feat(governance): add competition events subsumption bundle#23640
feat(governance): add competition events subsumption bundle#23640BrianCLong wants to merge 1 commit intomainfrom
Conversation
Creates the initial architectural implementation for the competition events subsumption plan. - Added `subsumption/competition-events/manifest.yaml` and `claims.md` for ground truth capture. - Defined GraphRAG schema `CompetitionEvent` in `src/graphrag/schema/competitionEvent.ts`. - Created rest connector `extractCompetitionEvent` in `src/connectors/rest/regulatoryNews.ts` with tests. - Added antitrust GitHub Actions policy in `.github/policies/competition/antitrust.yml`. - Created agent stub `CompetitionRiskAgent`. - Added stubs for benchmark and monitoring scripts. - Added standards, security, and runbook documentation to `docs/`. Co-authored-by: BrianCLong <6404035+BrianCLong@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces the 'Competition Events' feature, which includes a risk agent, a regulatory news extractor, and comprehensive documentation for operations, security, and standards. The feedback primarily addresses the 'manifest.yaml' file, which currently contains several placeholder values and incorrect file paths inherited from a template. Additionally, there are suggestions to improve the robustness of the antitrust policy matching condition and to properly handle an unused parameter in the risk agent.
| title: "TEMPLATE: Replace with ITEM title" | ||
| links: [] | ||
| type: "unknown" | ||
| date_version: "unknown" | ||
| intriguing_claim: "TEMPLATE: 1–2 sentences" | ||
| item_slug: "_template" |
There was a problem hiding this comment.
The manifest metadata contains placeholder values from the template. These should be updated to reflect the specific 'Competition Events' bundle.
title: "Competition Events Subsumption Bundle"
links: []
type: "governance"
date_version: "1.0.0"
intriguing_claim: "Tracks regulatory competition events and anti-competitive conduct allegations."
item_slug: "competition-events"|
|
||
| claim_registry: | ||
| mode: "missing-item" | ||
| claims_file: "subsumption/_template/claims.md" |
There was a problem hiding this comment.
The claims_file path points to the template directory. It should point to the claims.md file created in this PR.
claims_file: "subsumption/competition-events/claims.md"| - "docs/standards/subsumption-bundle-framework.md" | ||
| - "docs/security/data-handling/subsumption-bundle-framework.md" | ||
| - "docs/ops/runbooks/subsumption-bundle-framework.md" |
There was a problem hiding this comment.
The docs_targets paths point to generic framework documentation. They should be updated to match the documentation files added in this PR.
- "docs/standards/competition-events.md"
- "docs/security/data-handling/competition-events.md"
- "docs/ops/runbooks/competition-events.md"| @@ -0,0 +1,5 @@ | |||
| export class CompetitionRiskAgent { | |||
| analyze(text: string) { | |||
There was a problem hiding this comment.
The text parameter is currently unused. Prefixing it with an underscore is a common convention to indicate an intentionally unused parameter in TypeScript.
| analyze(text: string) { | |
| analyze(_text: string) { |
| rules: | ||
| - id: antitrust-01 | ||
| description: Flag mentions of anticompetitive conduct | ||
| condition: text contains "anti-competitive" |
There was a problem hiding this comment.
The condition text contains "anti-competitive" is case-sensitive and very specific. It will miss variations like "anticompetitive" or "Anti-competitive". Consider using a more flexible matching strategy if supported by the policy engine.
WalkthroughAdds a new competition events feature including antitrust policy configuration, regulatory news extraction connector, risk analysis agent, schema definitions, operational documentation, manifest files, and related tests. Changes
Sequence DiagramsequenceDiagram
participant Client
participant REST Connector
participant Competition Agent
participant Response
Client->>REST Connector: POST article text
REST Connector->>REST Connector: Compute SHA-256 hash
REST Connector->>Competition Agent: Pass extracted CompetitionEvent
Competition Agent->>Competition Agent: Analyze text for risk
Competition Agent->>Response: Return {riskScore: 0.8, flags: [antitrust]}
Response->>Client: Return analysis result
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
🚥 Pre-merge checks | ✅ 1 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (1 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 |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.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: 7f8719f8ce
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".
| type: "unknown" | ||
| date_version: "unknown" | ||
| intriguing_claim: "TEMPLATE: 1–2 sentences" | ||
| item_slug: "_template" |
There was a problem hiding this comment.
item_slug is still _template, so any tooling that derives identity from the manifest will attribute this bundle’s evidence to the template namespace instead of competition-events (the repo’s verifier extracts slug text and writes it into emitted evidence metadata). That creates collisions with other template-derived bundles and makes this new bundle non-addressable as its own ITEM.
Useful? React with 👍 / 👎.
| const hash = crypto.createHash('sha256').update(article).digest('hex'); | ||
| return { | ||
| id: hash, | ||
| type: "REGULATORY_COMPETITION_EVENT", |
There was a problem hiding this comment.
The extractor returns type, but the newly added CompetitionEvent schema defines event_type as the discriminator. This mismatch means payloads from extractCompetitionEvent do not conform to the declared schema and can be dropped or misclassified by consumers expecting CompetitionEvent-shaped objects.
Useful? React with 👍 / 👎.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 9
🧹 Nitpick comments (3)
scripts/monitoring/competition-drift.ts (1)
1-1: Stub file needs implementation or tracking.This monitoring script is a placeholder with no functional drift detection logic. The PR description mentions "post-merge monitoring" stubs.
Would you like me to:
- Generate a functional monitoring implementation for competition event drift detection (schema changes, data quality metrics, alert thresholds, etc.), or
- Open an issue to track this as deferred work with acceptance criteria?
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@scripts/monitoring/competition-drift.ts` at line 1, The file currently only contains a stub console.log; replace it with a proper monitoring implementation by adding a top-level async function monitorCompetitionDrift that orchestrates drift checks, and implement helper functions detectSchemaChanges, computeDataQualityMetrics, and sendAlert; detectSchemaChanges should compare current event schema to a stored baseline (e.g., loadBaselineSchema/loadBaseline function), computeDataQualityMetrics should calculate completeness, null rates and value distributions for key fields, and monitorCompetitionDrift should evaluate thresholds and call sendAlert (or log) when drift or quality thresholds are exceeded; ensure the script exports or runs monitorCompetitionDrift and include configuration for thresholds and a persistent baseline store or an issue if baseline is missing.scripts/bench/competition-event.ts (1)
1-1: Stub file needs implementation or tracking.This benchmark script is a placeholder with no functional implementation. The PR description acknowledges these as "placeholder scripts for performance benchmarking."
Would you like me to:
- Generate a functional benchmark implementation for competition event processing (measuring ingestion throughput, query performance, etc.), or
- Open an issue to track this as deferred work with acceptance criteria?
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@scripts/bench/competition-event.ts` at line 1, Replace the placeholder console.log in scripts/bench/competition-event.ts with a tracked TODO and open an issue to defer the benchmark work: create an issue describing required acceptance criteria (measure ingestion throughput, query latency, realistic dataset generation, repeatable runs, and CI gating), reference this file (scripts/bench/competition-event.ts) and its current stub (console.log('Benchmark script stub')), and add a short TODO comment in the file pointing to the issue number so future contributors know this is intentionally deferred.tests/connectors/regulatoryNews.test.ts (1)
5-10: Strengthen this test to assert deterministic contract, not just truthiness.
assert.ok(event.id)won’t catch hash regressions or shape regressions.Suggested test hardening
import test from 'node:test'; import assert from 'node:assert'; +import crypto from 'node:crypto'; import { extractCompetitionEvent } from '../../src/connectors/rest/regulatoryNews.js'; test('extractCompetitionEvent', () => { const article = 'OpenAI formally requested regulatory scrutiny from California AG.'; const event = extractCompetitionEvent(article); + const expectedId = crypto.createHash('sha256').update(article).digest('hex'); assert.strictEqual(event.type, 'REGULATORY_COMPETITION_EVENT'); - assert.ok(event.id); + assert.strictEqual(event.id, expectedId); + assert.deepStrictEqual(event.actors, []); + assert.deepStrictEqual(event.claims, []); });🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@tests/connectors/regulatoryNews.test.ts` around lines 5 - 10, The test uses assert.ok(event.id) which only checks truthiness; change it to assert a deterministic contract: call extractCompetitionEvent(article) and assert.strictEqual(event.type, 'REGULATORY_COMPETITION_EVENT') and then either assert.strictEqual(event.id, '<expected-deterministic-id>') (replace with the known hash/code produced for that article) or assert.match(event.id, /^[a-f0-9]{...}$/) to lock down the id format, and additionally assert deep properties of the event (e.g., assert.strictEqual(event.text, article) or assert.deepStrictEqual(event, { type: ..., id: ..., text: ... })) so the test fails on hash/shape regressions; update the test in tests/connectors/regulatoryNews.test.ts around the extractCompetitionEvent call accordingly.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.github/policies/competition/antitrust.yml:
- Line 5: The condition currently only checks for the exact string
"anti-competitive"; replace it with a case-insensitive regex that matches both
hyphenated and non-hyphenated forms, e.g. change the rule from condition: text
contains "anti-competitive" to a regex match like condition: text matches
"(?i)\\banti-?competitive\\b" so it catches "anti-competitive",
"anticompetitive", and case variants.
In `@docs/ops/runbooks/competition-events.md`:
- Around line 4-6: The runbook's alert threshold "extraction fails >5%"
conflicts with the declared SLO "SLO: 99% parse success" (1% failure budget);
update the alerting threshold to align with the SLO (e.g., trigger when
extraction fails >1% or a lower value like >0.5% for early warning) or change
the SLO to match the existing alerting (e.g., SLO: 95% parse success) and make
the change in the lines containing "extraction fails >5%" and "SLO: 99% parse
success" so the two values are consistent.
In `@docs/security/data-handling/competition-events.md`:
- Line 7: The phrase "Retention: 30 days raw, permanent structured" lacks a
compliance guardrail—update the doc to replace or augment "permanent structured"
with an explicit retention and reevaluation policy: define a structured-record
retention_duration (e.g., X years or indefinite with conditions), a periodic
review_cycle (e.g., annually), responsible_role or team (e.g., Data Protection
Officer / Data Retention Owner), required transformations
(pseudonymization/aggregation) and legal_basis for indefinite storage, and
mention audit/logging and deletion procedures (how to delete or re-evaluate
records and who approves exceptions) so the structured retention has clear
operational and compliance controls.
In `@src/agents/competition-risk-agent.ts`:
- Around line 2-3: The analyze method currently returns a hardcoded antitrust
risk for every input; change analyze(text: string) in the CompetitionRiskAgent
to compute a real heuristic: scan the input for configurable antitrust
keywords/phrases (e.g., "collude", "price fixing", "bid rigging", "market
allocation"), count hits and compute a normalized riskScore (0.0–1.0) based on
hits and text length, and populate flags only when relevant (e.g., include
'antitrust' or more specific flags like 'price-fixing'); if no keywords are
found return riskScore near 0 and an empty flags array. Ensure the function
signature remains analyze(text: string) and add a simple unit test or comment
describing the keyword list so maintainers can tune thresholds.
In `@src/connectors/rest/regulatoryNews.ts`:
- Around line 3-4: The function extractCompetitionEvent creates a hash from the
article without validating input; add an early guard in extractCompetitionEvent
that checks if article is null/undefined or article.trim() === '' and reject it
(e.g., return null or throw a ValidationError) before calling crypto.createHash,
so blank or whitespace-only inputs are not hashed or turned into events.
- Around line 5-8: The returned object in the regulatory news connector is using
the wrong field name "type" which must be renamed to "event_type" to match the
schema; update the return value (the object that includes id: hash, type:
"REGULATORY_COMPETITION_EVENT", actors: []) to replace the "type" property with
"event_type" (event_type: "REGULATORY_COMPETITION_EVENT") so that the output of
the regulatoryNews connector conforms to the competition event schema and passes
validation.
In `@src/graphrag/schema/competitionEvent.ts`:
- Line 4: The schema uses event_type but the regulatory extractor/test contract
expects the discriminant key type, causing a shape mismatch; update the
CompetitionEvent schema to use type: 'REGULATORY_COMPETITION_EVENT' (replace
event_type) and search/rename any references to event_type in related
code/tests/extractors to use type so the discriminant key is consistent with the
regulatory extractor and downstream consumers.
In `@subsumption/competition-events/manifest.yaml`:
- Line 3: The manifest still contains template placeholders (e.g., title:
"TEMPLATE: Replace with ITEM title") and references to the `_template` and
`subsumption-bundle-framework` artifacts which prevent the competition-events
bundle from resolving correct claims/docs/fixtures; update the manifest.yaml to
replace the TEMPLATE placeholders with the real `competition-events` values and
swap any `_template` and `subsumption-bundle-framework` artifact references to
the actual competition-events artifact names used by this bundle (check fields
around title, any `artifact:` entries, `docs`, `fixtures`, and `claims` keys) so
all references point to the competition-events resources instead of the
template/framework ones.
- Around line 22-23: The manifest currently sets required_checks_status:
"assumed" while deny_by_default_required: true which weakens enforcement; change
required_checks_status to a non-assumed value (e.g., "required" or "enforced")
so the deny-by-default gate requires actual CI verification, and apply the same
change for the other occurrence mentioned (lines 56-57) to ensure both places
use the stricter status.
---
Nitpick comments:
In `@scripts/bench/competition-event.ts`:
- Line 1: Replace the placeholder console.log in
scripts/bench/competition-event.ts with a tracked TODO and open an issue to
defer the benchmark work: create an issue describing required acceptance
criteria (measure ingestion throughput, query latency, realistic dataset
generation, repeatable runs, and CI gating), reference this file
(scripts/bench/competition-event.ts) and its current stub
(console.log('Benchmark script stub')), and add a short TODO comment in the file
pointing to the issue number so future contributors know this is intentionally
deferred.
In `@scripts/monitoring/competition-drift.ts`:
- Line 1: The file currently only contains a stub console.log; replace it with a
proper monitoring implementation by adding a top-level async function
monitorCompetitionDrift that orchestrates drift checks, and implement helper
functions detectSchemaChanges, computeDataQualityMetrics, and sendAlert;
detectSchemaChanges should compare current event schema to a stored baseline
(e.g., loadBaselineSchema/loadBaseline function), computeDataQualityMetrics
should calculate completeness, null rates and value distributions for key
fields, and monitorCompetitionDrift should evaluate thresholds and call
sendAlert (or log) when drift or quality thresholds are exceeded; ensure the
script exports or runs monitorCompetitionDrift and include configuration for
thresholds and a persistent baseline store or an issue if baseline is missing.
In `@tests/connectors/regulatoryNews.test.ts`:
- Around line 5-10: The test uses assert.ok(event.id) which only checks
truthiness; change it to assert a deterministic contract: call
extractCompetitionEvent(article) and assert.strictEqual(event.type,
'REGULATORY_COMPETITION_EVENT') and then either assert.strictEqual(event.id,
'<expected-deterministic-id>') (replace with the known hash/code produced for
that article) or assert.match(event.id, /^[a-f0-9]{...}$/) to lock down the id
format, and additionally assert deep properties of the event (e.g.,
assert.strictEqual(event.text, article) or assert.deepStrictEqual(event, { type:
..., id: ..., text: ... })) so the test fails on hash/shape regressions; update
the test in tests/connectors/regulatoryNews.test.ts around the
extractCompetitionEvent call accordingly.
🪄 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: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 19146f72-9f8c-4a4f-bdb9-c8661d98851f
📒 Files selected for processing (12)
.github/policies/competition/antitrust.ymldocs/ops/runbooks/competition-events.mddocs/security/data-handling/competition-events.mddocs/standards/competition-events.mdscripts/bench/competition-event.tsscripts/monitoring/competition-drift.tssrc/agents/competition-risk-agent.tssrc/connectors/rest/regulatoryNews.tssrc/graphrag/schema/competitionEvent.tssubsumption/competition-events/claims.mdsubsumption/competition-events/manifest.yamltests/connectors/regulatoryNews.test.ts
| rules: | ||
| - id: antitrust-01 | ||
| description: Flag mentions of anticompetitive conduct | ||
| condition: text contains "anti-competitive" |
There was a problem hiding this comment.
Broaden the match condition to avoid false negatives.
The current condition only catches the exact hyphenated phrase and will miss common variants like anticompetitive (and likely case variants), so antitrust mentions can slip through.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.github/policies/competition/antitrust.yml at line 5, The condition
currently only checks for the exact string "anti-competitive"; replace it with a
case-insensitive regex that matches both hyphenated and non-hyphenated forms,
e.g. change the rule from condition: text contains "anti-competitive" to a regex
match like condition: text matches "(?i)\\banti-?competitive\\b" so it catches
"anti-competitive", "anticompetitive", and case variants.
| * extraction fails >5% | ||
| * schema mismatch | ||
| * SLO: 99% parse success |
There was a problem hiding this comment.
Alert threshold conflicts with stated SLO.
A 99% parse-success SLO means a 1% failure budget, but the runbook alerts only after failures exceed 5%, which is too late for SLO protection.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@docs/ops/runbooks/competition-events.md` around lines 4 - 6, The runbook's
alert threshold "extraction fails >5%" conflicts with the declared SLO "SLO: 99%
parse success" (1% failure budget); update the alerting threshold to align with
the SLO (e.g., trigger when extraction fails >1% or a lower value like >0.5% for
early warning) or change the SLO to match the existing alerting (e.g., SLO: 95%
parse success) and make the change in the lines containing "extraction fails
>5%" and "SLO: 99% parse success" so the two values are consistent.
| * Never log: | ||
| * raw prompts | ||
| * internal embeddings | ||
| * Retention: 30 days raw, permanent structured |
There was a problem hiding this comment.
“Permanent structured” retention needs a compliance guardrail.
Without an explicit deletion/reevaluation policy for structured records, this creates a data-minimization and retention-risk gap.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@docs/security/data-handling/competition-events.md` at line 7, The phrase
"Retention: 30 days raw, permanent structured" lacks a compliance
guardrail—update the doc to replace or augment "permanent structured" with an
explicit retention and reevaluation policy: define a structured-record
retention_duration (e.g., X years or indefinite with conditions), a periodic
review_cycle (e.g., annually), responsible_role or team (e.g., Data Protection
Officer / Data Retention Owner), required transformations
(pseudonymization/aggregation) and legal_basis for indefinite storage, and
mention audit/logging and deletion procedures (how to delete or re-evaluate
records and who approves exceptions) so the structured retention has clear
operational and compliance controls.
| analyze(text: string) { | ||
| return { riskScore: 0.8, flags: ['antitrust'] }; |
There was a problem hiding this comment.
analyze currently classifies every text as antitrust risk.
This is functionally incorrect for a production path and will flood downstream systems with false positives.
Proposed minimal baseline behavior
export class CompetitionRiskAgent {
analyze(text: string) {
- return { riskScore: 0.8, flags: ['antitrust'] };
+ const normalized = text.toLowerCase();
+ const antitrustHit = /(anti-competitive|anticompetitive|antitrust|monopoly)/.test(normalized);
+ return {
+ riskScore: antitrustHit ? 0.8 : 0.1,
+ flags: antitrustHit ? ['antitrust'] : [],
+ };
}
}📝 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.
| analyze(text: string) { | |
| return { riskScore: 0.8, flags: ['antitrust'] }; | |
| analyze(text: string) { | |
| const normalized = text.toLowerCase(); | |
| const antitrustHit = /(anti-competitive|anticompetitive|antitrust|monopoly)/.test(normalized); | |
| return { | |
| riskScore: antitrustHit ? 0.8 : 0.1, | |
| flags: antitrustHit ? ['antitrust'] : [], | |
| }; | |
| } |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/agents/competition-risk-agent.ts` around lines 2 - 3, The analyze method
currently returns a hardcoded antitrust risk for every input; change
analyze(text: string) in the CompetitionRiskAgent to compute a real heuristic:
scan the input for configurable antitrust keywords/phrases (e.g., "collude",
"price fixing", "bid rigging", "market allocation"), count hits and compute a
normalized riskScore (0.0–1.0) based on hits and text length, and populate flags
only when relevant (e.g., include 'antitrust' or more specific flags like
'price-fixing'); if no keywords are found return riskScore near 0 and an empty
flags array. Ensure the function signature remains analyze(text: string) and add
a simple unit test or comment describing the keyword list so maintainers can
tune thresholds.
| export function extractCompetitionEvent(article: string) { | ||
| const hash = crypto.createHash('sha256').update(article).digest('hex'); |
There was a problem hiding this comment.
Reject empty/blank articles before hashing.
Creating events from blank input makes ingestion noisy and can produce duplicate placeholder events.
Suggested input validation
export function extractCompetitionEvent(article: string) {
+ if (!article || article.trim().length === 0) {
+ throw new Error('article must be a non-empty string');
+ }
const hash = crypto.createHash('sha256').update(article).digest('hex');
return {📝 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.
| export function extractCompetitionEvent(article: string) { | |
| const hash = crypto.createHash('sha256').update(article).digest('hex'); | |
| export function extractCompetitionEvent(article: string) { | |
| if (!article || article.trim().length === 0) { | |
| throw new Error('article must be a non-empty string'); | |
| } | |
| const hash = crypto.createHash('sha256').update(article).digest('hex'); |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/connectors/rest/regulatoryNews.ts` around lines 3 - 4, The function
extractCompetitionEvent creates a hash from the article without validating
input; add an early guard in extractCompetitionEvent that checks if article is
null/undefined or article.trim() === '' and reject it (e.g., return null or
throw a ValidationError) before calling crypto.createHash, so blank or
whitespace-only inputs are not hashed or turned into events.
| return { | ||
| id: hash, | ||
| type: "REGULATORY_COMPETITION_EVENT", | ||
| actors: [], |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== Locate schema and inspect event field names =="
fd -i 'competitionEvent.ts' | while read -r f; do
echo "--- $f ---"
rg -n -C2 'interface\s+CompetitionEvent|event_type|type\s*:' "$f"
done
echo
echo "== Inspect connector payload fields =="
fd -i 'regulatoryNews.ts' | while read -r f; do
echo "--- $f ---"
rg -n -C2 'extractCompetitionEvent|event_type|type\s*:' "$f"
doneRepository: BrianCLong/summit
Length of output: 747
Fix field name mismatch: type should be event_type.
The schema defines event_type as the field name (src/graphrag/schema/competitionEvent.ts, line 4), but the connector returns type (src/connectors/rest/regulatoryNews.ts, line 7). This contract violation will break validation and ingestion. Rename the field to event_type to match the schema.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/connectors/rest/regulatoryNews.ts` around lines 5 - 8, The returned
object in the regulatory news connector is using the wrong field name "type"
which must be renamed to "event_type" to match the schema; update the return
value (the object that includes id: hash, type: "REGULATORY_COMPETITION_EVENT",
actors: []) to replace the "type" property with "event_type" (event_type:
"REGULATORY_COMPETITION_EVENT") so that the output of the regulatoryNews
connector conforms to the competition event schema and passes validation.
| import type { EvidenceReport } from '../evidence/types.js'; | ||
|
|
||
| export interface CompetitionEvent extends EvidenceReport { | ||
| event_type: 'REGULATORY_COMPETITION_EVENT'; |
There was a problem hiding this comment.
Use a single discriminant key across schema and extractor (type vs event_type).
CompetitionEvent uses event_type, but the regulatory extractor/test contract uses type. This creates a guaranteed shape mismatch for competition events and can break downstream classification/query logic.
Proposed fix
export interface CompetitionEvent extends EvidenceReport {
- event_type: 'REGULATORY_COMPETITION_EVENT';
+ type: 'REGULATORY_COMPETITION_EVENT';
actors: string[];
claims: string[];
}🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/graphrag/schema/competitionEvent.ts` at line 4, The schema uses
event_type but the regulatory extractor/test contract expects the discriminant
key type, causing a shape mismatch; update the CompetitionEvent schema to use
type: 'REGULATORY_COMPETITION_EVENT' (replace event_type) and search/rename any
references to event_type in related code/tests/extractors to use type so the
discriminant key is consistent with the regulatory extractor and downstream
consumers.
| @@ -0,0 +1,57 @@ | |||
| version: 1 | |||
| item: | |||
| title: "TEMPLATE: Replace with ITEM title" | |||
There was a problem hiding this comment.
Replace template placeholders with competition-events bundle values.
This manifest is still wired to _template and subsumption-bundle-framework artifacts, so the competition-events bundle won’t resolve the correct claims/docs/fixtures.
Proposed fix
item:
- title: "TEMPLATE: Replace with ITEM title"
+ title: "Competition Events Subsumption Bundle"
@@
-item_slug: "_template"
+item_slug: "competition-events"
@@
claim_registry:
mode: "missing-item"
- claims_file: "subsumption/_template/claims.md"
+ claims_file: "subsumption/competition-events/claims.md"
@@
prs:
- - title: "feat(governance): add subsumption bundle framework verifier"
+ - title: "feat(governance): add competition events subsumption bundle"
@@
docs_targets:
- - "docs/standards/subsumption-bundle-framework.md"
- - "docs/security/data-handling/subsumption-bundle-framework.md"
- - "docs/ops/runbooks/subsumption-bundle-framework.md"
+ - "docs/standards/competition-events.md"
+ - "docs/security/data-handling/competition-events.md"
+ - "docs/ops/runbooks/competition-events.md"
@@
fixtures:
- deny_policy_dir: "subsumption/_template/fixtures/policy/deny"
+ deny_policy_dir: "subsumption/competition-events/fixtures/policy/deny"
tests:
positive:
- - "subsumption/_template/fixtures/tests/positive/minimal_bundle"
+ - "subsumption/competition-events/fixtures/tests/positive/minimal_bundle"
negative:
- - "subsumption/_template/fixtures/tests/negative/missing_docs"
+ - "subsumption/competition-events/fixtures/tests/negative/missing_docs"Also applies to: 8-8, 12-12, 15-15, 35-37, 43-48
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@subsumption/competition-events/manifest.yaml` at line 3, The manifest still
contains template placeholders (e.g., title: "TEMPLATE: Replace with ITEM
title") and references to the `_template` and `subsumption-bundle-framework`
artifacts which prevent the competition-events bundle from resolving correct
claims/docs/fixtures; update the manifest.yaml to replace the TEMPLATE
placeholders with the real `competition-events` values and swap any `_template`
and `subsumption-bundle-framework` artifact references to the actual
competition-events artifact names used by this bundle (check fields around
title, any `artifact:` entries, `docs`, `fixtures`, and `claims` keys) so all
references point to the competition-events resources instead of the
template/framework ones.
| required_checks_status: "assumed" | ||
| deny_by_default_required: true |
There was a problem hiding this comment.
Avoid assumed check status when deny-by-default is required.
Using "assumed" for required checks/discovery weakens enforcement and can allow policy gates to pass without verified CI evidence.
Proposed hardening
gates:
- name: "verify-subsumption-bundle"
- required_checks_status: "assumed"
+ required_checks_status: "required"
deny_by_default_required: true
@@
required_checks_discovery:
- status: "assumed"
+ status: "required"
instructions: "docs/required_checks.todo.md"Also applies to: 56-57
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@subsumption/competition-events/manifest.yaml` around lines 22 - 23, The
manifest currently sets required_checks_status: "assumed" while
deny_by_default_required: true which weakens enforcement; change
required_checks_status to a non-assumed value (e.g., "required" or "enforced")
so the deny-by-default gate requires actual CI verification, and apply the same
change for the other occurrence mentioned (lines 56-57) to ensure both places
use the stricter status.
1 participant
This PR introduces the necessary architectural foundations for tracking and handling regulatory competition events within the Summit OSINT platform. It follows the specifications for the 'Summit Subsumption Plan v2', specifically targeting anti-competitive conduct allegations.
The changes encompass:
manifest.yamlandclaims.mddefining the claim registry mapping.CompetitionEventschema extendingEvidenceReportto trackREGULATORY_COMPETITION_EVENTtypologies.regulatoryNews.ts) and corresponding unit tests.antitrust.yml).CompetitionRiskAgent.PR created automatically by Jules for task 16575147726239482173 started by @BrianCLong
Summary by CodeRabbit
New Features
Documentation
Tests
Chores