feat: opt-in published Terraform modules from approved sources (iteration 8)

Infrastructure code is plain resources by default. An Execution may opt in
with terraform_modules; the deployment default is TERRAFORM_MODULES, off.

- A module is accepted only from the registry namespaces the provider bundle
  lists (terraform-google-modules), at one exact version. Any other source is
  refused before Terraform runs; until now nothing stopped generated code
  naming any source for terraform init to download.
- terraform_module looks up a module's inputs, outputs and submodules from
  the registry and says when it cannot be used with the pinned provider.
- skills/google-cloud-iac-modules: when a module fits, and four modules with
  examples a test validates against hashicorp/google 8.6.0.
- Opted in, the IaC author and validator get the Skill and the lookup. Not
  opted in, they get neither and a module block is refused in code.
- A Change request follows its Baseline. execution.json records the choice.
- case-07 runs case 03's request with modules opted into.

Azure (aztfm) and AWS (terraform-aws-modules) sources are recorded in the
plan for when those Cloud providers are added. No case has run with this.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-09 22:09:29 +01:00
parent a8ed21b89d
commit ef37f59bad
35 changed files with 1482 additions and 7 deletions

View File

@@ -53,6 +53,7 @@ from app.tools.assessment import assess
from app.tools.execution import ORCHESTRATOR, OrchestratorToolbox, specialist_tools
from app.tools.guardrail import EXECUTION_SCOPE, instructs_agent
from app.tools.meaning import settle_meaning
from app.tools.modules import MODULE_TOOL, MODULES_OPTED_IN
from app.tools.pillars import ADVICE_KEY, KEPT_FOR_CHANGES, pillars_touched
from app.tools.skill_routing import read_first
from app.workflows.chain import (
@@ -458,6 +459,15 @@ def make_execution_nodes(
role = dataclasses.replace(
role, skills=(*role.skills, *(n for n in named if n not in role.skills))
)
opted_in = bool(task_input.get("terraform_modules"))
MODULES_OPTED_IN.set(opted_in)
if opted_in and role.modules_skill:
role = dataclasses.replace(role, skills=(*role.skills, role.modules_skill))
elif MODULE_TOOL in role.tools:
# Plain resources: no modules Skill and no module lookup.
role = dataclasses.replace(
role, tools=tuple(tool for tool in role.tools if tool != MODULE_TOOL)
)
if role.first_attempt_model and task_input.get("first_attempt"):
logger.info(
"[%s] %s takes %s for a first attempt",
@@ -874,6 +884,8 @@ def _specialist_input(
"first_attempt": not ledger.feedback(kind)
and (attempt == 1 or kind.value in deliverables),
"allow_cloud_read": state.get("allow_cloud_read"),
# Whether this Execution opted into published Terraform modules.
"terraform_modules": bool(state.get("terraform_modules")),
"working": dict(state.get("working", {}).get(kind.value, {})),
# Whether the user has been shown a draft of this Deliverable. Answering some
# other question about it, such as what to do after it stopped, is not that.
@@ -903,6 +915,9 @@ def _specialist_input(
# Skills carrying the organisation's standards or this engagement's
# constraints. Where one disagrees with general guidance, it wins.
"overlay_skills": sorted(state.get("overlay_skills") or {}),
# False: infrastructure code is plain resources. True: a published
# module may be used where the modules Skill says one fits.
"terraform_modules": bool(state.get("terraform_modules")),
# The pillars a change touches, when that could be judged: the design
# advisor consults those and keeps its earlier advice for the rest.
"pillars_to_consult": (hints or {}).get(kind.value),
@@ -1267,6 +1282,8 @@ def _write_outputs(
"baseline": (state.get("baseline") or {}).get("execution_id"),
# The overlay Skills it loaded, with the version of each.
"overlay_skills": dict(state.get("overlay_skills") or {}),
# Whether its infrastructure code was allowed published modules.
"terraform_modules": bool(state.get("terraform_modules")),
"status": status,
"warnings": list(state.get("warnings", [])),
# Flags a person should look at; nothing was done about them.