kami
3467826d4a
The reviewer prompt told the model to judge "the analysis requirements," but the reviewer stage only needed [patch, impl_plan] — it never actually received the analysis artifact, so the acceptance criteria it was meant to check against were never in its context. A reliability gate checking against criteria it can't see is theater. - reviewer now needs `analysis`, so the diff is judged against concrete, pre-stated acceptance criteria (§5 narrow question) rather than whole files against taste; the §3 minItems enforcement guarantees those criteria are non-empty. - reviewer.md operationalizes §5's two principles: evaluate the diff against each requirement (findings must map to a requirement/plan-step/defect), and don't re-report what deterministic tools already catch (compiler/detekt/tests — trust verification, point at failures, don't re-derive them). This is the workflow-level realization of §5. The full static-first infrastructure (running static tools as a pipeline step and mechanically excluding their findings from reviewer context) needs a static-findings event representation and is deferred. §6 critic calibration needs runtime history before it can say anything (spec ordering #5).
134 lines
4.4 KiB
TOML
134 lines
4.4 KiB
TOML
# Role pipeline: analyst → architect → planner → implementer ⇄ reviewer
|
|
#
|
|
# Each stage produces a typed artifact that the next stage `needs`, so work flows forward
|
|
# without a human relaying notes. The decision journal (pinned into every stage's context)
|
|
# carries steering/approvals/verdicts across the whole run, so the reviewer sees the same
|
|
# ground truth as the planner.
|
|
#
|
|
# The implementer⇄reviewer loop is gated by review_report.verdict:
|
|
# approved → done
|
|
# changes_requested → back to implementer (capped by implementer.max_retries, then escalates)
|
|
#
|
|
# Requires these artifact kinds in ~/.config/correx/config.toml (schemas under docs/schemas/):
|
|
# [[artifacts]]
|
|
# id = "analysis"; schema_path = "schemas/analysis.json"; llm_emitted = true
|
|
# [[artifacts]]
|
|
# id = "design"; schema_path = "schemas/design.json"; llm_emitted = true
|
|
# [[artifacts]]
|
|
# id = "impl_plan"; schema_path = "schemas/impl_plan.json"; llm_emitted = true
|
|
# [[artifacts]]
|
|
# id = "review_report"; schema_path = "schemas/review_report.json"; llm_emitted = true
|
|
#
|
|
# Prompt files (prompts/*.md, relative to this workflow) must exist for a real run.
|
|
|
|
id = "role_pipeline"
|
|
start = "analyst"
|
|
|
|
# 1. Understand the request and the relevant code. Read-only.
|
|
# ground_references: every workspace-relative file path the analysis names is checked
|
|
# for existence; a hallucinated path fails the stage and retries with the misses fed back.
|
|
[[stages]]
|
|
id = "analyst"
|
|
prompt = "prompts/analyst.md"
|
|
produces = [{ name = "analysis", kind = "analysis" }]
|
|
allowed_tools = ["file_read", "ShellTool"]
|
|
ground_references = true
|
|
token_budget = 16384
|
|
max_retries = 2
|
|
|
|
# 2. Decide the approach and component boundaries.
|
|
[[stages]]
|
|
id = "architect"
|
|
prompt = "prompts/architect.md"
|
|
needs = ["analysis"]
|
|
produces = [{ name = "design", kind = "design" }]
|
|
token_budget = 16384
|
|
max_retries = 2
|
|
|
|
# 3. Break the design into ordered, verifiable steps.
|
|
[[stages]]
|
|
id = "planner"
|
|
prompt = "prompts/planner.md"
|
|
needs = ["design"]
|
|
produces = [{ name = "impl_plan", kind = "impl_plan" }]
|
|
token_budget = 16384
|
|
max_retries = 2
|
|
|
|
# 4. Implement the plan. Writes files (jailed to the workspace). The loop target —
|
|
# max_retries here caps how many review→implement refinement rounds are allowed.
|
|
# Optional: a `writes` manifest (workspace-relative globs) hard-bounds where this
|
|
# stage may write — a FILE_WRITE outside it is blocked as scope creep. Left open
|
|
# here because the targets are task-specific; a task-scoped workflow would set e.g.
|
|
# writes = ["core/sessions/**", "testing/sessions/**"]
|
|
[[stages]]
|
|
id = "implementer"
|
|
prompt = "prompts/implementer.md"
|
|
needs = ["impl_plan"]
|
|
produces = [{ name = "patch", kind = "file_written" }]
|
|
allowed_tools = ["file_read", "file_write", "file_edit", "ShellTool"]
|
|
token_budget = 32768
|
|
max_retries = 3
|
|
|
|
# 5. Review the patch against the plan AND the analyst's acceptance criteria. The reviewer
|
|
# needs `analysis` so it judges the diff against concrete, pre-stated criteria (§5 narrow
|
|
# question) rather than whole files against taste.
|
|
[[stages]]
|
|
id = "reviewer"
|
|
prompt = "prompts/reviewer.md"
|
|
needs = ["patch", "impl_plan", "analysis"]
|
|
produces = [{ name = "review_report", kind = "review_report" }]
|
|
token_budget = 32768
|
|
max_retries = 2
|
|
|
|
# --- forward edges ---
|
|
|
|
[[transitions]]
|
|
id = "analyst-to-architect"
|
|
from = "analyst"
|
|
to = "architect"
|
|
condition_type = "artifact_validated"
|
|
condition_artifact_id = "analysis"
|
|
|
|
[[transitions]]
|
|
id = "architect-to-planner"
|
|
from = "architect"
|
|
to = "planner"
|
|
condition_type = "artifact_validated"
|
|
condition_artifact_id = "design"
|
|
|
|
[[transitions]]
|
|
id = "planner-to-implementer"
|
|
from = "planner"
|
|
to = "implementer"
|
|
condition_type = "artifact_validated"
|
|
condition_artifact_id = "impl_plan"
|
|
|
|
[[transitions]]
|
|
id = "implementer-to-reviewer"
|
|
from = "implementer"
|
|
to = "reviewer"
|
|
condition_type = "artifact_validated"
|
|
condition_artifact_id = "patch"
|
|
|
|
# --- verdict-gated loop exit / re-entry ---
|
|
|
|
[[transitions]]
|
|
id = "review-approved"
|
|
from = "reviewer"
|
|
to = "done"
|
|
condition_type = "artifact_field_equals"
|
|
condition_artifact_id = "review_report"
|
|
condition_field = "verdict"
|
|
condition_value = "approved"
|
|
condition_operator = "eq"
|
|
|
|
[[transitions]]
|
|
id = "review-changes-requested"
|
|
from = "reviewer"
|
|
to = "implementer"
|
|
condition_type = "artifact_field_equals"
|
|
condition_artifact_id = "review_report"
|
|
condition_field = "verdict"
|
|
condition_value = "approved"
|
|
condition_operator = "neq"
|