Inline pinning test in pipeline.rs constructs the same chain
shape module_name_from_json produces on serde-parse failure
(leaf wrapped with "parsing JSON in <path>" context) and
asserts both layers survive the formatter. RED→GREEN against
the property, not against production line bytes — for a
two-character fix, extracting a helper just for testability
would be over-engineering.
The strip_locations regex collapses \nCaused by: chains; the
{:#} alternate Display joins with ': ' on one line, so the
collapser is a no-op on the fixed output. AILX cohort
unaffected — only the harness-side anyhow path (module
rename pre-check) was dropping cause information.
Harness suite: 14/14 green (was 13/13 + 1 new pin).
Architect drift_found, both [low]:
- INDEX backfill for commit 90512d5 (brainstorm Step 7.5 SKILL.md
edit + roadmap P1 todo removed without a paired INDEX mirror).
- README "Total 8 passed" understated the actual 13/13 sweep.
Both fixed inline (mechanical, ≤30 LOC) per CLAUDE.md trivial-edits
carve-out; no implementer dispatch.
Bench: all three scripts exit 0, 0 regressed, 5 unexplained
latency.explicit_at_rc improvements not coupled to milestone work
(no in-workspace crate touched). Baseline left pristine — future
audits will reveal whether the improvements hold.
All 9 spec acceptance criteria green. Milestone closed clean.
Milestone "Cross-model authoring-form test" closed. Live IONOS run
against Qwen/Qwen3-Coder-Next executed at temperature=0, max-turns=5,
token-budget=500000. Raw dataset under runs/2026-05-12-df7531/:
RUN_STATUS=ok, scores.csv with 8 rows (4 tasks × 2 cohorts),
summary.md, plus 156 per-turn raw artefacts (request/response/program/
stderr/stdout) preserved for any future analysis.
Headline numbers:
- AILX cohort: 2/4 green, 1/4 first-attempt, ~95k prompt + ~2.6k completion
- JSON cohort: 1/4 green, 0/4 first-attempt, ~192k prompt + ~15k completion
- Only first-attempt success was AILX on t3_main_prints (~5 lines of
tagged s-expr vs ~23 lines of structured JSON for the JSON cohort's
turn-1 attempt that needed correction).
- Per spec, single subject + single deterministic run = data point,
not verdict.
DESIGN.md §"Decision 6: authoring surface" gains an "Empirical
addendum (2026-05-12)" subsection: 6-row metric table, illustrative
t3 contrast, explicit single-subject scope note pointing at the
roadmap follow-up entry for multi-subject expansion.
Roadmap: P2 entry "Cross-model authoring-form test" removed (this
journal is the convention's one-line mirror); P3 entry
"Multi-subject expansion (cross-model authoring-form follow-up)"
added with the run dir named as baseline.
Milestone artefacts span three iters (cma.1 master mini-spec +
renderer; cma.2 harness + tasks + reference solutions; cma.3 this
live run + DESIGN.md addendum + close).
Sibling standalone Cargo crate `harness/` under
experiments/2026-05-12-cross-model-authoring/ (out-of-workspace
idiom carried forward from cma.1 verbatim). Six modules:
strip_locations (regex pass for form-asymmetric location info,
calibrated against five real `ail check`/`ail parse` stderr
captures), pipeline (subprocess wrapper for parse|check|build +
5s-timeout exec; preflight on ail+clang), ionos (blocking reqwest
client + retry policy per spec), mock (canned-response loader),
scoring (CSV + summary.md), tasks (definition struct + loader).
main.rs ties them into the per-(cohort,task) loop with budget
accounting and per-turn artefact recording.
Four MVP tasks land with reference solutions that compile, build,
and execute green through the actual ail+clang pipeline:
t1_add_three (chained `+` + io/print_int), t2_length (polymorphic
List + recursion), t3_main_prints (minimal IO module), t4_count_zeros
(prelude Eq Int + branched if). Reference solutions stay in canonical
AILang form — param_modes is omitted when every parameter is the
Implicit default, consistent with the existing examples/ corpus.
13/13 tests green: 5 lib unit (strip_locations) + 5 integration
(strip_locations against verbatim captured fixtures) + 1
verify_references (drives every reference through the real
ail+clang pipeline) + 1 mock_full_run (full eight-row sweep with
mixed green-on-turn-2 + turn-limit cycles) + 1 budget_abort
(synthetic budget exhaustion with budget_abort rows + run_status).
Two implementer-phase repairs beyond the plan, both small and
surfaced in the iter journal Concerns:
1. pipeline.rs renames the program file to `<module-name>.ail.json`
between parse and check because `ail check` enforces filename
stem == module name (compiler contract the plan did not anticipate).
2. main.rs fills synthetic budget_abort rows for tasks the outer
loop never reached so scores.csv preserves the expected eight-row
shape on budget exhaustion.
One plan/text mismatch carried over: README "Total 8 passed" reflects
the plan's four-suite count; actual sweep produces 13. Doc-fix
candidate for cma.3.
cma.3 (live IONOS run + DESIGN.md addendum + roadmap edits) remains
out of scope.
Walks the implementer from a fresh harness/ Cargo project to a green
test sweep across strip_locations (5 unit + 5 integration on real
captured stderr), verify_references (4 reference solutions run
through the live ail+clang pipeline locally), mock_full_run (eight
canned-cohort-task pairs end-to-end), and budget_abort (tiny budget
exhaustion). Six modules: strip_locations, pipeline, ionos
(reqwest blocking + retry per spec §Error handling), mock, scoring,
tasks. Captures five real stderr samples (recon-collected) as
fixtures; strip_locations regex calibrated to the actual diagnostic
shape (handles `at byte N`, anyhow `Caused by:` chains).
Workspace-table and .gitignore included in Task 1 from the outset
(learned from cma.1 surfaced concerns; not repeated as
post-hoc journal items). Out-of-workspace pattern matches render/
verbatim. AIL_BIN env var with PATH fallback for `ail` resolution;
clang preflight check added since `ail build` shells to clang.
Two explicit deferrals to implementer named in the plan:
ParamMode names (lifted from cma.1) and prelude function symbols
(from crates/ailang-check/src/builtins.rs); both stable from cma.1
authoring, no re-derivation needed.
New top-level experiments/2026-05-12-cross-model-authoring/ (out of
root Cargo workspace; nested-crate standalone via empty [workspace]
table per Cargo idiom). The renderer projects one canonical
master/spec.md into two form-specific files (rendered/json.md and
rendered/ailx.md) by walking three directive forms ({form-only:
json}, {form-only: ailx}, {example: <id>}) and emitting per-example
fenced blocks sourced from 13 curated .ail.json fixtures.
Four test gates green (10/10 total):
- splitter_unit (7) — directive parser, malformed inputs panic
- spec_completeness (1) — AST-variant visitor lifted verbatim from
schema_coverage.rs; 34/34 variants covered by the curated subset
- example_roundtrip (1) — every fixture roundtrips through
ailang_surface::{print, parse} to identical canonical bytes
- token_balance (1) — form-only block totals balanced to 3.22% under
tiktoken-rs::cl100k_base (gate is ±5%)
Six of the 34 variants did not have a dedicated fixture topic in the
plan and were absorbed into the closest existing fixture per the
plan's Step 4.14 escape hatch (Let/Clone → fn_calls_prelude; LetRec
→ data_with_match; If → match_literal_pattern; ReuseAs →
data_simple; Const → floats). Surfaced as a journal note, not a
plan revision.
Two ancillary additions vs. plan, both structural Cargo necessities,
spec-compatible: render/Cargo.toml carries an empty [workspace] table
so the nested crate refuses parent-workspace discovery, and
render/.gitignore drops /target + Cargo.lock. Both surfaced inline
in the per-iter journal's Concerns section.
cma.2 (harness) and cma.3 (live IONOS run + DESIGN.md addendum +
journal + roadmap edits) remain out of scope per the spec.
Walks the implementer from a fresh directory to a green test sweep
(splitter_unit, spec_completeness, example_roundtrip, token_balance)
plus two checked-in rendered/*.md files. Visitor borrowed verbatim
from schema_coverage; master/examples authored fresh as a curated 13-
fixture set (one per AST variant cluster); master/spec.md authored in
13 sections with form-only blocks balanced by the ±5% gate.
Open authoring deferrals to the implementer (named at the planner
level, intentional): exact ParamMode enum names and the canonical
prelude function names — both retrieved from current source by
reading ailang-core/src/ast.rs and the prelude module at authoring
time, rather than pinned in the plan against a possibly-stale recall.
Single foreign subject (Qwen3-Coder-Next via IONOS). Two blind
cohorts: one sees only a JSON mini-spec, the other only an .ailx
mini-spec; same four tasks. Fairness anchored by a master source
plus a renderer (built on the existing ailang-surface roundtrip
machinery) that projects two form versions from one canonical
content base. Harness shells out to ail parse / check / build / run
and feeds back location-stripped errors so the JSON-pointer
asymmetry doesn't tilt the experiment. Out of scope for v1: a
verdict on Decision 6, a free-choice cohort, repetitions, a second
subject.
Grounding-check PASS on cma.1 (master + renderer + tests).
Names the runtime infrastructure prerequisite (malloc-backed refcounted
Str alongside static @.str_* globals) as its own milestone. Show + print
rewire now carries an explicit depends-on link. Existing Eq/Ord [x]
entry removed (shipped milestone 23; mirrored in WhatsNew + journal).
CLAUDE.md previously mixed universal facts (agent role boundaries,
commit discipline, design rationale, file roles, TDD-for-bugs) with
mode-specific autonomy rules (direction freedom, notifications,
WhatsNew procedure). Autonomous-by-default conflicted with the user's
intent that a fresh session should be collaborative-interactive unless
explicitly elevated.
Add `skills/boss/` containing only the three genuinely mode-specific
subsections — Direction freedom, Notifications, Done-state notifications:
WhatsNew.md. Trim CLAUDE.md from 343 to 243 lines; extend the skill-
system pointer paragraph with a one-sentence /boss gate. Universal
orchestrator discipline stays in CLAUDE.md because it applies whether
/boss is active or not.
Two cross-references that named the moved subsections by sub-heading
are repointed: skills/implement/SKILL.md and the implement-orchestrator
agent's standing reading list. The other ~11 agent-file references to
"orchestrator framing" still resolve correctly because that framing
stays in CLAUDE.md.
skills/README.md skill table extended with a `boss` row (now eight
skills); pipeline-diagram caption notes /boss wraps the pipeline.
.claude/skills/boss symlink follows the existing relative-path
convention.
Recon surfaced that several draft 'moved OUT' sections were universal,
not mode-specific (agent role boundaries, authority over skills, design
rationale, feature-acceptance criterion, when-not-to-delegate). These
apply in any session — interactive or /boss-active — because agents can
be dispatched, design choices can be made, and skills can be edited
outside /boss too.
Tighten the move-list to the three genuinely mode-specific subsections:
Direction freedom, Notifications, Done-state notifications: WhatsNew.md.
Everything else stays in CLAUDE.md. /boss becomes leaner, the universal/
mode-specific boundary is drawn at content that only applies inside the
autonomous loop. Re-dispatched grounding-check: PASS.
Closes the P1 todo from earlier today: Step 7.5 PASS report is
bound to the exact bytes of the spec at dispatch time. Any
subsequent edit — wording polish, user-requested change, anything
— invalidates the report and forces a fresh dispatch before the
Step 8 commit.
Three edits:
- Step 7.5 gets a 'Re-dispatch on any post-PASS edit' subsection
stating the rule and explaining why (PASS attests to bytes).
- Step 8 wording: '... edit in place, re-run Step 7 AND re-dispatch
Step 7.5, then return here. Only proceed after approval AND a
fresh Step 7.5 PASS.'
- Common Rationalisations + Red Flags gain matching entries
('just polishing wording, no need to re-dispatch' / 'Editing the
spec after PASS without re-dispatching').
Roadmap P1 todo retired with this commit.
The previous one-liner 'notify when done and nothing left to do'
left 'done' under-defined. Concrete failure mode (2026-05-12, this
session): test suite for an open milestone landed, I notified on
the user-specified stop trigger, but the milestone still had two
follow-up iters (DESIGN.md anchor + audit) plainly in scope. The
user's intent behind the trigger was 'wake me when there's
nothing else to do', not 'wake me at this checkpoint'.
The expanded section codes two states (done-state, problem-state),
explicitly names sub-goal completion as NOT a notify event, and
calibrates user-specified stop triggers: hit only if the trigger
leaves the queue truly empty.
Milestone-close audit found three drift items (architect) plus
two carry-on items; bench all-green.
Fixes (rt.tidy, boss-direct):
- 5th test parse_then_print_then_parse_is_idempotent_on_every_ailx_fixture
enforces Direction 2 of the Roundtrip Invariant directly. The
DESIGN.md enforcement list grows from four to five tests.
- docs/roadmap.md P1 'Round-trip completeness invariant' entry
retired with one-line journal mirror per roadmap convention.
- DESIGN.md wording sync: <16-hex> → <16-lowercase-hex> for the
Float-bits-hex spelling in the new section (matches §Data model).
Milestone closed clean; five workspace-wide tests anchor the
.ail.json ↔ .ailx bijection plus AST-variant coverage.
New top-level section '## Roundtrip Invariant' between Decision 11
and '## Mangling scheme'. States both directions of the .ail.json
↔ .ailx bijection, names Float-bits-hex encoding as the in-
invariant mechanism (not an exception), lists the four enforcement
tests by path, and explains why the property is top-level
(load-bearing on language identity, not on Decision 6's surface-
design rationale).
Decision 6 Constraint 2 rewritten as upward cross-reference to the
new section; the substantive content now lives at the anchor.
Direct boss edit (no planner/implement dispatch): spec Architecture
#1 fully specified the content, no design judgement deferred to
execution. The iter is a deterministic projection of the spec
onto DESIGN.md prose.
Three new reader-only tests pin the .ail.json / .ailx bijection
plus AST-variant coverage. All three passed first observation
across the current corpus — no roundtrip, schema-coverage, or
CLI-drift gaps surfaced.
- every_ailx_fixture_matches_its_json_counterpart (replaces the
3-pair handwritten exhibits): 57 paired .ailx fixtures pass.
- every_ast_variant_is_observed_in_the_fixture_corpus (new): 34/34
AST variants exercised across 136 fixtures; exhaustive matches
without _ wildcard so AST drift fails the build.
- cli_render_then_parse_preserves_canonical_bytes_on_every_fixture
(new): 136 fixtures round-trip through ail render → tempfile →
ail parse with BLAKE3 identity on canonical bytes.
No production code, no DESIGN.md changes (those follow in later
iterations). Tests are pure readers of the repo per spec
acceptance #7 — tempfile crate added as workspace dep for the CLI
roundtrip's intermediate file outside the repo.
Surfaced while scoping an empirical test of Decision 6 (.ailx as the
AI authoring projection). The cross-model test depends on a structural
.ail.json <-> .ailx bijection being established and prominently anchored
in DESIGN.md first; otherwise measured form-preference is contaminated
by expressive-power gaps rather than authoring ergonomics. P2 entry
carries the smoke-test evidence and full IONOS-endpoint addressing
notes so the test can be picked up without redoing the connection work.
Milestone-23 close audit. Architect clean on substance; one
pre-existing DESIGN.md grammar stub (line 1692, dangling 'The
original' from 2026-05-10 design-md-consolidation) caught and
fixed.
Bencher localised the compile_check.py regression to H2 (the 5 new
polymorphic prelude Def::Fns iter 23.5 added — each carries forall
+ class constraint + match/not body, all typechecked on every
workspace check). H1 (linearity workspace-visibility extension +
contains_rigid_var) is negligible at today's 2-module workspace.
The regression is the feature's measured cost. Ratified per audit
skill (--update-baseline + journal entry). 0/24 metrics regressed
post-update.
Milestone 23 (Eq/Ord prelude) is closed.
Five polymorphic prelude free fns (ne/lt/le/gt/ge) plus three E2E
fixtures: positive composition over Int/Bool/Str, user-ADT with
user-written Eq/Ord on IntBox, and Float-NoInstance with a
Float-aware diagnostic addendum cross-referencing DESIGN.md §"Float
semantics".
Two checker-side fixes were needed alongside the prelude additions,
both symmetric to the iter 23.4-prep visibility fix:
- linearity::check_module_with_visible — workspace-aware callee-mode
resolution so a Borrow-mode user fn forwarding into a prelude poly
fn (e.g. `at_most x y = not (gt x y)`) doesn't false-fire
consume-while-borrowed.
- mono::collect_mono_targets — distinguish rigid forall vars from
unbound metavars; rigid-bearing free-fn targets skip (they get
re-collected with concrete subst when the enclosing fn itself
monomorphises). Without this, a polymorphic body calling another
polymorphic free fn produced a spurious __Unit specialisation
whose body referenced compare at Unit.
Roadmap split: shipped Eq/Ord half checked, Show + print-rewire half
remains pending behind the heap-Str ABI prerequisite. DESIGN.md
§"Prelude classes" amended.
One pre-existing fixture (test_22b1_missing_method) renamed its
class method ne → tne to avoid collision with the new prelude `ne`.
Bench: check.py + cross_lang.py exit 0; compile_check.py exits 1
with one sub-ms check_ms.local_rec_capture at +26% (tolerance 25%) —
prelude-growth-related noise-band fluctuation, ratifiable per spec
§248-249 and journal Concerns.
Restructure ailang-check/src/mono.rs::monomorphise_workspace into a
single specialiser over every Type::Forall-quantified Def::Fn, covering
both class-method residuals AND polymorphic free-fn call sites in one
fixpoint pass. Remove the codegen-time specialiser (lower_polymorphic_call,
module_polymorphic_fns, mono_queue, mono_emitted, emit_specialised_fn,
plus the now-dead helpers apply_subst_to_term, descriptor_for_subst,
type_descriptor) entirely. Codegen sees only monomorphic Def::Fns after
this iter — no polymorphic call sites, no codegen-time queue.
Architecture changes:
- MonoTarget: struct → enum with ClassMethod / FreeFn variants; dedup
keys are guaranteed-disjoint via 'class'/'free' first component.
- collect_mono_targets: new FreeFnCall channel through synth (cleaner
than the plan's separate-walker proposal — one less data flow,
substitution tracking comes 'for free' via fresh metavars +
post-synth subst.apply). Plan Step 4.4 (polymorphic_free_fns env
field) consequently obsolete.
- synthesise_mono_fn_for_free_fn: new free-fn entry point; substitutes
rigid vars in BOTH the type AND the body (body substitution required
because free-fn bodies carry inner Lams whose param_tys reference
outer Forall vars — adapted from plan's 'body unchanged' sketch).
- mono_symbol_n: N-ary extension of mono_symbol; bit-stable for the
single-type-var case (hash-stability pin Task 1 fires zero times
through all eight refactor tasks).
- rewrite_class_method_calls → rewrite_mono_calls; interleaved-slot
collector preserves the positional-cursor invariant across both
channels.
- workspace_has_typeclasses → workspace_has_specialisable_targets
(principled correctness; old predicate happened to already be true
for every user workspace because the prelude is auto-injected).
Codegen cleanup:
- Two call sites of lower_polymorphic_call deleted (codegen/src/lib.rs
lines ~1939-1945, ~1965-1973).
- lower_polymorphic_call body, module_polymorphic_fns field +
population + Emitter wiring, mono_queue / mono_emitted, drain loop,
emit_specialised_fn — all removed.
- is_static_callee collapsed to module_user_fns-only.
- subst.rs apply_subst_to_term + descriptor_for_subst removed; synth.rs
type_descriptor removed (all dead post-removal).
- ail emit-ir command pipeline gains lift_letrecs + monomorphise_workspace
pre-passes (pre-iter-23.4 the codegen-time poly path was masking
this dependency — emit-ir is now consistent with build).
- Net codegen reduction: -285 lines lib.rs, -93 lines subst.rs.
Tests:
- mono_hash_stability.rs (new): regression pin for six primitive Eq/Ord
mono-symbol body hashes; stayed bit-stable through all eight refactor
tasks.
- mono_unification.rs (new): six tests covering variant-key disjointness,
free-fn target emission, free-fn synthesis with rigid substitution,
rewrite walker on free fns, identity for poly-free-fn-only workspaces,
end-to-end cmp_max_smoke runtime correctness.
- typeclass_22b3.rs: three test sites updated to MonoTarget::ClassMethod
enum form.
- 73 e2e + 18 typeclass + 81 codegen tests all green workspace-wide.
DESIGN.md §'Monomorphisation (post-typecheck, pre-codegen)' amended:
two-arm fixpoint described, disjoint-keyed dedup, cursor-aligned
walker, removed codegen-time path.
Bench check (all exit 0, 112 metrics stable): bench/check.py +
compile_check.py + cross_lang.py.
Plan parent: docs/plans/2026-05-11-iter-23.4.md (fab1685).
Spec parent: docs/specs/2026-05-11-23-eq-ord-prelude.md (841d65d).
Per-iter journal documents two adapted deviations from the plan
(synth-channel vs separate walker; body substitution; emit-ir fix);
no spec defects.
Plan for the corrected iter 23.4: restructure mono.rs into a single
specialiser for every Type::Forall-quantified Def::Fn (class methods
+ polymorphic free fns) in one fixpoint pass, and remove the codegen-
time specialiser (lower_polymorphic_call + module_polymorphic_fns +
mono_queue) entirely.
11 tasks, 4-step TDD template per task (write-failing-test →
verify-fail → write-impl → verify-pass), no per-task commit step
under the new disc.1 discipline.
Parent spec: docs/specs/2026-05-11-23-eq-ord-prelude.md (re-grounded
2026-05-11 against main HEAD 51da9fa, PASS, 10 load-bearing
assumptions verified).
Open commitments resolved:
- N-ary mono-symbol naming: spec default <name>__<t1>__<t2>__...
- Target-collector: extension of existing collect_mono_targets
(lockstep with collect_residuals_ordered)
- Original poly Def::Fn retention: kept parallel to Def::Class/
Def::Instance
Float-NoInstance diagnostic wording remains deferred to iter 23.5.
Two project-wide rules are now explicit across every skill:
1. Only the Boss commits. No skill agent (implementer,
brainstormer, planner, debugger, fieldtester, docwriter,
architect, bencher) runs `git commit`. Agents write their
artefacts to the working tree as unstaged changes; the Boss
inspects, decides commit shape, and commits.
2. main HEAD is sacrosanct. No actor runs `git reset` or
`git revert` on main. Bad work stays in the working tree
where it is still discardable via `git checkout -- <paths>`.
Implement loses the `iter/<iter_id>` branch mechanic entirely;
Phase 0 of the orchestrator-agent now does a clean-tree check
and refuses to start on a dirty tree. Per-task agent commits
are removed everywhere; reviewers operate against
`git diff HEAD` instead of `pre_task_sha..head_sha`.
Motivation: 2026-05-11 iter 23.4 stranded prep2/prep3 commits on
an iter-branch that never integrated to main, then a corrected
spec falsely claimed those commits had shipped. Branch-per-iter
+ manual-Boss-merge + iter-stacking made the strand structurally
possible. See docs/journals/2026-05-11-iter-disc.1.md for the
full per-task notes and motivation.
Brainstorm assumed all four 23.4-prep commits had shipped to main.
Branch verification (post-iter/23.4 deletion) showed only prep1
(linearity + check bare-name) is on main; prep2 + prep3 were
attempted on the stranded iter/23.4 branch and never landed.
Spec corrections:
- Goal section: prep-commit status block reflects actual main state.
- Architecture: drop §2 (prep2/prep3 rollback) — no rollback exists
on main; section count drops from four to three artefacts.
- Components table: prep2/prep3 row now reads 'abandoned 2026-05-11
with iter/23.4 deletion', not 'shipped, rolled back in 23.4'.
- Acceptance criterion 1: drop the 'prep2 + prep3 are rolled back'
clause.
- Load-bearing assumption 5: now states prep2/prep3 never reached
main (fixes the silent-assumption pattern this spec exists to
prevent — same failure mode the original Spec-23 had).
- Load-bearing assumption 6: cite the cherry-picked main SHAs
(0caaced, 923dd8c) alongside the stranded-branch originals
(8d39f13, aef4ab8).
- Known costs: drop the '23.4 rollback' line item.
The 23.4 mono-unification plan (ea0285b) assumed prep1 + prep2 +
prep3 were on main. They never were — they sit only on iter/23.4.
Spec component table was factually wrong. Plan Task 10 (revert prep
commits) was impossible on main. Discarding the plan; the spec is
next revised against the actual main state.
Plan-recon for iter 23.4 surfaced that poly_box_proj.ail.json does
not exist in examples/. The three load-bearing regression fixtures
are poly_id, poly_apply, and poly_rec_capture (the latter at
examples/poly_rec_capture.ail.json, driven by e2e.rs::poly_rec_capture_demo).
Three references in the spec corrected. Substantive intent (three
existing polymorphic fixtures regress unchanged under unified mono)
unchanged.
Note 3: agent output format leaked internal-thinking preamble before
the structured report block — Iron Law should forbid preamble.
Note 4: Boss-requested behaviour change for impending-BLOCK paths —
on miss, agent attempts to write missing GREEN test (test code only,
never src/) before falling to BLOCK; requires tool + Iron Law update.
Both notes are for the future skillsystem-postmortem entry; out of
gc.1 scope.
Brummel