(...) calls using the same messages so startup output follows the project's logging conventions.
173-174: ⚡ Quick winBindufy already normalizes Agno
RunOutputvia.content, so this isn’t a critical bug.
manifest_workerrunsResultProcessor.normalize_result(), which returnsresult.contentwhen the handler returns an object with a.contentattribute—soreturn resultshould work with agno’sRunOutput. Returningresult.content(orresult.to_dict()["content"]) is still optional for clarity/consistency with thebindufydocs.🤖 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/cbam-calculator/cbam_calculator.py` around lines 173 - 174, The handler currently returns the raw object from agent.run (result) which relies on downstream normalization; to make the output explicit and consistent with Bindufy docs, change the return to return the RunOutput's content (e.g., use result.content or result.to_dict()["content"]) so manifest_worker.ResultProcessor.normalize_result() still receives the expected string payload; locate the agent.run call in the function that invokes the agent (agent.run) and replace the final return of result with returning its .content.
🤖 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 `@examples/cbam-calculator/cbam_calculator.py`:
- Around line 166-171: The guard computes query from user_messages[-1] but never
uses it when invoking the agent, so align the inputs: either use the extracted
query when running the agent (pass [ {"role": "user", "content": query} ] or
equivalent to agent.run) or remove the query variable and validate directly
against messages/user_messages; update the code paths around query,
user_messages, messages, and the agent.run call so the same data is validated
and passed to the agent.
In `@pyproject.toml`:
- Line 67: Remove the "duckduckgo-search>=8.1.1" entry from the core
[project.dependencies] block in pyproject.toml and ensure it remains only in the
optional [project.optional-dependencies].agents group; verify the CBAM example
(examples/cbam-calculator/cbam_calculator.py) continues to import only agno,
OpenRouter and python-dotenv (and not DuckDuckGoTools) so runtime installs are
not forced to include duckduckgo-search.
---
Nitpick comments:
In `@examples/cbam-calculator/cbam_calculator.py`:
- Around line 185-186: Replace the two startup print() calls with a module
logger: import and instantiate logger = get_logger(__name__) from
bindu.utils.logging and replace the prints in cbam_calculator.py (the two lines
printing startup URL and example) with logger.info(...) calls using the same
messages so startup output follows the project's logging conventions.
- Around line 173-174: The handler currently returns the raw object from
agent.run (result) which relies on downstream normalization; to make the output
explicit and consistent with Bindufy docs, change the return to return the
RunOutput's content (e.g., use result.content or result.to_dict()["content"]) so
manifest_worker.ResultProcessor.normalize_result() still receives the expected
string payload; locate the agent.run call in the function that invokes the agent
(agent.run) and replace the final return of result with returning its .content.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: ca3ae039-ac6c-406b-aa50-3fcacad7d5dc
⛔ Files ignored due to path filters (1)
uv.lockis excluded by!**/*.lock
📒 Files selected for processing (5)
examples/cbam-calculator/.env.exampleexamples/cbam-calculator/README.mdexamples/cbam-calculator/cbam_calculator.pyexamples/cbam-calculator/skills/cbam-compliance-skill/skill.yamlpyproject.toml
Comment on lines
+166
to
+171
| query = user_messages[-1].get("content", "").strip() | ||
| if not query: | ||
| return ( | ||
| "Empty query. Please describe your import situation, e.g. " | ||
| "'Calculate CBAM cost for 200 tonnes of aluminium from Turkey'" | ||
| ) |
There was a problem hiding this comment.
Minor: query is validated but never used.
The non-empty query is computed for the empty-input guard but the agent is run on the full messages list, so the extracted query is otherwise unused. Functionally fine; flagging for clarity since the guard and the run input diverge.
🤖 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/cbam-calculator/cbam_calculator.py` around lines 166 - 171, The
guard computes query from user_messages[-1] but never uses it when invoking the
agent, so align the inputs: either use the extracted query when running the
agent (pass [ {"role": "user", "content": query} ] or equivalent to agent.run)
or remove the query variable and validate directly against
messages/user_messages; update the code paths around query, user_messages,
messages, and the agent.run call so the same data is validated and passed to the
agent.
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
examples/cbam-calculator/cbam_calculator.py (1)
166-171:⚠️ Potential issue | 🔴 Critical | ⚡ Quick win
loggeris undefined — this will raiseNameErrorat runtime.Line 167 calls
logger.debug(...)butloggeris never imported or instantiated. This will crash when the handler receives a valid query.🐛 Proposed fix: Add logger import and instantiation
import os +from bindu.utils.logging import get_logger from agno.agent import Agent from agno.models.openrouter import OpenRouter from bindu.penguin.bindufy import bindufy from dotenv import load_dotenv load_dotenv() + +logger = get_logger(__name__)As per coding guidelines: "Use
get_logger(__name__)frombindu/utils/logging.pyfor logging".🤖 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/cbam-calculator/cbam_calculator.py` around lines 166 - 171, The code calls logger.debug(...) in the handler where it computes query from user_messages but never defines logger, causing a NameError; import get_logger from bindu.utils.logging and instantiate logger = get_logger(__name__) at the module level (with the other imports) so the logger symbol used around the query/user_messages logic is defined; verify the instantiation is above the function that references logger.
🧹 Nitpick comments (1)
examples/cbam-calculator/cbam_calculator.py (1)
184-187: 💤 Low valueConsider using logger for startup messages per coding guidelines.
The startup messages use
print(). While this is common for CLI banners, the coding guidelines specify usingget_logger(__name__)instead ofprint().♻️ Optional: Use logger for consistency
if __name__ == "__main__": - print("🌍 CBAM Carbon Calculator running at http://localhost:3773") - print("♻️ Example: Calculate CBAM cost for 200 tonnes of aluminium from Turkey") + logger.info("🌍 CBAM Carbon Calculator running at http://localhost:3773") + logger.info("♻️ Example: Calculate CBAM cost for 200 tonnes of aluminium from Turkey") bindufy(config, handler)As per coding guidelines: "Use
get_logger(__name__)frombindu/utils/logging.pyfor logging, notprint()".🤖 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/cbam-calculator/cbam_calculator.py` around lines 184 - 187, Startup messages use print() instead of the project logger; import get_logger from bindu.utils.logging, create a logger = get_logger(__name__) near the module top if not present, and replace the two print() calls in the if __name__ == "__main__": block with logger.info(...) (keeping the same message strings) before calling bindufy(config, handler); ensure no other call sites rely on stdout prints.
🤖 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.
Outside diff comments:
In `@examples/cbam-calculator/cbam_calculator.py`:
- Around line 166-171: The code calls logger.debug(...) in the handler where it
computes query from user_messages but never defines logger, causing a NameError;
import get_logger from bindu.utils.logging and instantiate logger =
get_logger(__name__) at the module level (with the other imports) so the logger
symbol used around the query/user_messages logic is defined; verify the
instantiation is above the function that references logger.
---
Nitpick comments:
In `@examples/cbam-calculator/cbam_calculator.py`:
- Around line 184-187: Startup messages use print() instead of the project
logger; import get_logger from bindu.utils.logging, create a logger =
get_logger(__name__) near the module top if not present, and replace the two
print() calls in the if __name__ == "__main__": block with logger.info(...)
(keeping the same message strings) before calling bindufy(config, handler);
ensure no other call sites rely on stdout prints.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 875e7b9e-446a-48d6-b901-731e058d1a8a
📒 Files selected for processing (1)
examples/cbam-calculator/cbam_calculator.py
Member
|
hey @Subhajitdas99 also this pr |
Member
|
i am closing it |
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
2 participants
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
examples/cbam-calculator/— an Agno + OpenRouter agent that checks CBAM applicability, applies the 50-tonne exemption threshold, estimates certificate costs using EU ETS price, and generates a compliance checklist.Change Type
Scope
Linked Issue/PR
Related: Bindu trade compliance roadmap (Discord, 29 May 2026). Second agent in the compliance toolchain after #569 (HS Code Classifier).
User-Visible / Behavior Changes
New example agent at
examples/cbam-calculator/. RequiresOPENROUTER_API_KEY. No changes to existing behaviour.Security Impact
# pragma: allowlist secretadded to suppress false-positive detection.Verification
Environment
Steps to Test
cd examples/cbam-calculatorcp .env.example .envand setOPENROUTER_API_KEYpython cbam_calculator.pyCalculate CBAM cost for 200 tonnes of aluminium from TurkeyExpected Behavior
Actual Behavior
Matches expected. Correctly returned:
Evidence
Human Verification
Compatibility / Migration
Failure Recovery
Remove
examples/cbam-calculator/— self-contained, no framework changes.Risks and Mitigations
Checklist
Summary by CodeRabbit
New Features
Documentation
Chores