Files

T

kami 1b58bc325e wip(freestyle/acr): grounding & edit-tool fixes + ACR-compiler experiment

This branch's uncommitted WIP, committed together (entangled at file level).
Distinct pieces of work:

Freestyle QA fixes (this session):
- FileEditTool: pre-validate replace anchor in validateRequest — reject a
  missing/ambiguous target BEFORE the approval gate, mirroring read/write's
  file-not-found / read-before-write pre-checks. Shared not-found/ambiguous
  messages between validate and execute so they can't drift.
- PlanGrounder: add `scanned` flag; when no RepoMapComputedEvent was recorded,
  repoMapPaths is "unknown" not "empty workspace" — skip scope grounding
  (which proves a path ABSENT) so real paths (apps/server/**) aren't falsely
  rejected. Build-manifest check still runs.
- FreestyleDriver: wire scanned=(repoMap!=null); on plan rejection emit a
  session-terminal WorkflowFailedEvent so a rejected run reads FAILED, not the
  COMPLETED-lie (last verdict was the planning-phase WorkflowCompleted).
- ServerModule: resolve project-memory workspace root from the session's bound
  workspace (sessionWorkspaceRoot) instead of boot-static pm.repoRoot(), fixing
  the workspace-binding divergence (correx vs empty scratch dir). Retire tracked
  in Vikunja #266.
- LaunchRegistrationRaceTest: join registered jobs before asserting launchCount
  — computeIfAbsent returns the Job immediately but the fire-and-forget launch
  body lagged awaitAll (the 49-vs-50 flake).

ACR concept-compiler experiment (pre-existing WIP on this branch):
- ExecutionPlanCompiler/Model/PlanLinter, #264 needs-seam (sessionArtifacts),
  LSP diagnostics subsystem (LspDiagnosticEvents/Runner/Lsp4j), BootWorkspace,
  config surface, workflow prompts/schemas, orchestrator advance-don't-rerun.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-19 01:20:37 +04:00

2.2 KiB

Raw Blame History

infrastructure/workflow/

Purpose

Workflow and prompt loading adapters. Parses TOML workflow definitions into core:transitions execution plans (TomlWorkflowLoader, ExecutionPlanCompiler), loads prompt files from the filesystem (FileSystemPromptLoader), and validates plan structure (PlanLinter).

Ownership

Adapter for core:transitions and core:inference workflow interfaces. Depends on core:transitions, core:inference, core:events, core:artifacts. Uses Jackson for TOML parsing.

Local Contracts

WorkflowLoader (implemented by TomlWorkflowLoader) is the interface for reading workflow definitions; implementations must not embed domain logic beyond parsing and structural validation.
PromptLoader (implemented by FileSystemPromptLoader) reads prompt text from disk; filesystem reads are environment observations — callers must record the loaded content as events if replay must reproduce the exact prompt (invariant #9).
ExecutionPlanCompiler converts the parsed ExecutionPlanModel into a runnable plan for core:transitions; compilation is deterministic given the same input model.
PlanLinter enforces structural rules (e.g. unreachable stages are rejected); linting failures throw WorkflowValidationException.
PlanDerivedManifest exposes the write manifest derived from a plan.
For a plan with no explicit build expectation, ExecutionPlanCompiler marks every write-declaring stage and the graph-terminal stage for the runtime auto build gate; plans with no declared writes are not represented as compiler-verified.
When a plan declares a dod producer, freestyle implementation/review stages consume that session-scoped artifact; reviewer prompts are compiler-bound to its reviewer-owned criteria.
Lsp4jDiagnosticsRunner uses LSP 3.17 pull diagnostics for registered languages and degrades to the static one-shot floor when a server is unavailable.

Work Guidance

Standard adapter rules apply (see parent AGENTS.md). Filesystem I/O in withContext(Dispatchers.IO). TOML parsing errors must be surfaced as WorkflowValidationException, not raw Jackson exceptions.

Verification

./gradlew :infrastructure:workflow:test --rerun-tasks

Child DOX Index

No child AGENTS.md (leaf module).

2.2 KiB Raw Blame History