agentfootprint 6.43.0 → 6.45.0

package/dist/esm/adapters/observability/audit.d.ts

@@ -0,0 +1,254 @@
+/**
+ * auditExport — tamper-evident audit bundle (backlog #20, compliance
+ * wedge item 2; pairs with #19's `otelObservability` GenAI spans).
+ *
+ * Consumes the typed `agentfootprint.*` event stream and accumulates an
+ * append-only, HASH-CHAINED record log: every record carries the SHA-256
+ * of its own canonical serialization plus the hash of the previous
+ * record. Flipping a single byte anywhere in an exported bundle makes
+ * `verifyAuditBundle` name the exact record that broke — the
+ * record-keeping shape EU AI Act Art. 12 asks for (events the system
+ * logged, in order, demonstrably unmodified since capture).
+ *
+ * Pattern: Observability strategy (one purpose — chain accumulation)
+ *          + pure offline verifier.
+ * Role:    Outer ring (Hexagonal). Attach via
+ *          `agent.enable.observability({ strategy: auditExport() })`.
+ * Emits:   nothing — terminal sink.
+ *
+ * ## What lands in the chain
+ *
+ * One record per typed event, in dispatch order: decisions
+ * (`agent.route_decided`, `composition.route_decided` incl. decide()
+ * evidence), tool calls (`stream.tool_start/_end`), validation
+ * rejections (#9), permission verdicts and halts, credential lifecycle,
+ * costs, errors, skill/memory/context activity. Each new `meta.runId`
+ * is anchored by a GENESIS record (`audit.genesis`) carrying the runId,
+ * the agent identity, and library versions — runs chain back-to-back in
+ * one log, so silently DROPPING a whole run breaks the chain too.
+ *
+ * High-volume content deltas (`stream.token`, `stream.thinking_delta`)
+ * are excluded by default (`includeTokenEvents: true` to include).
+ *
+ * ## Record / bundle schema
+ *
+ * ```
+ * AuditRecord  = { seq, timestamp, eventType, payload, meta, prevHash, hash }
+ *   hash       = SHA-256 hex over canonicalJson(record minus `hash`)
+ *   prevHash   = previous record's `hash` (ZERO_HASH at chain start)
+ * AuditBundle  = { header, records, finalHash }
+ *   header     = { format, hashAlgorithm, canonicalization, chainHead,
+ *                  firstSeq, recordCount, exportedAt, library }
+ * ```
+ *
+ * Canonicalization is `afp-cjson/1` (see `lib/canonicalJson.ts` — those
+ * rules ARE the contract; the header names them so independent
+ * verifiers can re-implement byte-exactly).
+ *
+ * ## Persistence + long runs
+ *
+ * Persistence is the CONSUMER's job — the bundle is plain JSON
+ * (`JSON.stringify(strategy.bundle())`, store anywhere). For long runs,
+ * `drain()` returns the records accumulated since the last drain while
+ * keeping the chain intact ACROSS drains: each segment's
+ * `header.chainHead` equals the previous segment's `finalHash`, so
+ * `verifyAuditBundle([seg1, seg2, ...])` re-verifies the concatenation
+ * end-to-end.
+ *
+ * ## PII discipline (mirrors #19's otelObservability)
+ *
+ * Payloads enter records through a bounding layer — by default
+ * (`payloadMode: 'bounded'`) record payloads NEVER carry raw runtime
+ * values that can echo PII:
+ *
+ *   - tool args             → `'[keys: …]'` (top-level key NAMES only)
+ *   - tool results          → `'[type: …]'` (typeof only)
+ *   - userPrompt / LLM content / thinking blocks / history
+ *                           → `'[N chars]'` / `'[N messages]'` markers
+ *   - content PREVIEWS (`contentSummary` on context/memory events,
+ *     `rawContent`, `resultSummary`, `droppedSummaries`) → markers
+ *     (for short content a preview IS the content; `contentHash`
+ *     stays — it links identical content without echoing it)
+ *   - error MESSAGE strings (`error`, `errorMessage`, `lastError`,
+ *     `rawOutput`)          → `'[N chars]'` (messages can echo values)
+ *   - free-form Records (`questionPayload`, `resumeInput`, risk/eval
+ *     `evidence`, memory `scoreEvidence`) → `'[keys: …]'`
+ *
+ * Everything else is embedded as the registry payload (sanitized:
+ * strings capped at 256 chars, lists at 32 items, cycles broken) —
+ * those payloads are bounded by construction: identifiers, counts,
+ * enums, decide() evidence (engine-bounded + redaction-aware),
+ * validation issues (paths/TYPES per #9), credential events (no
+ * secrets by contract).
+ *
+ * `payloadMode: 'verbatim'` embeds full payloads (still
+ * JSON-sanitized). For Art. 12 completeness on an access-controlled
+ * store that is often the point — but the bundle then carries prompts,
+ * tool args/results and model output. Treat it as PII-bearing, and
+ * remember the Agent sets NO footprintjs RedactionPolicy by default
+ * (policies you do set redact the emit channel UPSTREAM of this
+ * strategy, so redacted events arrive here already redacted).
+ *
+ * ## Tamper-EVIDENT, not tamper-PROOF (honest threat model)
+ *
+ * The chain proves INTERNAL consistency: any partial modification —
+ * edit, insert, delete, reorder, drop-a-run — is detected and named.
+ * It does NOT prove provenance: an adversary holding the only copy can
+ * recompute every hash from the mutation onward and present a
+ * self-consistent forgery. For non-repudiation, anchor `finalHash`
+ * externally as part of your retention process (write-once/WORM store,
+ * signed log, RFC 3161 timestamping, or simply a second party) — then
+ * a whole-suffix recomputation no longer matches the anchor.
+ *
+ * ## Runtime requirements
+ *
+ * Hashing uses `node:crypto` (`createHash('sha256')`) — zero new
+ * dependencies, imported lazily at first use (same gating as the
+ * optional vendor SDKs in this folder, so merely importing this module
+ * stays browser-safe). `auditExport` and `verifyAuditBundle` therefore
+ * run anywhere `node:crypto` exists: Node ≥ 20, Bun, Deno,
+ * edge runtimes with Node compat (e.g. Cloudflare `nodejs_compat`).
+ * In a browser there is no SYNC SHA-256 (WebCrypto is async-only), so
+ * both throw a descriptive error — verify server-side, or re-implement
+ * verification from the documented contract (it is pure: recompute
+ * SHA-256 over `afp-cjson/1` canonicalization and walk the chain).
+ *
+ * @example Capture → export → verify
+ * ```ts
+ * import { auditExport, verifyAuditBundle } from 'agentfootprint/observability-providers';
+ *
+ * const audit = auditExport({ agent: 'loan-officer' });
+ * const stop = agent.enable.observability({ strategy: audit });
+ * await agent.run({ message: 'assess application A-17' });
+ * stop();
+ *
+ * const bundle = audit.bundle();            // JSON-serializable
+ * await fs.writeFile('run.audit.json', JSON.stringify(bundle));
+ *
+ * const check = verifyAuditBundle(bundle);  // offline — no agent needed
+ * // check.valid === true; tamper with one byte → { valid: false, brokenAt: <seq> }
+ * ```
+ */
+import { CANONICAL_JSON_VERSION } from '../../lib/canonicalJson.js';
+import type { ObservabilityStrategy } from '../../strategies/types.js';
+/** SHA-256 of "nothing" — the `prevHash` of the first record in a
+ *  chain and the `chainHead` of a chain's first segment. */
+export declare const AUDIT_ZERO_HASH: string;
+/** `eventType` of the per-run genesis record. Deliberately OUTSIDE the
+ *  `agentfootprint.*` registry namespace — it is a chain-level record,
+ *  not a dispatched event (#20 ships zero new typed events). */
+export declare const AUDIT_GENESIS_EVENT_TYPE = "audit.genesis";
+/** Format identifier carried on every bundle header. */
+export declare const AUDIT_BUNDLE_FORMAT = "agentfootprint.audit/1";
+/**
+ * One link of the hash chain.
+ *
+ * `hash` = SHA-256 hex over `canonicalJson` of the record WITHOUT the
+ * `hash` field (i.e. `{ seq, timestamp, eventType, payload, meta,
+ * prevHash }` — canonical key order makes field order irrelevant).
+ * Because the preimage is "everything but `hash`", ADDING a field to a
+ * record is detected exactly like mutating one.
+ */
+export interface AuditRecord {
+    /** 0-based position in the chain (monotonic across drains). */
+    readonly seq: number;
+    /** Wall-clock ms of the source event (`meta.wallClockMs`). */
+    readonly timestamp: number;
+    /** Registry event name verbatim, or {@link AUDIT_GENESIS_EVENT_TYPE}. */
+    readonly eventType: string;
+    /** Bounded / sanitized event payload (see module PII docs). */
+    readonly payload: unknown;
+    /** Sanitized event meta (runId, runtimeStageId, paths, indices). */
+    readonly meta: {
+        readonly runId: string;
+    } & Readonly<Record<string, unknown>>;
+    /** `hash` of the previous record ({@link AUDIT_ZERO_HASH} at chain start). */
+    readonly prevHash: string;
+    /** SHA-256 hex of this record's canonical preimage. */
+    readonly hash: string;
+}
+export interface AuditBundleHeader {
+    readonly format: typeof AUDIT_BUNDLE_FORMAT;
+    readonly hashAlgorithm: 'sha-256';
+    readonly canonicalization: typeof CANONICAL_JSON_VERSION;
+    /** `prevHash` of `records[0]` — {@link AUDIT_ZERO_HASH} for the first
+     *  segment, the previous segment's `finalHash` after a `drain()`. */
+    readonly chainHead: string;
+    /** `seq` of `records[0]` (continues across drains). */
+    readonly firstSeq: number;
+    readonly recordCount: number;
+    /** Wall-clock ms when `bundle()` / `drain()` produced this export. */
+    readonly exportedAt: number;
+    readonly library: {
+        readonly name: 'agentfootprint';
+        readonly version: string;
+    };
+}
+/** JSON-serializable export of the chain (or one drained segment). */
+export interface AuditBundle {
+    readonly header: AuditBundleHeader;
+    readonly records: readonly AuditRecord[];
+    /** `hash` of the last record (= `chainHead` when `records` is empty).
+     *  The next drained segment's `chainHead` equals this value. */
+    readonly finalHash: string;
+}
+export interface AuditVerifyResult {
+    readonly valid: boolean;
+    /** Records whose hashes were recomputed and matched. */
+    readonly recordsChecked: number;
+    /** `seq` of the first record that fails (or the expected seq at the
+     *  failure point, when the stored seq itself was tampered). */
+    readonly brokenAt?: number;
+    /** Human-readable cause — names the failed check. */
+    readonly reason?: string;
+}
+export interface AuditExportOptions {
+    /** Agent identity recorded in every run's genesis record (service /
+     *  agent name as your compliance review knows it). */
+    readonly agent?: string;
+    /**
+     * `'bounded'` (default) — payloads pass the PII bounding layer (see
+     * module docs). `'verbatim'` — full payloads, JSON-sanitized only.
+     *
+     * @remarks Verbatim bundles carry prompts, tool args/results and
+     * model output. Treat the store as PII-bearing; the Agent applies NO
+     * RedactionPolicy by default.
+     */
+    readonly payloadMode?: 'bounded' | 'verbatim';
+    /** Include `stream.token` / `stream.thinking_delta` events (high
+     *  volume; content still bounded under `payloadMode: 'bounded'`).
+     *  Default `false`. */
+    readonly includeTokenEvents?: boolean;
+    /** Extra version pins for the genesis record (your app, model
+     *  config revision, policy bundle hash, …). */
+    readonly versions?: Readonly<Record<string, string>>;
+}
+/** The strategy returned by {@link auditExport}. */
+export interface AuditExportStrategy extends ObservabilityStrategy {
+    /** Snapshot the retained records WITHOUT draining. Safe mid-run. */
+    bundle(): AuditBundle;
+    /** Return the records accumulated since the last drain and clear
+     *  them from memory. Chain state persists — consecutive drained
+     *  segments re-verify end-to-end via `verifyAuditBundle([...])`. */
+    drain(): AuditBundle;
+    /** Records currently retained (since last drain). */
+    recordCount(): number;
+}
+export declare function auditExport(opts?: AuditExportOptions): AuditExportStrategy;
+/**
+ * Recompute the hash chain of a bundle (or of consecutive drained
+ * segments, in order) and report the exact record where integrity
+ * breaks. Pure function over JSON data — runs offline, long after the
+ * run, with no agent and no strategy instance.
+ *
+ * Checks, in order, per segment:
+ *   1. header format / algorithm / canonicalization are supported
+ *   2. `recordCount` matches `records.length`
+ *   3. segment continuity (`chainHead`/`firstSeq` extend the previous
+ *      segment's `finalHash`/seq range)
+ *   4. per record: `seq` is contiguous, `prevHash` links the previous
+ *      record, and SHA-256 over the canonical preimage (the record
+ *      minus `hash` — so ADDED fields are caught too) matches `hash`
+ *   5. `finalHash` equals the last record's hash
+ */
+export declare function verifyAuditBundle(input: AuditBundle | readonly AuditBundle[]): AuditVerifyResult;

package/dist/esm/adapters/observability/cloudwatch.d.ts

@@ -0,0 +1,96 @@
+/**
+ * cloudwatchObservability — Generic AWS CloudWatch Logs adapter.
+ *
+ * Ships every `AgentfootprintEvent` to a CloudWatch Logs stream. Use
+ * when you want agent telemetry alongside the rest of your AWS
+ * observability stack — CloudWatch Insights queries, alarms,
+ * cross-service correlation. Same SDK as `agentcoreObservability`
+ * but **without** the AgentCore-specific defaults (log-stream
+ * convention, format opinions). Use this when:
+ *
+ *   1. You're shipping to CloudWatch but NOT running inside Bedrock
+ *      AgentCore (most common case).
+ *   2. You want full control over log group / stream / format and
+ *      don't need AgentCore's hosted-agent telemetry conventions.
+ *
+ * Subpath:  `agentfootprint/observability-providers`
+ * Peer dep: `@aws-sdk/client-cloudwatch-logs` (OPTIONAL — installed
+ *           only when this adapter is used; declared via
+ *           `peerDependenciesMeta.{name}.optional = true`).
+ *
+ * This module also exports the underlying base function used by
+ * `agentcoreObservability` — keeps the per-event hot path in one
+ * place so improvements (batching, retry, backpressure) flow to
+ * every CloudWatch-shaped adapter automatically.
+ *
+ * @example
+ * ```ts
+ * import { cloudwatchObservability } from 'agentfootprint/observability-providers';
+ * import { microtaskBatchDriver } from 'footprintjs/detach';
+ *
+ * agent.enable.observability({
+ *   strategy: cloudwatchObservability({
+ *     region: 'us-east-1',
+ *     logGroupName: '/myapp/agent-prod',
+ *     logStreamName: `${process.env.HOSTNAME}/${Date.now()}`,
+ *   }),
+ *   detach: { driver: microtaskBatchDriver, mode: 'forget' },
+ * });
+ * ```
+ */
+import type { ObservabilityStrategy } from '../../strategies/types.js';
+export interface CloudwatchObservabilityOptions {
+    /** AWS region. Falls back to AWS_REGION / AWS_DEFAULT_REGION env. */
+    readonly region?: string;
+    /** CloudWatch Logs log group. **Required.** Must exist or your IAM
+     *  role must allow `logs:CreateLogGroup`. */
+    readonly logGroupName: string;
+    /** CloudWatch Logs log stream within the group. Conventionally
+     *  `<host>/<startTime>` so multi-instance deployments don't
+     *  collide. Created on first put if it doesn't exist (or your
+     *  role must allow `logs:CreateLogStream`). Defaults to
+     *  `agentfootprint`. */
+    readonly logStreamName?: string;
+    /** Max events buffered before forced flush. Default 100. */
+    readonly maxBatchEvents?: number;
+    /** Max payload bytes (UTF-8) buffered before forced flush. Default
+     *  10240 (10 KB). CloudWatch hard caps at 1 MB / batch but we keep
+     *  the default low so latency stays bounded. */
+    readonly maxBatchBytes?: number;
+    /** Forced-flush interval when traffic is sparse. Default 1000ms.
+     *  `0` disables time-based flush — only size triggers fire. */
+    readonly flushIntervalMs?: number;
+    /** Test injection — bypasses SDK lazy-require entirely. When set,
+     *  `region` / IAM are ignored. */
+    readonly _client?: CloudWatchLikeClient;
+}
+export interface CloudWatchLikeClient {
+    putLogEvents(input: {
+        logGroupName: string;
+        logStreamName: string;
+        logEvents: ReadonlyArray<{
+            timestamp: number;
+            message: string;
+        }>;
+    }): Promise<unknown>;
+}
+/**
+ * Internal: shared CloudWatch Logs base used by every adapter that
+ * ships to CWL. `cloudwatchObservability` is the public generic
+ * factory; `agentcoreObservability` calls this with AgentCore-flavored
+ * defaults.
+ *
+ * Exported for adapter authors only — consumers should call
+ * `cloudwatchObservability` or `agentcoreObservability` directly.
+ *
+ * @internal
+ */
+export declare function _buildCloudWatchObservability(opts: CloudwatchObservabilityOptions, strategyName: string): ObservabilityStrategy;
+/**
+ * Generic CloudWatch Logs observability adapter. See
+ * `CloudwatchObservabilityOptions` for the per-option contract.
+ *
+ * For AgentCore-specific conventions, use `agentcoreObservability`
+ * which thin-wraps this with AgentCore-flavored defaults.
+ */
+export declare function cloudwatchObservability(opts: CloudwatchObservabilityOptions): ObservabilityStrategy;

package/dist/esm/adapters/observability/otel.d.ts

@@ -0,0 +1,237 @@
+/**
+ * otelObservability — OpenTelemetry distributed-tracing adapter.
+ *
+ * Ships every agentfootprint event as OpenTelemetry spans + span events
+ * via a consumer-supplied OTel API, following the OpenTelemetry **GenAI
+ * semantic conventions** (`gen_ai.*` attribute namespace) plus
+ * agentfootprint-specific explainability attributes (`agentfootprint.*`).
+ * Same hierarchical mapping as the X-Ray adapter, but the destination is
+ * whichever OTel-compat backend the consumer's SDK exports to:
+ *
+ *   - **Honeycomb** (OTLP/HTTP)
+ *   - **Grafana Cloud / Tempo / Mimir** (OTLP)
+ *   - **AWS Distro for OTel** → AWS X-Ray (alternative to xrayObservability)
+ *   - **Datadog APM** (OTLP endpoint)
+ *   - **Splunk Observability Cloud** (OTLP)
+ *   - **New Relic** (OTLP endpoint)
+ *   - **Lightstep / ServiceNow Cloud Observability** (OTLP)
+ *   - any custom OTel collector / processor pipeline
+ *
+ * Subpath:  `agentfootprint/observability-providers`
+ * Peer dep: `@opentelemetry/api` (OPTIONAL — installed only when
+ *           this adapter is used. The consumer ALSO installs the
+ *           OTel SDK + exporter of their choice — that's the BYO
+ *           contract that makes this adapter backend-agnostic.).
+ *
+ * **Why BYO SDK:** OTel's SDK is heavyweight and exporter-specific
+ * (each backend has its own exporter package). Forcing a particular
+ * exporter would defeat the "OTel is portable" guarantee. Consumers
+ * configure the SDK + exporter once at app startup; we just speak
+ * the typed OTel API.
+ *
+ * ## Event → span/attribute mapping
+ *
+ *   agent.turn_start          ↦  start root span (one trace per turn) —
+ *                                `gen_ai.operation.name: 'invoke_agent'`
+ *   agent.turn_end            ↦  end root span (+ turn-total `gen_ai.usage.*`)
+ *   agent.iteration_start     ↦  start child span under root
+ *   agent.iteration_end       ↦  end iteration span
+ *   stream.llm_start          ↦  start child span (inference) — `gen_ai.*`
+ *                                request attrs (`chat` operation)
+ *   stream.llm_end            ↦  end llm span (+ `gen_ai.usage.*`,
+ *                                `gen_ai.response.*`)
+ *   stream.tool_start         ↦  start child span — `execute_tool` operation,
+ *                                `gen_ai.tool.name` / `gen_ai.tool.call.id`
+ *   stream.tool_end           ↦  end tool span (ERROR status + `error.type`
+ *                                if errored). Correlated by toolCallId so
+ *                                PARALLEL tool calls close the right span.
+ *   cost.tick                 ↦  setAttribute on topmost active span
+ *   error.fatal               ↦  ERROR status on root + defensive unwind
+ *   context.evaluated         ↦  N span events `agentfootprint.skill.routing`
+ *                                — SYNTHESIZED name (one per routing entry),
+ *                                not a registry-verbatim forward; all other
+ *                                span events use the registry name verbatim
+ *
+ * ## Decisions = SPAN EVENTS, not attributes (design decision)
+ *
+ * Explainability signals (route decisions, skill routing, validation
+ * rejections, permission checks, credential lifecycle) are emitted as
+ * **span events** on the currently-active span rather than attributes:
+ *
+ *   1. MULTIPLICITY — an iteration span can carry several decisions
+ *      (route + N skill routings + M permission checks). Attributes are
+ *      last-write-wins and would clobber; span events accumulate.
+ *   2. ORDERING — span events carry their own timestamps, preserving the
+ *      decision sequence inside one span. Compliance review (EU AI Act
+ *      Art. 12 record-keeping) needs the order decisions were made.
+ *   3. ROUND-TRIP — OTLP backends (and agentThinkingUI's `fromOTLP`
+ *      ingestion) surface span events as first-class timeline entries.
+ *
+ * When the consumer-injected tracer's spans don't implement `addEvent`
+ * (minimal test doubles), the adapter falls back to flattened
+ * `${eventName}.${key}` attributes — degraded (last-write-wins) but
+ * never silently dropped.
+ *
+ * ## PII discipline
+ *
+ * Mirrors the #9 validation contract: attribute values NEVER echo
+ * runtime VALUES that can carry PII —
+ *   - tool args  → top-level key NAMES only (`agentfootprint.tool.args.keys`)
+ *   - tool results → `typeof` only (`agentfootprint.tool.result.type`)
+ *   - validation issues → path / expected / got TYPES (bounded upstream)
+ *   - decide() evidence → rule labels, operators, thresholds (developer
+ *     constants) and the engine's redaction-aware value SUMMARIES
+ *   - userPrompt / llm content / thinking → never emitted
+ *   - error.fatal → stage + scope only (error MESSAGES can echo values)
+ *   - credential events carry no secrets by construction (registry contract)
+ *
+ * @example Basic — Honeycomb via OTLP
+ * ```ts
+ * import { NodeTracerProvider } from '@opentelemetry/sdk-trace-node';
+ * import { OTLPTraceExporter } from '@opentelemetry/exporter-trace-otlp-http';
+ * import { BatchSpanProcessor } from '@opentelemetry/sdk-trace-base';
+ * import { otelObservability } from 'agentfootprint/observability-providers';
+ *
+ * // Set up OTel ONCE at app startup.
+ * const provider = new NodeTracerProvider();
+ * provider.addSpanProcessor(new BatchSpanProcessor(new OTLPTraceExporter({
+ *   url: 'https://api.honeycomb.io/v1/traces',
+ *   headers: { 'x-honeycomb-team': process.env.HONEYCOMB_KEY },
+ * })));
+ * provider.register();
+ *
+ * const otel = otelObservability({
+ *   serviceName: 'my-agent',
+ *   // genAiSpanNames: true,  // opt-in spec span names ('chat gpt-4', …)
+ * });
+ * agent.enable.observability({ strategy: otel });
+ * // Optional — operator-level decide()/select() evidence as span events:
+ * // Agent.create({...}).recorder(otel.decisionEvidenceRecorder())
+ * ```
+ *
+ * @example Test injection
+ * ```ts
+ * otelObservability({
+ *   serviceName: 'test',
+ *   tracer: mockTracer, // anything matching the OTel Tracer interface
+ * });
+ * ```
+ */
+import type { FlowDecisionEvent, FlowSelectedEvent } from 'footprintjs';
+import type { ObservabilityStrategy } from '../../strategies/types.js';
+export interface OtelObservabilityOptions {
+    /** Service name on every emitted span. Surfaces in your OTel
+     *  backend's service map. Required. */
+    readonly serviceName: string;
+    /** OTel Tracer to use. Defaults to
+     *  `trace.getTracer('agentfootprint', AGENTFOOTPRINT_VERSION)`
+     *  (where `trace` is the lazy-imported `@opentelemetry/api`). */
+    readonly tracer?: OtelTracerLike;
+    /** 0..1 — sample rate for turn-level spans. Default `1.0`.
+     *  Sampling decisions are normally an OTel SDK concern (via
+     *  `Sampler`); this option is a per-strategy override for cases
+     *  where the consumer wants agentfootprint to drop spans BEFORE
+     *  they reach the SDK (e.g., aggressive cost control). */
+    readonly sampleRate?: number;
+    /**
+     * Opt-in OTel GenAI semconv SPAN NAMES (default `false`):
+     *
+     *   root  → `invoke_agent {serviceName}`  (was `{serviceName}`)
+     *   llm   → `chat {model}`                (was `llm`)
+     *   tool  → `execute_tool {toolName}`     (was `tool:{toolName}`)
+     *
+     * Off by default because existing consumers' dashboards / alerts key
+     * on the legacy span names — renames would break them. All `gen_ai.*`
+     * ATTRIBUTES are emitted regardless of this flag (purely additive),
+     * so semconv-aware backends can already group by
+     * `gen_ai.operation.name` with the flag off.
+     */
+    readonly genAiSpanNames?: boolean;
+    /**
+     * Explainability span events (default `true`): route decisions, skill
+     * routing provenance, validation rejections, permission decisions,
+     * credential lifecycle. Set `false` to emit only the span tree +
+     * `gen_ai.*` attributes (e.g., aggressive per-byte vendor billing).
+     */
+    readonly explainability?: boolean;
+}
+/** Attribute value union we emit. Matches OTel's `AttributeValue`
+ *  subset: primitives + homogeneous string arrays
+ *  (`gen_ai.response.finish_reasons`, issue lists, …). */
+export type OtelAttributeValue = string | number | boolean | readonly string[];
+/** Subset of `@opentelemetry/api`'s `Tracer` we depend on. */
+export interface OtelTracerLike {
+    startSpan(name: string, options?: OtelSpanOptions, context?: unknown): OtelSpanLike;
+}
+/** Subset of `@opentelemetry/api`'s `SpanOptions`. */
+export interface OtelSpanOptions {
+    attributes?: Record<string, OtelAttributeValue>;
+    startTime?: number;
+    kind?: number;
+}
+/** Subset of `@opentelemetry/api`'s `Span` we depend on. */
+export interface OtelSpanLike {
+    setAttribute(key: string, value: OtelAttributeValue): unknown;
+    setStatus(status: {
+        code: number;
+        message?: string;
+    }): unknown;
+    end(endTime?: number): void;
+    spanContext(): {
+        traceId: string;
+        spanId: string;
+        traceFlags: number;
+    };
+    /** OTel `Span.addEvent` — optional in the duck-typed surface so
+     *  minimal test doubles still satisfy the interface. Explainability
+     *  signals degrade to flattened attributes when absent. */
+    addEvent?(name: string, attributes?: Record<string, OtelAttributeValue>): unknown;
+}
+/**
+ * footprintjs CombinedRecorder (FlowRecorder channel) that forwards
+ * decide()/select() operator-level evidence into the paired
+ * otelObservability strategy as span events. Attach via
+ * `Agent.create({...}).recorder(...)` or
+ * `executor.attachCombinedRecorder(...)`.
+ */
+export interface OtelDecisionEvidenceRecorder {
+    readonly id: string;
+    onDecision(event: FlowDecisionEvent): void;
+    onSelected(event: FlowSelectedEvent): void;
+}
+/** Return type of {@link otelObservability} — the base
+ *  ObservabilityStrategy plus the decide()/select() evidence bridge. */
+export interface OtelObservabilityStrategy extends ObservabilityStrategy {
+    /**
+     * Build the decide()/select() evidence bridge for this strategy.
+     *
+     * Operator-level decision evidence (which rule fired, the
+     * `key op threshold → actual` conditions) travels on footprintjs's
+     * FlowRecorder channel (`onDecision` / `onSelected`) — it never
+     * reaches the typed event dispatcher, so the strategy alone can't
+     * see it. This recorder is the bridge (same pattern as the #5
+     * causal-evidence bridge in `memory/causal/evidenceRecorder.ts`).
+     *
+     * Decisions WITHOUT structured evidence are skipped — they already
+     * arrive via the `agent.route_decided` / `composition.route_decided`
+     * typed events, so forwarding them here would double-report.
+     *
+     * @remarks PII: attaching this recorder EXPORTS bounded actual scope
+     * values to your OTel collector — each condition renders as
+     * `key op threshold → actualSummary (bool)`, where `actualSummary` is
+     * the engine's redaction-aware ≤80-char value summary (e.g.
+     * `creditScore gt 700 → 750 (true)`). Keys covered by a footprintjs
+     * `RedactionPolicy` render `[REDACTED]`; everything else leaves the
+     * process. For compliance record-keeping that disclosure is usually
+     * the point — but treat the collector as PII-bearing, or redact the
+     * relevant keys upstream, before attaching.
+     *
+     * @remarks Attach ONCE per executor. Every instance carries the
+     * well-known id `'otel-decision-evidence'`, so re-attaching is
+     * idempotent-by-ID (the replacement prevents double-reported span
+     * events); instances from the same strategy share its turn state by
+     * design.
+     */
+    decisionEvidenceRecorder(): OtelDecisionEvidenceRecorder;
+}
+export declare function otelObservability(opts: OtelObservabilityOptions): OtelObservabilityStrategy;

package/dist/esm/adapters/observability/xray.d.ts

@@ -0,0 +1,88 @@
+/**
+ * xrayObservability — AWS X-Ray distributed-tracing adapter.
+ *
+ * Maps agentfootprint's event taxonomy onto AWS X-Ray segment trees:
+ *
+ *     agent.turn_start          ↦  root segment (one trace per turn)
+ *     agent.turn_end            ↦  close root segment + flush
+ *     agent.iteration_start     ↦  push subsegment under root
+ *     agent.iteration_end       ↦  close iteration subsegment
+ *     stream.llm_start          ↦  push leaf subsegment (model call)
+ *     stream.llm_end            ↦  close llm subsegment
+ *     stream.tool_start         ↦  push leaf subsegment (tool call)
+ *     stream.tool_end           ↦  close tool subsegment (correlated
+ *                                  by toolCallId — parallel-safe)
+ *     error.fatal               ↦  fault on root + close the whole
+ *                                  tree (turn_end never arrives)
+ *
+ * Events are anchored on `meta.runId` (the dispatcher envelope),
+ * with a `payload.runId` fallback for hand-built events.
+ *
+ * The result in the X-Ray Trace Map: a hierarchical timeline of every
+ * agent run — turn → iteration → llm-call/tool-call — queryable in
+ * X-Ray Insights, joinable with the rest of your AWS distributed
+ * trace via `AWSTraceHeader` propagation (consumer's responsibility
+ * to wire upstream/downstream IDs).
+ *
+ * Subpath:  `agentfootprint/observability-providers`
+ * Peer dep: `@aws-sdk/client-xray` (OPTIONAL — installed only when
+ *           this adapter is used).
+ *
+ * Sampling:
+ *   By default every turn produces one trace. Pass `sampleRate: 0.1`
+ *   to sample 10% of turns — sampling decisions are made at
+ *   `turn_start` and persist for the whole turn (so partial traces
+ *   never reach X-Ray).
+ *
+ * @example
+ * ```ts
+ * import { xrayObservability } from 'agentfootprint/observability-providers';
+ * import { microtaskBatchDriver } from 'footprintjs/detach';
+ *
+ * agent.enable.observability({
+ *   strategy: xrayObservability({
+ *     region: 'us-east-1',
+ *     serviceName: 'my-agent',
+ *     sampleRate: 0.1,                    // 10% sampling
+ *   }),
+ *   detach: { driver: microtaskBatchDriver, mode: 'forget' },
+ * });
+ * ```
+ *
+ * @example Test injection
+ * ```ts
+ * xrayObservability({
+ *   serviceName: 'test',
+ *   _client: {
+ *     putTraceSegments: async (input) => { capturedDocs.push(input); },
+ *   },
+ * });
+ * ```
+ */
+import type { ObservabilityStrategy } from '../../strategies/types.js';
+export interface XrayObservabilityOptions {
+    /** AWS region. Falls back to AWS_REGION / AWS_DEFAULT_REGION env. */
+    readonly region?: string;
+    /** Service name on every emitted segment. Surfaces in X-Ray's
+     *  service map. Required. */
+    readonly serviceName: string;
+    /** 0..1 — fraction of turns to sample. Default `1.0` (every turn).
+     *  Decisions are made at `turn_start` and persist for the whole
+     *  turn so partial traces never reach X-Ray. */
+    readonly sampleRate?: number;
+    /** Max segments buffered before forced flush. X-Ray's
+     *  `PutTraceSegments` API accepts up to 50 segments per call;
+     *  default 25 keeps latency tight. */
+    readonly maxBatchSegments?: number;
+    /** Forced flush window for low-traffic agents. Default 1000ms.
+     *  `0` disables time-based flush. */
+    readonly flushIntervalMs?: number;
+    /** Test injection — bypasses SDK lazy-require entirely. */
+    readonly _client?: XRayLikeClient;
+}
+export interface XRayLikeClient {
+    putTraceSegments(input: {
+        TraceSegmentDocuments: ReadonlyArray<string>;
+    }): Promise<unknown>;
+}
+export declare function xrayObservability(opts: XrayObservabilityOptions): ObservabilityStrategy;