e7009bc304e9322e619b78c4e7868bbaaf4e87b3
7 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Brummel
|
edbbb68f97 |
feat(agents): pin explicit reasoning effort on every agent and workflow call
Effort joins model as a mandatory pin: an omitted field inherits the session effort, coupling every dispatch's thinking budget to whatever the user happens to be chatting at (often xhigh) — the same session-state coupling the model pin removes. The assignment follows the model split: - xhigh on every opus agent (judgement roles are the pipeline's quality floor and must not degrade with the session); - high on every sonnet agent (tightly-scoped plan execution gains little from xhigh but pays its latency per dispatch, and these are the per-task in-loop roles — wall-clock is the efficiency metric; not lower than high, since re-loops cost more than saved thinking); - medium inline in the workflow scripts for schema-bound extraction/verification stages that author no code (preflight, plan-extract, mini-verify, tree-check, finalize, build/suite verify). Workflow agent() calls pass effort explicitly on every call — whether frontmatter effort propagates through an agentType dispatch is undocumented, so the scripts do not rely on it. Policy documented in docs/agent-template.md § effort, mirroring § model. |
||
|
Brummel
|
6bfec9655c |
feat(agents): pin explicit model on every agent and workflow call
Agents and workflows previously carried no model field, so every dispatch inherited the session model — including fable, which is banned for all plugin agents and workflows by owner decree. Every dispatch now pins opus or sonnet explicitly. - opus (low-volume judgment gates whose misses silently poison downstream work): architect, bencher, debugger, fieldtester, grounding-check, plan-recon, quality-reviewer, spec-skeptic, tdd-author - sonnet (mechanical scope, in-loop or fanned out): docwriter, glossary-extractor, implementer, spec-reviewer, synthetic-user, tester - workflows: all 13 agent() call sites pin a model — sonnet everywhere except the quality-reviewer gate in implement-loop, the loop's last correctness check (spec-reviewer only gates task-text correspondence; real-bug finding is the documented opus strength) - docs/agent-template.md: model is now a mandatory frontmatter field, with the assignment rule and the fable ban recorded |
||
|
Brummel
|
c39a817982 |
feat(brainstorm): swarm-simulated discovery replacing the serial interview
Replace brainstorm's ~10 serial user round-trips with a parallel populate-then-triage: enumerate the load-bearing forks, populate them with a grounded synthetic-user swarm (mandatory per-answer citation), and triage — a fork the swarm settles on a cited shared ground is decided (user vetoes), a split or ungrounded-consensus is a direction fork the user settles. A cross-check surfaces any fork the orchestrator's own enumeration held open but the swarm closed. A fire-check + grounding floor skip the swarm when it would be ceremony. Under /boss the swarm runs autonomously: convergent forks are decided and recorded on the reference issue, only a divergent direction fork (or a sub-floor greenfield design) bounces. Retires trigger-4's "fresh brainstorm is too high-context to run autonomously" rationale — the swarm is the compaction. - brainstorm/agents/synthetic-user.md: new read-only swarm agent - brainstorm/SKILL.md: full rewrite to the swarm flow + new Iron Law - boss/SKILL.md: autonomous swarm-brainstorm (Iron Law, trigger 4, asymmetry, notifications, rationalisations, red flag) - docs/pipeline.md: brainstorm phase description - specify/SKILL.md: brainstorm characterised as swarm discovery, not interview closes #19 |
||
|
Brummel
|
4f83305525 |
feat(specify): add spec-production entry path; split brainstorm
Add `specify` as a third co-equal entry path into the dev cycle: it produces an approved spec from already-settled sources (an exhaustive issue, a long in-context design discussion, or a design brainstorm just ratified) with review but no interview. This is the producing half of a deliberate deciding/producing split — `brainstorm` shrinks to optional discovery, `specify` becomes the sole spec-production gate before `planner`, mirroring the RED->GREEN split that keeps tdd/debug honest. What moved: - brainstorm/SKILL.md: stripped of the hard-gate, the acceptance criterion, write-spec, self-review, grounding-check, user-review, and planner-handoff steps; terminal state is now handing a ratified design narrative to specify. Steps renumbered 1-5 (production steps left). - specify/SKILL.md (new): the production core, with a precondition gate (Step 1.5) that bounces to brainstorm the moment the sources do not resolve a load-bearing decision — the same discipline tdd uses. - The grounding-check agent moved brainstorm/agents/ -> specify/agents/ (no-orphan-agents: it lives under its dispatcher), refs repointed. - boss/SKILL.md: Entry-path reflection is now three-way (tdd / specify / brainstorm). specify dispatches autonomously (bounded, no interview) and pauses at its user-review gate; only a fresh brainstorm cycle stays a pre-dispatch bounce-back. - pipeline.md, README, profile-schema, the profile template, and the migration layout updated so every pipeline rendering agrees; specify is a CORE node (not opt-in, unlike tdd) carrying gates: [planner]. Design alternative rejected: parallel sibling skills sharing a docs/spec-production.md (extract-to-doc). Chosen extract-and-chain instead — the shared surface is ~70%, so a shared doc would either become the skill body or drift; chaining keeps one executed home for the gates. Verification (prose repo, no test suite): the spec's internal- consistency grep suite (no two-path drift, no direct brainstorm->planner edge, specify referenced in every rendering, grounding-check single home under specify, specify structural completeness) all green. Orchestrator inspection additionally fixed two dead step-refs the plan under-scoped (a "(Step 4)" lift-validation pointer and a "Skipping Step 7 self-review" red flag, both pointing at steps brainstorm no longer has) and corrected six pre-existing brainstorm->planner renderings in pipeline.md and tdd that predated this cycle. Known follow-ups (non-blocking): the committed spec writes `skills/specify/` in places (typo; skill dirs are repo-top-level) — to be corrected separately. The grounding-check hard-gate was degenerate for this very cycle (this repo has no profile and no test suite); the skip is documented in the spec and the session. |
||
|
Brummel
|
0b969838c0 |
refactor: single-source carrier/handoff contracts across skills
Apply the debug-skill pattern (commits 6410732..de42974) to the remaining skills: the agent file is the single source for each interface field's semantics; the SKILL.md copy is reduced to field names plus a pointer, marking the agent's contract table authoritative. Because SKILL.md loads into orchestrator context and agents/*.md into the subagent's fresh system prompt with no transclusion, duplicated field tables drift apart over time. - brainstorm: carrier (spec_path/iteration_scope) -> grounding-check; the absolute-path requirement now lives only in the agent. - planner: carrier (spec_path/iteration_scope/focus_hint) -> plan-recon, including the mandatory/optional markers and the BLOCKED-on-missing rule SKILL.md had omitted. - fieldtest: carrier + produced fields -> fieldtester; the skill-level `status` roll-up (clean/friction_found/bugs_found/infra_blocked), which is not part of the agent's run-status protocol, stays defined in SKILL.md only. - docwriter: carrier + produced fields -> docwriter agent. - implement: carrier (iter_id scratch-dir/stats/not-a-branch semantics) -> implement-orchestrator; per-task sub-status vocabulary moved into the orchestrator-agent (it runs the loop in a fresh context and could not read SKILL.md at runtime, yet referenced "the sub-status table" by name); task_text_path single-sourced in implementer with spec-reviewer cross-referencing. audit was already the reference implementation (pointers, no restated contracts) and is unchanged. closes #2 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Brummel
|
fc36647c28 |
feat: grounding-check code-block parse pass (issue #1 Fix 2)
Adds a third pass to the grounding-check agent: when the profile
declares `spec_validation.parsers`, every fenced spec block whose
fence label has an entry is run through its parser (temp file + `ext`,
`cmd` with {file}); a non-zero exit marks the block unparseable and
the aggregate status becomes BLOCK. Complementary to the existing
test-ratification search (checks the spec's own bytes, not codebase
behaviour) and independent of the orchestrator's Step-7 gate (Fix 1) —
a fresh-context second line of the same defense.
Amends the Iron Law to permit per-block parser runs (same read-only
spirit as test-list/type-check), adds an "Unparseable code blocks"
report section, a Common Rationalisation, a Red Flag, and the agent
description.
refs #1
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
||
|
Brummel
|
37482ed03d |
brainstorm: skill + grounding-check agent migrated
Seventh skill via the boss pattern. brainstorm is the spec-generation hard-gate; grounding-check is its Step-7.5 read-only assumption-ratification reviewer. Vocabulary substitutions: - AILang → "this project" - milestone → cycle - Boss → orchestrator - ailang-grounding-check → grounding-check - "the AILang program" / ".ail Form-A" → "the user-facing program in the project's canonical authoring/consumer form" - "Brummel (orchestrator) + Claude" → "orchestrator + Claude" AILang-specific bits dropped or generalized: - `docs/specs/<milestone>.md` / `docs/plans/` → `paths.spec_dir` / `paths.plan_dir` - AILang feature-acceptance criterion's three specific clauses (LLM-author-reaches-for-it, measurable correctness/redundancy improvement, no-reintroduction-of-core-constraint-bug) → "the criterion declared in the project's CLAUDE.md", with the three typical-shape clauses retained as illustrative - `design/contracts/0004-feature-acceptance.md` cross-ref → pointer to project CLAUDE.md - "AILang's own thesis is structured concrete form over prose description" → "concrete code first, prose second" (the discipline survives without the project-thesis hook) - The 2026-05-11 incident date → generic "recurring failure mode" framing (the discipline survives without the date) - `tea issues create --repo Brummel/AILang` → "the project's issue-tracker create command (typically tea/gh)" with both examples shown - `cargo test --list -p <crate>` / `cargo check` → "the project's test-list / type-check command" with Rust example - `crates/*/tests/`, `crates/*/src/**/tests.rs`, `examples/` → derived from `paths.code_roots` and the project's examples / fixtures convention - The `Spec-23 / prelude free-fn ne / typeclass elaboration` worked example → generic "spec section that proposes adding to a table or extending a pass without stating that the existing entries / passes cover the new shape" - AILang skill-system index reference (`skills/README.md`) → `../../README.md` (plugin's top-level) - "Form-A / .ail / monomorphised compare__T symbol" examples → generic "function names, type names, schema fields, pass names" example Universal substance preserved verbatim: - The hard-gate (3 lines) — NO IMPLEMENTATION UNTIL SPEC APPROVED - Nine-step process (explore context → clarify Q&A → propose 2-3 approaches → apply feature-acceptance → present in sections → write spec → self-review → grounding-check → user-review-gate → hand off) - "Concrete code first, prose second" discipline (the universally-applicable form of what was the AILang-thesis hook) - "The criterion is unjudgeable without concrete code" rule (universal good practice; project's CLAUDE.md picks the specific criterion) - Spec structure (Goal / Architecture / Concrete code shapes / Components / Data flow / Error handling / Testing strategy / Acceptance criteria) - Step-7 self-review checklist (5 items) - Step-7.5 grounding-check dispatch + PASS/BLOCK/INFRA_ERROR three-way classification + failure-mode procedure + re- dispatch on post-PASS edit rule - All 8 Common Rationalisations rows - All 9 Red Flags bullets - grounding-check's six-step process incl. assumption extraction, search design, ratification classification, aggregate status computation - grounding-check's Iron Law (5 lines), output format (exact layout preserved), 6 Common Rationalisations rows, 8 Red Flags bullets The brainstorm is the largest skill in the migration (366 → 355 lines after substitutions). Calibrated discipline kept intact per memory feedback_dont_strip_repeated_discipline.md: "concrete code first" + grounding-check hard-gate + "re- dispatch on post-PASS edit" are the load-bearing rules; all survive verbatim except for project-specific identifiers. |