Create a learning session. learner_id is required (P0 is single-learner).

Domain-grounding switches are stored per session, not globally. When domain_grounding_warn_user is true the returned notice must be shown to the user before the grounding stage starts.

Find existing sessions by learner and optionally topic.

Use this to recover a session id after a chat window is reopened.

Return session state, the latest goal, node count and the next lifecycle step.

Persist the learning goal and its constraints (lifecycle Stage 1).

Return the most recently saved learning goal for a session.

Apply a learner's requested learning mode (section 32).

Pass the learner's own words in request - e.g. "以项目实战为主", "我要准备考试", "只学核心内容，尽快学会". Recognised modes are project_based / exam_prep / core_only / balanced. Stored as session-level Learning Configuration + Policy Overrides; the program is never modified, and unrecognised requests are reported back.

Return the session's active learning mode, overrides and preferences.

Return a diagnostic blueprint.

Rejected by the State Guard until Domain Grounding is completed, unless the session was created with allow_skip_domain_grounding=true.

Record one diagnostic answer as a learner attempt.

Return the stored diagnostic summary plus every diagnostic attempt.

Persist the diagnostic summary and mark the diagnostic phase complete.

Return a DAG template. Node content is generated by the host agent's LLM.

Persist knowledge nodes. Each unit_tag must respect unit_concept_budget.

Persist knowledge edges. The DAG is validated first and rejected if invalid.

List knowledge nodes, optionally filtered by teaching unit.

List knowledge edges (prerequisite / support / extension / related).

Validate the stored DAG: cycles, dangling edges, self-loops, isolated nodes.

Return the full teaching context in one call to reduce round trips.

List the pedagogical strategies available to the policy engine.

List the concrete teaching actions the host agent may execute.

Report which implementation backs each pluggable seam (section 35).

Covers state estimation, assessment aggregation, policy, review scheduling, storage and artifact storage.

Evaluate the policy for the current state without persisting a decision.

Record the decision actually acted on, for later replay.

Read the pedagogical decision history for a session.

Return an assessment blueprint with the rubric dimensions to score.

Validate dimension scores and compute the weighted overall_score.

Does not persist anything. transfer and hint_dependency are excluded from the aggregate by design.

Record an active misconception in its authoritative table.

Mark a misconception as resolved and refresh the cached snapshot.

Return the server-estimated learner knowledge state.

Return past assessment results, including the raw answer for audit.

Return a transfer-probe blueprint (near / variation / far / integrated).

Return review items with current retrievability and due status.

Create a review item for a node if one does not exist yet.

Submit an FSRS rating (1=Again, 2=Hard, 3=Good, 4=Easy) and reschedule.

List due review items.

A non-empty result does not block new learning globally - blocking is a per-node Policy + State Guard decision.

Recompute retrievability for every review item of a learner.

Set the current teaching focus to a unit or node.

Dry-run the State Guard for an advance request without changing state.

Record a learner attempt and return its attempt_id for assessment.

Commit assessment evidence and update learner state server-side.

raw_answer and assessor_type are mandatory: the original learner response is stored for audit and never discarded. mastery_probability is computed by the runtime, not supplied by the caller.

Request the next unit.

Every node sharing the unit_tag must pass its own node-level guard; one failure rejects the whole request. There is no unit table.

Move the teaching focus back to an earlier node.

Record a transfer probe result; transfer_type is near/variation/far/integrated.

Store a learner reflection as an artifact.

Set the session status (active/paused/completed/abandoned).

Save the agent's domain grounding report and unlock diagnostics.

The full text is stored as an artifact of type agent_benchmark_report; structured claims go to benchmark_claims.

Save one structured knowledge claim with its source and confidence.

Return grounding report metadata, claims and sources for a session.

Check whether a claim is linked to a real evidence source.

Record conflicting sources instead of silently choosing one.

Save a learning artefact (HTML, Markdown, chart, code, report...).

Fetch an artefact by id.

List artefacts for a session, optionally filtered by type.

Return the static Obsidian vault specification.

Specification only - the runtime never reads or writes local vault files.

Return the static web-component specification.

Specification only - the runtime never generates HTML or reads front-end sources.

Export the full session bundle as JSON, optionally to a file path.

Generate the closing report, separating observed evidence from estimates.

Return the section 26.1 learning-outcome indicators.

Covers Immediate Performance, Delayed Retention, Transfer Performance, Time/Attempts to Target Evidence, Hint Dependency, Misconception Resolution, Confidence Calibration and Learning Gain.