feat(portfolio): K3 — portfolio learning loop (shared verdict store, parity row 5) [skip-docs]

A single VerdictStore threaded through run_portfolio: a verdict available when
project k composes survives into project k+1's fold (method-spec §5 cross-project
threading). The optional verdict_dir is the portfolio-level expert inbox, read
before each fold (role split §3 Step 7 — the portfolio never writes a run's own
verdict back; §1/§6 — no self-contamination, only expert/seed verdicts cross).
compose_run_context gains an optional passed-in store (None = fresh; every
existing caller composes exactly as before).

Load-bearing (tests/test_portfolio_learning_loadbearing.py), 2 detach proofs +
control + §4.2 idempotency:
- cross-project threading: project 1's bundle seed survives into project 2's
  prompt via the shared store; detach (compose ignores the passed-in store,
  always fresh) -> red.
- portfolio inbox fold: a verdict_dir marker reaches the project's fold; detach
  (drop the run_portfolio merge) -> red; control (no verdict_dir) -> marker absent.
- double-merge idempotency: a verdict merged before every project folds exactly
  once (first-write-wins on id).

437->442 green, golden byte-exact, full gate clean (ruff + format + mypy strict).
run_s10.py and runs/ byte-untouched. README synced (test count, portfolio block,
load-bearing list). K2 re-entrancy test stays green — the shared store threads
verdict fold lines only, never bundle context markers.

[skip-docs]: no invariant changed (CLAUDE.md untouched); the run_portfolio and
compose_run_context docstrings + README carry the doc need.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RiTwaKLesgcwXx2mDviqpt

README.md

@@ -13,7 +13,7 @@ human-in-the-loop, and the system learns from the verdicts.
 > **Status:** the D7 build (S5–S10) is complete, and the deterministic **ingest layer**
 > (CSV and SQL source types) has since been added in front of the loop. The deterministic
 > backbone, the agentic loop, the learning loop, and the ingest connectors are wired seam by
-> seam, each proven by load-bearing tests (437 tests, all running offline without an API
+> seam, each proven by load-bearing tests (442 tests, all running offline without an API
 > key). The programme's single budgeted **live model run has been executed and validated** —
 > its artifacts are committed under [`runs/s10/`](runs/s10/) (see below).
 
@@ -93,11 +93,14 @@ description, never from its code)
   budget stop included. The model client is injected, so the offline suite proves the
   same orchestration with a scripted client; only the CLI's default constructs the SDK
   client.
-- `portfolio.py` — the sequential multi-project run: `run_portfolio` drives N projects from
-  a schema-validated reference config, composing each project's context afresh (re-entrant,
-  fresh debate state per run) and collecting one result per project in config order. The
-  §8 budget meter is the one explicitly shared, portfolio-wide cap; the default failure
-  policy raises (a stack-local choice until D-D flips it to collect-and-continue).
+- `portfolio.py` — the sequential multi-project run and learning loop: `run_portfolio` drives
+  N projects from a schema-validated reference config, composing each project's context afresh
+  (re-entrant, fresh debate state per run) and collecting one result per project in config
+  order. Two things are deliberately shared portfolio-wide: the §8 budget meter (the cap) and a
+  single learning `VerdictStore` — a verdict available when project k composes survives into
+  project k+1's fold (cross-project threading, §5), and an optional `verdict_dir` is the
+  portfolio-level expert inbox the system reads before each fold. The default failure policy
+  raises (a stack-local choice until D-D flips it to collect-and-continue).
 - `run_s10.py` — the programme's ONE live run (cost discipline D6); run-path only.
 
 ### Load-bearing tests (§11)
@@ -110,7 +113,9 @@ proposal), `test_step5_refine_loadbearing.py` (the rejection reason verifiably r
 retry prompt, and the loop still stops at the cap), `test_step7_async_loop_loadbearing.py`
 (a verdict dropped after run A reaches run B's prompt through the file loop, with an
 empty-inbox control), `test_step8_promotion_loadbearing.py` (the gate refuses non-approved
-verdicts; the promoted signal stays out of the read-context), and
+verdicts; the promoted signal stays out of the read-context),
+`test_portfolio_learning_loadbearing.py` (a verdict available at project k survives into
+project k+1's fold via the shared store, with a marker-absent control), and
 `test_sdk_isolation.py` (local config cannot capture the checker).
 
 ## The ingest layer — CSV and SQL, in front of the loop
@@ -173,7 +178,7 @@ Python ≥3.10 · [`claude-agent-sdk`](https://pypi.org/project/claude-agent-sdk
 
 ```bash
 uv sync          # install dependencies
-uv run pytest    # 437 tests — run without any API key and without network
+uv run pytest    # 442 tests — run without any API key and without network
 uv run ruff check . && uv run ruff format --check .
 uv run mypy src  # strict
 ```