feat: agent-driven policy management MVP#1151

Merged

johntmyers merged 23 commits intomainfrom

feat/agent-driven-policy-management

May 9, 2026

Commits on May 8, 2026

docs(rfc): add agent-driven policy management

zredlined
authored and
johntmyers
committed
docs(rfc): switch policy MVP to local API

zredlined
authored and
johntmyers
committed
docs(rfc): clarify policy advisor skill and local logs

zredlined
authored and
johntmyers
committed
feat(sandbox): add agent-driven policy proposal loop

zredlined
authored and
johntmyers
committed
test(examples): add codex policy dogfood loop

zredlined
authored and
johntmyers
committed
refactor(examples): make policy demo agent-agnostic

zredlined
authored and
johntmyers
committed
refactor(examples): colocate policy validation harness

zredlined
authored and
johntmyers
committed
docs(examples): add policy demo env sample

zredlined
authored and
johntmyers
committed
docs(examples): use placeholder env example

zredlined
authored and
johntmyers
committed
feat(sandbox): wire policy.local denials to OCSF JSONL log

zredlined
authored and
johntmyers
committed
feat(cli): show L7 protocol/method/path in rule get output

zredlined
authored and
johntmyers
committed
refactor(examples): rewrite policy demo as Codex-default loop

zredlined
authored and
johntmyers
committed
style(sandbox,cli): apply rustfmt

zredlined
authored and
johntmyers
committed
perf(examples): cap Codex reasoning at 'low' in policy demo

zredlined
authored and
johntmyers
committed
fix(sandbox): harden policy.local denials endpoint

zredlined
authored and
johntmyers
committed
fix(examples): redact tokens in agent log tail and validate DEMO_FILE_DIR

zredlined
authored and
johntmyers
committed
refactor(sandbox): centralize policy.local routes and skill path

zredlined
authored and
johntmyers
committed
feat(sandbox): switch /v1/denials to shorthand log pass-through

zredlined
authored and
johntmyers
committed
chore(sandbox): align proto inits with main's L7 GraphQL additions

zredlined
authored and
johntmyers
committed
feat(sandbox): gate agent policy proposals behind opt-in feature flag

zredlined
authored and
johntmyers
committed
test(policy-advisor): require proposal opt-in for e2e

zredlined
authored and
johntmyers
committed
refactor(sandbox): group policy poll loop state
johntmyers
committed
test(e2e): isolate Kubernetes user namespace test
johntmyers
committed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: agent-driven policy management MVP#1151

feat: agent-driven policy management MVP#1151
johntmyers merged 23 commits intomainfrom
feat/agent-driven-policy-management

Commits on May 8, 2026

docs(rfc): add agent-driven policy management

docs(rfc): switch policy MVP to local API

docs(rfc): clarify policy advisor skill and local logs

feat(sandbox): add agent-driven policy proposal loop

test(examples): add codex policy dogfood loop

refactor(examples): make policy demo agent-agnostic

refactor(examples): colocate policy validation harness

docs(examples): add policy demo env sample

docs(examples): use placeholder env example

feat(sandbox): wire policy.local denials to OCSF JSONL log

feat(cli): show L7 protocol/method/path in rule get output

refactor(examples): rewrite policy demo as Codex-default loop

style(sandbox,cli): apply rustfmt

perf(examples): cap Codex reasoning at 'low' in policy demo

fix(sandbox): harden policy.local denials endpoint

fix(examples): redact tokens in agent log tail and validate DEMO_FILE_DIR

refactor(sandbox): centralize policy.local routes and skill path

feat(sandbox): switch /v1/denials to shorthand log pass-through

chore(sandbox): align proto inits with main's L7 GraphQL additions

feat(sandbox): gate agent policy proposals behind opt-in feature flag

test(policy-advisor): require proposal opt-in for e2e

refactor(sandbox): group policy poll loop state

test(e2e): isolate Kubernetes user namespace test