DESIGN_STRATEGIST.md §2.5. The strategist's two write actions.
propose_lead validates motivating_hypothesis exists in the graph,
validates expected_evidence_type is a real edge type, validates
source_id refers to a real source in the case — fast specific
errors so the strategist gets fixable feedback rather than a
generic crash. On success, calls graph.add_lead with proposed_by=
"strategist" and round_number=graph.current_strategist_round so
the round-completion code can collect this round's leads.
declare_investigation_complete sets graph.strategist_complete_requested
which the orchestrator inspects after each strategist run to decide
whether to break the loop. reason must come from a closed enum so
the audit log is consistent.
EvidenceGraph gains two transient run-context fields:
current_strategist_round — set by orchestrator at start of round
strategist_complete_requested — flipped by declare_complete
These are intentionally NOT persisted — they're per-run flags, not
graph state.
Both tools required to be in InvestigationStrategist.mandatory_record_
tools (added in S4) so the agent's forced-retry mechanism kicks in if
it returns without taking a documented decision.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
DESIGN_STRATEGIST.md §1. Foundation for the Phase 3 strategist loop.
Lead now carries four annotations that let the orchestrator measure
marginal yield per lead and dedupe strategist proposals:
- proposed_by (agent that proposed it: "strategist", "filesystem", …)
- motivating_hypothesis (hyp-id the lead is meant to corroborate/refute)
- expected_evidence_type (edge type the lead's worker should produce)
- round_number (0 = Phase 1 lead, ≥1 = strategist-proposed)
add_lead idempotently dedupes strategist proposals on
(motivating_hypothesis, expected_evidence_type, target_agent, source_id)
to prevent the "strategist loops on the same lead" failure mode.
New InvestigationRound dataclass records per-round provenance: before/
after hypothesis status snapshots, phenomena + edge count deltas, and
the strategist's decision_rationale. ``new_phenomena_count``,
``new_edges_count``, ``status_flips`` are derived properties that the
marginal_yield tool will use.
start_investigation_round / complete_investigation_round /
get_investigation_round / latest_round / leads_from_round complete the
lifecycle. complete is idempotent on already-closed rounds.
Lead.from_dict is forward-compat for state files written before this
commit. InvestigationRound persists as a top-level list in
graph_state.json (auto-save + load_state both wired).
EvidenceGraph also gains graph.budgets and graph.run_start_monotonic
fields that the budget_status view (S2) will read; orchestrator
populates them in S5.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First full-case run (runs/2026-05-20T20-15-04/) produced hypotheses
with log_odds +31 (8 direct_evidence + 15 supports). That's the
naive-Bayes independence assumption breaking down: 15 different
phenomena all "supporting" the same hypothesis from one source are
not 15 independent pieces of evidence, they're highly correlated.
DESIGN.md §4.5 last bullet flagged this as a "未实施旋钮" — this
commit implements it.
Rule: the k-th edge of a given (hyp_id, edge_type) contributes
log_lr_base / k instead of log_lr_base. Cumulative is harmonic
sum H_N, bounded by ~ ln N. Single-edge hypotheses unaffected
(k=1 → /1 → no change). Replaying the 2026-05-20 graph's 108
edges under the new rule pulls the top hypothesis from +31.0 →
+8.75; the smallest active hypothesis from +4.0 → +2.08.
Also adds rank + log_lr_base to confidence_log entries so the
math is auditable from the persisted graph.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First full-case run (runs/2026-05-20T20-15-04/) produced 83 GroundingError
rejections, almost all from a single failure mode: LLM cites a plausible-
looking inv-XXXXXXXX that doesn't exist, while the fact's value is in fact
present verbatim in one of its real tool outputs. The agent knew which
tool it read from, it just mis-typed the citation id.
Two-layer fix in evidence_graph.validate_fact_grounding:
Layer A (silent heal): when the cited inv-id misses, search the same
agent / task's invocations for one whose output contains the value
(strict or normalised substring). If exactly one matches, rewrite
fact.invocation_id in place and accept. Multi-match is NOT auto-
rescued — the candidate ids go back to the LLM so it picks deliberately.
Layer B (informative retry): GroundingError now appends the agent's
recent invocation ids and a brief tool-call summary, so the LLM has
the real ids in front of it for the next attempt rather than
fabricating again from memory.
Both layers preserve the design invariant: the fact's value must still
be present in a real tool output — nothing new can land grounded that
wasn't already verifiable. Cross-agent / cross-task isolation is also
preserved (rescue candidates filtered on agent + task_id).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Five interrelated cleanups:
1. Lead -> Phenomenon provenance
- Phenomenon.from_lead_id field on the dataclass
- BaseAgent.run(lead_id=...) writes self._current_lead_id
- _add_phenomenon auto-injects from agent state (LLM unaware)
- Orchestrator dispatch passes lead.id; Phase 1/2-auto/4/5 stay None
- Merge path preserves the first non-None lead_id on collision
2. Unified Phenomenon <-> Hypothesis link path
- HypothesisAgent only adds hypotheses, never links
- link_phenomenon_to_hypothesis tool + executor removed
- All links go through Orchestrator._judge_new_phenomena
- Phase 2 unconditionally judges after hypothesis generation
- Gap Analysis judges after each dispatch round
(Three previously-missing judge calls now in place.)
3. SSOT in agent subclasses
- Remove RoleTemplate dataclass, ROLE_TEMPLATES dict,
_instantiate_from_template method
- Each agent subclass owns name, role, and tool list
- agent_factory.py shrinks from 299 to 153 lines
- All 7 agents now route through _AGENT_CLASSES (filesystem,
registry, communication, network, timeline were previously dead
subclasses overridden by templates)
4. Configurable edge weights
- HYPOTHESIS_EDGE_WEIGHTS -> _DEFAULT_EDGE_WEIGHTS (private default)
- EvidenceGraph(edge_weights=...) override via config.yaml
- hypothesis_edge_weights section in config.yaml (commented example)
- main.py and regenerate_report.py read and pass through
5. regenerate_report.py auto-picks the latest run/*/graph_state.json
when no CLI arg is given (was a hardcoded date path)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
