feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite by Copilot · Pull Request #48036 · github/gh-aw

Copilot · 2026-07-25T15:57:41Z

Implements the specs/intent-attribution-compliance/README.md formal spec, which defines minimum conformance invariants for the Intent Attribution & Agent Governance system. PolicyCompiler had no Compile method, making the policy compilation path untestable and unimplemented.

`pkg/intent/policy.go`

PolicyCompiler.Compile(IntentRecord, RepositoryContext) ExecutionPolicy — applies matching rules sequentially; falls back to safest default when no rules match.
safestDefaultPolicy() — propose_only autonomy, none write scope, human approval required, auto-merge explicitly denied (*bool = false), MaxAttempts: 1.
PolicyRule.matches() — condition fields are wildcards when empty; currently gates on When.Org.
mergePolicy(base, fragment) — stricter-wins semantics: OR for HumanApprovalRequired, AND for AutoMergeAllowed, min for MaxAttempts.

`pkg/intent/intent_formal_test.go` (new)

Ten deterministic tests covering all invariants from the behavioral coverage map (!integration build tag, intent_test package):

Test	Invariant
`TestFormal_ExplicitIntentWins`	P1 — Explicit metadata wins over closing issues and labels
`TestFormal_SingleClosingIssue`	P2 — One closing issue → `source: closing_issue`
`TestFormal_MultipleClosingIssuesAmbiguous`	P3 — 2+ closing issues → `status: ambiguous`
`TestFormal_AmbiguousNeverMapped`	P4 — Ambiguous records never become `mapped`
`TestFormal_LabelFallback`	P5 — PR labels used as fallback when no closing issues
`TestFormal_UnlinkedWhenNoSource`	P6 — No source → `status: unlinked`, `source: none`
`TestFormal_SafestPolicyFields`	P7 — Zero-rule compiler returns the safest execution policy
`TestFormal_PolicyDeterminism`	P8 — Same inputs always yield identical policies
`TestFormal_ExplicitOverridesSuggested`	P9 — Explicit intent never returns `suggested` status
`TestFormal_SingleSourcePerRecord`	P10 — Every resolved record carries exactly one source

go test ./pkg/intent/... -run Formal
ok  github.com/github/gh-aw/pkg/intent  0.005s

Fixes [formal-spec] specs/intent-attribution-compliance/README.md — Formal model & test suite — 2026-07-25 #48035

Generated by 👨‍🍳 PR Sous Chef · gpt54 · 4.65 AIC · ⌖ 8.93 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

Generated by 👨‍🍳 PR Sous Chef · gpt54 · 8.27 AIC · ⌖ 7.9 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

Generated by 👨‍🍳 PR Sous Chef · gpt54 · 28.9 AIC · ⌖ 8.1 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

Generated by 👨‍🍳 PR Sous Chef · gpt54 · 5.95 AIC · ⌖ 5.16 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

…uite (P1–P10) Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

Copilot

Pull request overview

Implements intent policy compilation and adds formal compliance tests for attribution invariants.

Changes:

Adds policy rule matching, merging, and safe defaults.
Adds ten attribution and governance compliance tests.
Policy precedence and fail-closed behavior require corrections.

Show a summary per file

File	Description
`pkg/intent/policy.go`	Implements policy compilation and merging.
`pkg/intent/intent_formal_test.go`	Adds formal compliance tests.

Review details

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comments suppressed due to low confidence (2)

pkg/intent/policy.go:115

Rules are ordered from highest to lowest precedence, but these unconditional assignments let every later, lower-precedence rule replace an earlier constraint—for example, bounded can replace propose_only, or any_branch can replace none. Compare the documented restrictiveness of these enum values (or retain the first specified value) so lower-precedence rules cannot weaken the result.

	if fragment.Autonomy != "" {
		result.Autonomy = fragment.Autonomy
	}
	if fragment.WriteScope != "" {
		result.WriteScope = fragment.WriteScope

pkg/intent/policy.go:129

Appending allowed-tool lists unions permissions instead of combining constraints. If a higher-precedence rule allows only read and a lower rule allows only write, this returns both tools rather than the empty intersection; cloneStrings also converts an explicit non-nil empty deny-all list to nil/unrestricted. Intersect non-nil allowlists while preserving the nil-versus-empty distinction.

	result.AllowedTools = append(cloneStrings(base.AllowedTools), fragment.AllowedTools...)

Files reviewed: 2/2 changed files
Comments generated: 3
Review effort level: Medium

…iance

gh-aw-bot · 2026-07-25T16:19:26Z

@copilot please run the pr-finisher skill, address the unresolved review feedback below, and rerun checks once the branch is up to date.

Unresolved review feedback (newest first):

Copilot reviewer: feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite #48036 (comment)
Copilot reviewer: feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite #48036 (comment)
Copilot reviewer: feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite #48036 (comment)

Generated by 👨‍🍳 PR Sous Chef · gpt54 · 4.65 AIC · ⌖ 8.93 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

…ority/Risk in policy rules - Compile() short-circuits unlinked/ambiguous records to safestDefaultPolicy() regardless of any configured rules, fixing the fail-closed contract - Compile() uses a fresh accumulator seeded by the first matching rule so that permissive values (auto_merge: true, max_attempts > 1) are no longer silently discarded by the safest-default base - matches() now gates on Domain, Priority, and Risk via record labels; checks Org against both repo.Org and repo.Owner - Adds TestFormal_FailClosedForIndeterminate (P7b): verifies both unlinked and ambiguous records receive the safest policy even with a permissive wildcard rule Co-authored-by: gh-aw-bot <259018956+gh-aw-bot@users.noreply.github.com>

…MergeTrue - deepCopyPolicy() helper ensures AutoMergeAllowed, AllowedTools, DeniedTools, RequiredChecks, and RuleIDs are freshly allocated so accumulated policy cannot alias the original rule.Set fields - Rename autoMergeTrue → autoMerge in TestFormal_FailClosedForIndeterminate Co-authored-by: gh-aw-bot <259018956+gh-aw-bot@users.noreply.github.com>

Copilot · 2026-07-25T16:35:32Z

@copilot please run the pr-finisher skill, address the unresolved review feedback below, and rerun checks once the branch is up to date.

Unresolved review feedback (newest first):...

All three reviewer threads are addressed and replied to. Summary of changes:

pkg/intent/policy.go

Compile: short-circuits unlinked/ambiguous records to safestDefaultPolicy() before any rule evaluation (fail-closed contract)
Compile: uses a fresh accumulator seeded by deepCopyPolicy(rule.Set) for the first matching rule, so permissive values (auto_merge: true, max_attempts > 1) are no longer silently clamped
matches: now evaluates Domain, Priority, and Risk against rec.Labels; checks Org against both repo.Org and repo.Owner
deepCopyPolicy: new helper that freshly allocates AutoMergeAllowed, AllowedTools, DeniedTools, RequiredChecks, and RuleIDs to prevent aliasing of rule fields

pkg/intent/intent_formal_test.go

Adds TestFormal_FailClosedForIndeterminate (P7b): both unlinked and ambiguous records return the safest policy even when a permissive wildcard rule is configured

Local validation: make agent-report-progress green (lint + test-unit pass). CI must be re-triggered by a maintainer after this push.

…iance

gh-aw-bot · 2026-07-25T17:50:10Z

@copilot please run the pr-finisher skill, review the remaining unresolved feedback on this PR, address anything still outstanding, and rerun checks once the branch is up to date.

A prior sous-chef nudge was addressed, but the PR still appears active and may need final review/cleanup before merge.

Generated by 👨🍳 PR Sous Chef
_{Comment /souschef to run again}

Generated by 👨‍🍳 PR Sous Chef · gpt54 · 8.27 AIC · ⌖ 7.9 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

Copilot · 2026-07-25T17:59:26Z

@copilot please run the pr-finisher skill, review the remaining unresolved feedback on this PR, address anything still outstanding, and rerun checks once the branch is up to date.

A prior sous-chef...

All outstanding review feedback was addressed in the previous pass. Current state:

Reviews — All three reviewer threads addressed, replied to, and ready to resolve (fail-closed short-circuit, matches predicate coverage, P7b indeterminate test)
Branch — Up to date with main (merge commit 86f1c78)
Local validation — make agent-report-progress-no-test passes (lint green, all lock files in sync); go test ./pkg/intent/... passes (all 11 formal tests + existing resolver/spec tests)

No further changes needed. CI must be re-triggered by a maintainer (close/reopen, workflow_dispatch, or a push) before merge.

gh-aw-bot · 2026-07-25T18:18:39Z

@copilot please run the pr-finisher skill, resolve the still-open review threads that already have follow-up replies, and rerun checks once the branch is up to date.

Unresolved review feedback (newest first):

Copilot reviewer: feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite #48036 (comment)
Copilot reviewer: feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite #48036 (comment)
Copilot reviewer: feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite #48036 (comment)

A prior response indicates these items were addressed, so please resolve the corresponding threads if they are complete and confirm the PR is ready for maintainer review.

Generated by 👨🍳 PR Sous Chef
_{Comment /souschef to run again}

Generated by 👨‍🍳 PR Sous Chef · gpt54 · 28.9 AIC · ⌖ 8.1 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

Copilot · 2026-07-25T18:25:39Z

@copilot please run the pr-finisher skill, resolve the still-open review threads that already have follow-up replies, and rerun checks once the branch is up to date.

Unresolved review feedback (new...

All three threads (r3650510295, r3650510286, r3650510278) were addressed in code (commits 74d27ad, be0ea7d) and replied to. The GitHub GraphQL API is blocked in this sandbox, so I cannot programmatically resolve the threads — a maintainer will need to click "Resolve conversation" on each.

The PR is otherwise ready: all 27 tests pass, lint is clean, branch is up to date with main.

github-actions · 2026-07-25T18:34:50Z

🤖 PR Triage

Field	Value
Category	feature
Risk	Medium
Priority Score	58/100
Score Breakdown	impact: 30, urgency: 12, quality: 16
Recommended Action	📦 batch_review
CI Status	✅ copilot checks passed

Rationale: Implements and a formal attribution compliance test suite (2 files, 396 additions). Adds previously-missing implementation for a formal spec. Medium risk due to new API surface and policy compilation logic. CI passes. Needs human review of policy semantics.

Generated by 🔧 PR Triage Agent · sonnet46 · 36.7 AIC · ⌖ 8.07 AIC · ⊞ 5.7K · ◷

…iance

gh-aw-bot · 2026-07-25T21:17:48Z

@copilot please run the pr-finisher skill, resolve the still-open review threads that already have follow-up replies, and confirm this PR is ready for maintainer review.

Unresolved review feedback (newest first):

Copilot reviewer: feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite #48036 (comment)
Copilot reviewer: feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite #48036 (comment)
Copilot reviewer: feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite #48036 (comment)

A prior response indicates these items were addressed, so please resolve the corresponding threads if complete and rerun checks if anything changes.

Generated by 👨🍳 PR Sous Chef
_{Comment /souschef to run again}

Generated by 👨‍🍳 PR Sous Chef · gpt54 · 5.95 AIC · ⌖ 5.16 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

Initial plan

bd5c050

Copilot AI assigned Copilot and pelikhan Jul 25, 2026

Copilot AI linked an issue Jul 25, 2026 that may be closed by this pull request

[formal-spec] specs/intent-attribution-compliance/README.md — Formal model & test suite — 2026-07-25 #48035

Open

Copilot started work on behalf of pelikhan July 25, 2026 15:58 View session

feat(intent): add PolicyCompiler.Compile and formal compliance test s…

d9a8fc1

…uite (P1–P10) Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

Copilot AI changed the title ~~[WIP] Formalize intent attribution compliance specification~~ feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite Jul 25, 2026

Copilot finished work on behalf of pelikhan July 25, 2026 16:12

Copilot AI requested a review from pelikhan July 25, 2026 16:12

pelikhan marked this pull request as ready for review July 25, 2026 16:13

Copilot AI review requested due to automatic review settings July 25, 2026 16:13

Copilot started reviewing on behalf of pelikhan July 25, 2026 16:13 View session

Copilot AI reviewed Jul 25, 2026

View reviewed changes

Comment thread pkg/intent/policy.go Outdated

Comment thread pkg/intent/policy.go Outdated

Comment thread pkg/intent/intent_formal_test.go

Merge branch 'main' into copilot/formal-spec-intent-attribution-compl…

8237290

…iance

github-actions Bot mentioned this pull request Jul 25, 2026

[pr-sous-chef] PR Sous Chef run report - 2026-07-25T00:16:35Z #47879

Open

Copilot started work on behalf of gh-aw-bot July 25, 2026 16:20 View session

Copilot AI and others added 2 commits July 25, 2026 16:34

Copilot finished work on behalf of gh-aw-bot July 25, 2026 16:36

Copilot AI requested a review from gh-aw-bot July 25, 2026 16:36

github-actions Bot mentioned this pull request Jul 25, 2026

[Contribution Check Report] Contribution Check — 2026-07-25 #47889

Open

Merge branch 'main' into copilot/formal-spec-intent-attribution-compl…

86f1c78

…iance

Copilot started work on behalf of gh-aw-bot July 25, 2026 17:51 View session

Copilot finished work on behalf of gh-aw-bot July 25, 2026 18:00

Copilot started work on behalf of gh-aw-bot July 25, 2026 18:20 View session

Copilot finished work on behalf of gh-aw-bot July 25, 2026 18:26

github-actions Bot added pr-action:batch_review pr-agent:copilot-swe-agent pr-priority:medium pr-risk:medium pr-type:feature labels Jul 25, 2026

github-actions Bot mentioned this pull request Jul 25, 2026

[PR Triage Report] PR Triage Report — 2026-07-25 (Run 30169682123) #48050

Open

Merge branch 'main' into copilot/formal-spec-intent-attribution-compl…

3c54125

…iance

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite#48036

feat(intent): implement PolicyCompiler.Compile and formal attribution compliance test suite#48036
pelikhan with Copilot wants to merge 7 commits into
mainfrom
copilot/formal-spec-intent-attribution-compliance

Copilot AI commented Jul 25, 2026 •

edited by github-actions Bot

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

gh-aw-bot commented Jul 25, 2026

Uh oh!

Copilot AI commented Jul 25, 2026

Uh oh!

gh-aw-bot commented Jul 25, 2026

Uh oh!

Copilot AI commented Jul 25, 2026

Uh oh!

gh-aw-bot commented Jul 25, 2026

Uh oh!

Copilot AI commented Jul 25, 2026

Uh oh!

github-actions Bot commented Jul 25, 2026

Uh oh!

gh-aw-bot commented Jul 25, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Uh oh!

Conversation

Copilot AI commented Jul 25, 2026 • edited by github-actions Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

pkg/intent/policy.go

pkg/intent/intent_formal_test.go (new)

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Review details

Uh oh!

Uh oh!

Uh oh!

Uh oh!

gh-aw-bot commented Jul 25, 2026

Uh oh!

Copilot AI commented Jul 25, 2026

Uh oh!

gh-aw-bot commented Jul 25, 2026

Uh oh!

Copilot AI commented Jul 25, 2026

Uh oh!

gh-aw-bot commented Jul 25, 2026

Uh oh!

Copilot AI commented Jul 25, 2026

Uh oh!

github-actions Bot commented Jul 25, 2026

🤖 PR Triage

Uh oh!

gh-aw-bot commented Jul 25, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Copilot AI commented Jul 25, 2026 •

edited by github-actions Bot

Loading

`pkg/intent/policy.go`

`pkg/intent/intent_formal_test.go` (new)