feat(agents): hypothesis agent with prompt template + s-expr extraction

Aggiunge HypothesisAgent che invoca LLMClient con system/user template
parametrizzati sul genoma e sul MarketSummary, poi estrae la S-expression
(da fence markdown lisp/scheme/sexp o testo nudo), la parsa e la valida.
Restituisce HypothesisProposal con strategy=None + parse_error in caso di
output malformato, mantenendo sempre il CompletionResult per accounting.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/unit/test_hypothesis_agent.py

@@ -0,0 +1,93 @@
+from multi_swarm.agents.hypothesis import HypothesisAgent, MarketSummary
+from multi_swarm.genome.hypothesis import HypothesisAgentGenome, ModelTier
+from multi_swarm.llm.client import CompletionResult
+
+
+def make_summary() -> MarketSummary:
+    return MarketSummary(
+        symbol="BTC/USDT",
+        timeframe="1h",
+        n_bars=1000,
+        return_mean=0.0001,
+        return_std=0.01,
+        skew=0.1,
+        kurtosis=3.5,
+        volatility_regime="high",
+    )
+
+
+def test_hypothesis_agent_calls_llm_and_parses(mocker):  # type: ignore[no-untyped-def]
+    fake_llm = mocker.MagicMock()
+    fake_llm.complete.return_value = CompletionResult(
+        text="(strategy (when (gt (indicator rsi 14) 70.0) (entry-short)))",
+        input_tokens=200,
+        output_tokens=80,
+        tier=ModelTier.C,
+        model="qwen",
+    )
+    g = HypothesisAgentGenome(
+        system_prompt="Pensa come un fisico.",
+        feature_access=["close"],
+        temperature=0.9,
+        top_p=0.95,
+        model_tier=ModelTier.C,
+        lookback_window=200,
+        cognitive_style="physicist",
+    )
+    agent = HypothesisAgent(llm=fake_llm)
+    proposal = agent.propose(g, make_summary())
+    assert proposal.strategy is not None
+    assert proposal.raw_text.startswith("(strategy")
+    assert proposal.completion.input_tokens == 200
+    fake_llm.complete.assert_called_once()
+
+
+def test_hypothesis_agent_returns_none_on_parse_error(mocker):  # type: ignore[no-untyped-def]
+    fake_llm = mocker.MagicMock()
+    fake_llm.complete.return_value = CompletionResult(
+        text="this is not s-expression",
+        input_tokens=200,
+        output_tokens=80,
+        tier=ModelTier.C,
+        model="qwen",
+    )
+    g = HypothesisAgentGenome(
+        system_prompt="x",
+        feature_access=["close"],
+        temperature=0.9,
+        top_p=0.95,
+        model_tier=ModelTier.C,
+        lookback_window=200,
+        cognitive_style="physicist",
+    )
+    agent = HypothesisAgent(llm=fake_llm)
+    proposal = agent.propose(g, make_summary())
+    assert proposal.strategy is None
+    assert proposal.parse_error is not None
+
+
+def test_hypothesis_agent_extracts_sexp_from_markdown_fence(mocker):  # type: ignore[no-untyped-def]
+    fake_llm = mocker.MagicMock()
+    fake_llm.complete.return_value = CompletionResult(
+        text=(
+            "Ecco la strategia:\n```lisp\n"
+            "(strategy (when (lt (indicator rsi 14) 30.0) (entry-long)))\n"
+            "```\nFatta."
+        ),
+        input_tokens=200,
+        output_tokens=80,
+        tier=ModelTier.C,
+        model="qwen",
+    )
+    g = HypothesisAgentGenome(
+        system_prompt="x",
+        feature_access=["close"],
+        temperature=0.9,
+        top_p=0.95,
+        model_tier=ModelTier.C,
+        lookback_window=200,
+        cognitive_style="physicist",
+    )
+    agent = HypothesisAgent(llm=fake_llm)
+    proposal = agent.propose(g, make_summary())
+    assert proposal.strategy is not None