pluribus-context 0.3.27 → 0.3.29

package/docs/context-budget-receipts.md

@@ -63,6 +63,50 @@ Public trace:
 
 - `examples/context-input-evidence/subagent-context-budget-otel-trace.json`
 
+## Per-agent MCP injection
+
+Role-specific subagents may need different MCP surfaces: a testing agent might need `testing` and `github`, while deployment, analytics, email, or browser servers should stay outside that boot context. The receipt should prove the policy boundary before the first task:
+
+- role/session id for the subagent without raw instructions;
+- available server count/hash for the role;
+- excluded server count/hash before boot;
+- loaded vs deferred tool-definition counts;
+- startup token bucket after the policy was applied; and
+- an explicit audit gap that this proves injection scope, not semantic tool quality.
+
+Minimal events:
+
+- `subagent.mcp_policy.applied`
+- `subagent.context_boot.evaluated`
+
+## ToolSearch propagation into subagents
+
+When MCP tools are deferred behind `ToolSearch`, subagent bugs can hide in three different layers:
+
+- the parent/orchestrator policy intended to expose or exclude MCP/ToolSearch;
+- the subagent `tools:` declaration made `ToolSearch` available, stripped it, or froze an older registry; and
+- the runtime filter actually exposed the deferred-tools channel after spawn.
+
+The receipt should make those layers distinguishable without raw tool schemas, prompts, agent files, or private paths. It should include:
+
+- spawn path and whether skill context was active;
+- coarse bucket for parent intermediate tool calls before spawn;
+- `tools:` declaration shape such as wildcard, explicit include, or exclusion style;
+- whether `ToolSearch` was declared and actually exposed to the subagent;
+- parent vs subagent MCP server count buckets;
+- loaded vs deferred tool-definition buckets; and
+- a `filtered_by` or `filter_reason` category.
+
+Runnable fixture:
+
+```bash
+node examples/context-input-evidence/convert-subagent-toolsearch-propagation-log.mjs
+```
+
+Public trace:
+
+- `examples/context-input-evidence/subagent-toolsearch-propagation-otel-trace.json`
+
 ## Delegation boundary
 
 A subagent can save parent context at boot and still lose the benefit if raw child output is pasted back into the parent. The receipt should prove:
@@ -146,7 +190,8 @@ Instead of “why is my subagent bad?”, ask for a receipt or debug JSON that c
 2. How many were loaded into the parent?
 3. How many were loaded into the subagent?
 4. How many were suppressed/deferred?
-5. What token bucket remained before the first tool call?
-6. Did raw child output return to the parent, or only a bounded summary?
+5. For a subagent, which MCP servers were allowed and which were excluded before boot?
+6. What token bucket remained before the first tool call?
+7. Did raw child output return to the parent, or only a bounded summary?
 
 That is the narrow wedge for Pluribus: context-budget evidence across agent boundaries, not another memory store or tool router.

package/examples/agent-skills/context-receipts/README.md

@@ -13,10 +13,14 @@ It is intentionally markdown-only so it can be copied into a local skills direct
 Ask an agent or harness using the skill to emit a receipt for one workflow and verify these constraints:
 
 ```bash
-grep -E 'mcp\.tool_index\.loaded|context\.skill\.registry\.index\.loaded|subagent\.delegation\.requested' receipt.jsonl
+grep -E 'mcp\.tool_index\.loaded|context\.skill\.registry\.index\.loaded|subagent\.mcp_policy\.applied|subagent\.toolsearch\.propagation\.evaluated|subagent\.delegation\.requested' receipt.jsonl
 grep -E 'raw_(schema|query|args|result|output)_copied":false|raw.*CopiedToReceipt":false' receipt.jsonl
 ```
 
 Then manually check that the receipt contains counts, hashes, ids, buckets, and `audit_gap`, but does **not** contain private prompts, raw schemas, tool args/results, skill bodies, memory bodies, customer names, secrets, or transcript text.
 
-For executable fixture examples, see [`../../context-input-evidence/`](../../context-input-evidence/).
+For executable fixture examples, see [`../../context-input-evidence/`](../../context-input-evidence/), including the ToolSearch propagation smoke:
+
+```bash
+node ../../context-input-evidence/convert-subagent-toolsearch-propagation-log.mjs
+```

package/examples/agent-skills/context-receipts/SKILL.md

@@ -59,6 +59,42 @@ Minimal event names:
 - `context.input.loaded`
 - `context.input.candidate_suppressed`
 
+## Per-agent MCP injection smoke
+
+For role-specific subagents or per-agent MCP configs, prove the policy boundary before debugging model quality:
+
+- which subagent role/session requested tools;
+- which MCP servers were available to that role;
+- which servers were explicitly excluded before boot;
+- whether startup loaded full schemas or only a compact index;
+- how many tool definitions stayed deferred/suppressed; and
+- the startup token bucket after policy was applied.
+
+Minimal JSONL event names:
+
+```jsonl
+{"event":"subagent.mcp_policy.applied","subagent_role":"testing","available_server_count":2,"available_servers_hash":"sha256:...","excluded_server_count":5,"excluded_servers_hash":"sha256:...","policy_source":"role_config","raw_server_names_copied":false}
+{"event":"subagent.context_boot.evaluated","subagent_role":"testing","loaded_tool_definition_count":0,"deferred_tool_definition_count":48,"startup_token_bucket":"50k_75k","raw_schema_copied":false,"audit_gap":"proves injection boundary, not tool relevance"}
+```
+
+## ToolSearch propagation smoke
+
+For subagents that should inherit MCP through `ToolSearch`, distinguish policy, declaration, and runtime filtering:
+
+- did the parent/orchestrator intend to expose MCP or exclude it for this subagent?
+- was the subagent spawned immediately or after parent tool calls/orchestration work?
+- was the `tools:` declaration wildcard, explicit include, or exclusion style?
+- was `ToolSearch` declared and was it actually exposed in the subagent tool surface?
+- did MCP servers/tool definitions stay deferred, or did the channel collapse to zero?
+- was the agent registry loaded at session boot, making newly added agent files invisible until restart?
+
+Minimal JSONL event names:
+
+```jsonl
+{"event":"subagent.toolsearch.propagation.evaluated","spawn_path":"Task","tools_declaration_shape":"enumerated_include","toolsearch_declared":false,"toolsearch_exposed":false,"mcp_servers_available_bucket":"0","deferred_tool_definitions_bucket":"0","filtered_by":"frontmatter_tools_policy_or_runtime_filter","raw_tool_schemas_copied":false}
+{"event":"subagent.toolsearch.matrix.completed","tested_axis":"tools_frontmatter_shape","audit_gap":"proves ToolSearch exposure, not semantic tool relevance or runtime call success"}
+```
+
 ## Subagent / manager boundary smoke
 
 For subagents, manager agents, or child workers, answer:

package/examples/context-input-evidence/convert-subagent-toolsearch-propagation-log.mjs

@@ -0,0 +1,171 @@
+#!/usr/bin/env node
+import { createHash } from 'node:crypto';
+import { readFileSync, writeFileSync } from 'node:fs';
+import { dirname, join, resolve } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const here = dirname(fileURLToPath(import.meta.url));
+const inputPath = process.argv[2] ? resolve(process.argv[2]) : join(here, 'sample-subagent-toolsearch-propagation-log.jsonl');
+const receiptPath = process.argv[3] ? resolve(process.argv[3]) : join(here, 'subagent-toolsearch-propagation-receipt.ndjson');
+const tracePath = process.argv[4] ? resolve(process.argv[4]) : join(here, 'subagent-toolsearch-propagation-otel-trace.json');
+
+function sha256(value) {
+  return `sha256:${createHash('sha256').update(value ?? '').digest('hex')}`;
+}
+
+function hashRef(value) {
+  return sha256(value ?? '').slice(0, 19);
+}
+
+function readJsonl(path) {
+  return readFileSync(path, 'utf8')
+    .trim()
+    .split('\n')
+    .filter(Boolean)
+    .map((line, index) => {
+      try {
+        return JSON.parse(line);
+      } catch (error) {
+        throw new Error(`Invalid JSONL at ${path}:${index + 1}: ${error.message}`);
+      }
+    });
+}
+
+function unixNano(isoTimestamp) {
+  return `${BigInt(Date.parse(isoTimestamp)) * 1_000_000n}`;
+}
+
+function otelValue(value) {
+  if (typeof value === 'boolean') return { boolValue: value };
+  if (typeof value === 'number' && Number.isInteger(value)) return { intValue: String(value) };
+  if (typeof value === 'number') return { doubleValue: value };
+  if (value == null) return { stringValue: '' };
+  return { stringValue: String(value) };
+}
+
+function attributesToOtel(attributes) {
+  return Object.entries(attributes).map(([key, value]) => ({ key, value: otelValue(value) }));
+}
+
+function countBucket(value) {
+  if (value === 0) return 'zero';
+  if (value <= 5) return 'under_5';
+  if (value <= 25) return 'under_25';
+  if (value <= 100) return 'under_100';
+  if (value <= 500) return 'under_500';
+  return 'over_500';
+}
+
+const records = readJsonl(inputPath);
+const session = records.find((record) => record.type === 'session.start');
+const probes = records.filter((record) => record.type === 'subagent.spawn.probe');
+const completed = records.find((record) => record.type === 'subagent.toolsearch.matrix.completed');
+
+if (!session || probes.length === 0 || !completed) {
+  throw new Error(`Expected session.start, subagent.spawn.probe records, and subagent.toolsearch.matrix.completed in ${inputPath}`);
+}
+
+const traceSeed = `${session.session_id}:${session.conversation_id}:subagent-toolsearch-propagation`;
+const traceId = sha256(traceSeed).replace('sha256:', '').slice(0, 32);
+const spanId = sha256(`${traceSeed}:span`).replace('sha256:', '').slice(0, 16);
+
+const events = [
+  ...probes.map((record) => ({
+    trace_id: traceId,
+    span_id: spanId,
+    name: 'subagent.toolsearch.propagation.evaluated',
+    time: record.time,
+    attributes: {
+      'session.id': session.session_id,
+      'gen_ai.conversation.id': session.conversation_id,
+      'agent.name': session.agent,
+      'subagent.type_hash': hashRef(record.subagent_type),
+      'subagent.spawn.path': record.spawn_path,
+      'subagent.skill_context_active': record.skill_context_active,
+      'subagent.parent_intermediate_tool_call_count_bucket': countBucket(record.parent_intermediate_tool_call_count),
+      'subagent.tools.declaration_shape': record.tools_declaration_shape,
+      'subagent.tools.toolsearch_declared': record.toolsearch_declared,
+      'subagent.tools.toolsearch_exposed': record.toolsearch_exposed,
+      'subagent.mcp.parent_server_count_bucket': countBucket(record.mcp_server_count_parent),
+      'subagent.mcp.available_server_count_bucket': countBucket(record.mcp_server_count_subagent),
+      'subagent.mcp.loaded_tool_definition_count_bucket': countBucket(record.loaded_tool_definition_count),
+      'subagent.mcp.deferred_tool_definition_count_bucket': countBucket(record.deferred_tool_definition_count),
+      'subagent.tools.filter_reason': record.filter_reason,
+      'subagent.tools.declaration_hash': sha256(record.raw_tools_declaration),
+      'privacy.raw_tools_declaration_recorded': false,
+      'privacy.raw_tool_schemas_recorded': false,
+      'privacy.raw_prompts_recorded': false,
+      'privacy.raw_paths_recorded': false
+    }
+  })),
+  {
+    trace_id: traceId,
+    span_id: spanId,
+    name: 'subagent.toolsearch.matrix.completed',
+    time: completed.time,
+    attributes: {
+      'session.id': session.session_id,
+      'gen_ai.conversation.id': session.conversation_id,
+      'subagent.toolsearch.tested_axis': completed.tested_axis,
+      'subagent.toolsearch.probe_count_bucket': countBucket(completed.probe_count),
+      'subagent.toolsearch.passing_probe_count_bucket': countBucket(completed.passing_probe_count),
+      'subagent.toolsearch.failing_probe_count_bucket': countBucket(completed.failing_probe_count),
+      'subagent.toolsearch.recommended_next_probe_hash': hashRef(completed.recommended_next_probe),
+      'subagent.toolsearch.audit_gap': completed.audit_gap
+    }
+  }
+];
+
+writeFileSync(receiptPath, `${events.map((event) => JSON.stringify(event)).join('\n')}\n`);
+
+const trace = {
+  resourceSpans: [
+    {
+      resource: {
+        attributes: attributesToOtel({
+          'service.name': 'pluribus-subagent-toolsearch-propagation-receipt-demo',
+          'service.version': '0.0.0-fixture',
+          'deployment.environment.name': 'local-fixture'
+        })
+      },
+      scopeSpans: [
+        {
+          scope: {
+            name: 'pluribus.context_input_evidence.subagent_toolsearch_propagation_demo',
+            version: '0.0.0-fixture'
+          },
+          spans: [
+            {
+              traceId,
+              spanId,
+              parentSpanId: '',
+              name: 'agent.subagent.toolsearch.propagation',
+              kind: 1,
+              startTimeUnixNano: unixNano(probes[0].time),
+              endTimeUnixNano: unixNano(completed.time),
+              attributes: attributesToOtel({
+                'session.id': session.session_id,
+                'gen_ai.conversation.id': session.conversation_id,
+                'agent.name': session.agent,
+                'workspace.name_hash': hashRef(session.workspace),
+                'gen_ai.request.model': session.model,
+                'subagent.context.receipt.scope': 'toolsearch_propagation_matrix'
+              }),
+              events: events.map((event) => ({
+                name: event.name,
+                timeUnixNano: unixNano(event.time),
+                attributes: attributesToOtel(event.attributes)
+              })),
+              status: { code: 1 }
+            }
+          ]
+        }
+      ]
+    }
+  ]
+};
+
+writeFileSync(tracePath, `${JSON.stringify(trace, null, 2)}\n`);
+
+console.log(`Wrote ${receiptPath}`);
+console.log(`Wrote ${tracePath}`);

package/examples/context-input-evidence/sample-subagent-toolsearch-propagation-log.jsonl

@@ -0,0 +1,5 @@
+{"type":"session.start","time":"2026-05-25T20:00:00.000Z","session_id":"sess_toolsearch_propagation_demo","conversation_id":"conv_toolsearch_propagation_demo","agent":"claude-code","workspace":"private-repo-redacted","model":"claude-opus-4.7"}
+{"type":"subagent.spawn.probe","time":"2026-05-25T20:00:01.000Z","subagent_type":"architect","spawn_path":"Task","skill_context_active":false,"parent_intermediate_tool_call_count":0,"tools_declaration_shape":"enumerated_include","toolsearch_declared":false,"toolsearch_exposed":false,"mcp_server_count_parent":6,"mcp_server_count_subagent":0,"deferred_tool_definition_count":0,"loaded_tool_definition_count":0,"filter_reason":"frontmatter_tools_policy_or_runtime_filter","raw_tools_declaration":"Read, Write, Edit, Glob, Grep, Bash, Task, WebSearch"}
+{"type":"subagent.spawn.probe","time":"2026-05-25T20:00:02.000Z","subagent_type":"general-purpose","spawn_path":"Task","skill_context_active":false,"parent_intermediate_tool_call_count":0,"tools_declaration_shape":"wildcard","toolsearch_declared":true,"toolsearch_exposed":true,"mcp_server_count_parent":6,"mcp_server_count_subagent":6,"deferred_tool_definition_count":49,"loaded_tool_definition_count":0,"filter_reason":"wildcard_allows_deferred_tool_channel","raw_tools_declaration":"*"}
+{"type":"subagent.spawn.probe","time":"2026-05-25T20:00:03.000Z","subagent_type":"explore","spawn_path":"Task","skill_context_active":false,"parent_intermediate_tool_call_count":0,"tools_declaration_shape":"exclusion_style","toolsearch_declared":false,"toolsearch_exposed":false,"mcp_server_count_parent":6,"mcp_server_count_subagent":0,"deferred_tool_definition_count":0,"loaded_tool_definition_count":0,"filter_reason":"exclusion_style_did_not_preserve_deferred_tool_channel","raw_tools_declaration":"All tools except Agent, ExitPlanMode, Edit, Write, NotebookEdit"}
+{"type":"subagent.toolsearch.matrix.completed","time":"2026-05-25T20:00:04.000Z","tested_axis":"tools_frontmatter_shape","probe_count":3,"passing_probe_count":1,"failing_probe_count":2,"recommended_next_probe":"fresh_session_explicit_toolsearch_in_tools_list","audit_gap":"proves ToolSearch exposure and MCP count buckets, not semantic tool relevance or runtime tool-call success"}

package/examples/context-input-evidence/subagent-toolsearch-propagation-otel-trace.json

@@ -0,0 +1,522 @@
+{
+  "resourceSpans": [
+    {
+      "resource": {
+        "attributes": [
+          {
+            "key": "service.name",
+            "value": {
+              "stringValue": "pluribus-subagent-toolsearch-propagation-receipt-demo"
+            }
+          },
+          {
+            "key": "service.version",
+            "value": {
+              "stringValue": "0.0.0-fixture"
+            }
+          },
+          {
+            "key": "deployment.environment.name",
+            "value": {
+              "stringValue": "local-fixture"
+            }
+          }
+        ]
+      },
+      "scopeSpans": [
+        {
+          "scope": {
+            "name": "pluribus.context_input_evidence.subagent_toolsearch_propagation_demo",
+            "version": "0.0.0-fixture"
+          },
+          "spans": [
+            {
+              "traceId": "503722a46b27d38ce02b9ba8c7b445f6",
+              "spanId": "b338ade0fe167184",
+              "parentSpanId": "",
+              "name": "agent.subagent.toolsearch.propagation",
+              "kind": 1,
+              "startTimeUnixNano": "1779739201000000000",
+              "endTimeUnixNano": "1779739204000000000",
+              "attributes": [
+                {
+                  "key": "session.id",
+                  "value": {
+                    "stringValue": "sess_toolsearch_propagation_demo"
+                  }
+                },
+                {
+                  "key": "gen_ai.conversation.id",
+                  "value": {
+                    "stringValue": "conv_toolsearch_propagation_demo"
+                  }
+                },
+                {
+                  "key": "agent.name",
+                  "value": {
+                    "stringValue": "claude-code"
+                  }
+                },
+                {
+                  "key": "workspace.name_hash",
+                  "value": {
+                    "stringValue": "sha256:6d00f89e3ce3"
+                  }
+                },
+                {
+                  "key": "gen_ai.request.model",
+                  "value": {
+                    "stringValue": "claude-opus-4.7"
+                  }
+                },
+                {
+                  "key": "subagent.context.receipt.scope",
+                  "value": {
+                    "stringValue": "toolsearch_propagation_matrix"
+                  }
+                }
+              ],
+              "events": [
+                {
+                  "name": "subagent.toolsearch.propagation.evaluated",
+                  "timeUnixNano": "1779739201000000000",
+                  "attributes": [
+                    {
+                      "key": "session.id",
+                      "value": {
+                        "stringValue": "sess_toolsearch_propagation_demo"
+                      }
+                    },
+                    {
+                      "key": "gen_ai.conversation.id",
+                      "value": {
+                        "stringValue": "conv_toolsearch_propagation_demo"
+                      }
+                    },
+                    {
+                      "key": "agent.name",
+                      "value": {
+                        "stringValue": "claude-code"
+                      }
+                    },
+                    {
+                      "key": "subagent.type_hash",
+                      "value": {
+                        "stringValue": "sha256:f2e40fc1edb7"
+                      }
+                    },
+                    {
+                      "key": "subagent.spawn.path",
+                      "value": {
+                        "stringValue": "Task"
+                      }
+                    },
+                    {
+                      "key": "subagent.skill_context_active",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "subagent.parent_intermediate_tool_call_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.declaration_shape",
+                      "value": {
+                        "stringValue": "enumerated_include"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.toolsearch_declared",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.toolsearch_exposed",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.parent_server_count_bucket",
+                      "value": {
+                        "stringValue": "under_25"
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.available_server_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.loaded_tool_definition_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.deferred_tool_definition_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.filter_reason",
+                      "value": {
+                        "stringValue": "frontmatter_tools_policy_or_runtime_filter"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.declaration_hash",
+                      "value": {
+                        "stringValue": "sha256:318352b16ca17e43ab5aef62a29dc33fdfd01285efba75a7ba97b4be735d9ef1"
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_tools_declaration_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_tool_schemas_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_prompts_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_paths_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    }
+                  ]
+                },
+                {
+                  "name": "subagent.toolsearch.propagation.evaluated",
+                  "timeUnixNano": "1779739202000000000",
+                  "attributes": [
+                    {
+                      "key": "session.id",
+                      "value": {
+                        "stringValue": "sess_toolsearch_propagation_demo"
+                      }
+                    },
+                    {
+                      "key": "gen_ai.conversation.id",
+                      "value": {
+                        "stringValue": "conv_toolsearch_propagation_demo"
+                      }
+                    },
+                    {
+                      "key": "agent.name",
+                      "value": {
+                        "stringValue": "claude-code"
+                      }
+                    },
+                    {
+                      "key": "subagent.type_hash",
+                      "value": {
+                        "stringValue": "sha256:db45ca5bb406"
+                      }
+                    },
+                    {
+                      "key": "subagent.spawn.path",
+                      "value": {
+                        "stringValue": "Task"
+                      }
+                    },
+                    {
+                      "key": "subagent.skill_context_active",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "subagent.parent_intermediate_tool_call_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.declaration_shape",
+                      "value": {
+                        "stringValue": "wildcard"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.toolsearch_declared",
+                      "value": {
+                        "boolValue": true
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.toolsearch_exposed",
+                      "value": {
+                        "boolValue": true
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.parent_server_count_bucket",
+                      "value": {
+                        "stringValue": "under_25"
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.available_server_count_bucket",
+                      "value": {
+                        "stringValue": "under_25"
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.loaded_tool_definition_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.deferred_tool_definition_count_bucket",
+                      "value": {
+                        "stringValue": "under_100"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.filter_reason",
+                      "value": {
+                        "stringValue": "wildcard_allows_deferred_tool_channel"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.declaration_hash",
+                      "value": {
+                        "stringValue": "sha256:684888c0ebb17f374298b65ee2807526c066094c701bcc7ebbe1c1095f494fc1"
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_tools_declaration_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_tool_schemas_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_prompts_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_paths_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    }
+                  ]
+                },
+                {
+                  "name": "subagent.toolsearch.propagation.evaluated",
+                  "timeUnixNano": "1779739203000000000",
+                  "attributes": [
+                    {
+                      "key": "session.id",
+                      "value": {
+                        "stringValue": "sess_toolsearch_propagation_demo"
+                      }
+                    },
+                    {
+                      "key": "gen_ai.conversation.id",
+                      "value": {
+                        "stringValue": "conv_toolsearch_propagation_demo"
+                      }
+                    },
+                    {
+                      "key": "agent.name",
+                      "value": {
+                        "stringValue": "claude-code"
+                      }
+                    },
+                    {
+                      "key": "subagent.type_hash",
+                      "value": {
+                        "stringValue": "sha256:6f281157ab24"
+                      }
+                    },
+                    {
+                      "key": "subagent.spawn.path",
+                      "value": {
+                        "stringValue": "Task"
+                      }
+                    },
+                    {
+                      "key": "subagent.skill_context_active",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "subagent.parent_intermediate_tool_call_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.declaration_shape",
+                      "value": {
+                        "stringValue": "exclusion_style"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.toolsearch_declared",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.toolsearch_exposed",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.parent_server_count_bucket",
+                      "value": {
+                        "stringValue": "under_25"
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.available_server_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.loaded_tool_definition_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.mcp.deferred_tool_definition_count_bucket",
+                      "value": {
+                        "stringValue": "zero"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.filter_reason",
+                      "value": {
+                        "stringValue": "exclusion_style_did_not_preserve_deferred_tool_channel"
+                      }
+                    },
+                    {
+                      "key": "subagent.tools.declaration_hash",
+                      "value": {
+                        "stringValue": "sha256:7bceda7b67b76245654ccbe33f1ba47f7ee3608823be750c83112219b205aab3"
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_tools_declaration_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_tool_schemas_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_prompts_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    },
+                    {
+                      "key": "privacy.raw_paths_recorded",
+                      "value": {
+                        "boolValue": false
+                      }
+                    }
+                  ]
+                },
+                {
+                  "name": "subagent.toolsearch.matrix.completed",
+                  "timeUnixNano": "1779739204000000000",
+                  "attributes": [
+                    {
+                      "key": "session.id",
+                      "value": {
+                        "stringValue": "sess_toolsearch_propagation_demo"
+                      }
+                    },
+                    {
+                      "key": "gen_ai.conversation.id",
+                      "value": {
+                        "stringValue": "conv_toolsearch_propagation_demo"
+                      }
+                    },
+                    {
+                      "key": "subagent.toolsearch.tested_axis",
+                      "value": {
+                        "stringValue": "tools_frontmatter_shape"
+                      }
+                    },
+                    {
+                      "key": "subagent.toolsearch.probe_count_bucket",
+                      "value": {
+                        "stringValue": "under_5"
+                      }
+                    },
+                    {
+                      "key": "subagent.toolsearch.passing_probe_count_bucket",
+                      "value": {
+                        "stringValue": "under_5"
+                      }
+                    },
+                    {
+                      "key": "subagent.toolsearch.failing_probe_count_bucket",
+                      "value": {
+                        "stringValue": "under_5"
+                      }
+                    },
+                    {
+                      "key": "subagent.toolsearch.recommended_next_probe_hash",
+                      "value": {
+                        "stringValue": "sha256:4a49fb4516c4"
+                      }
+                    },
+                    {
+                      "key": "subagent.toolsearch.audit_gap",
+                      "value": {
+                        "stringValue": "proves ToolSearch exposure and MCP count buckets, not semantic tool relevance or runtime tool-call success"
+                      }
+                    }
+                  ]
+                }
+              ],
+              "status": {
+                "code": 1
+              }
+            }
+          ]
+        }
+      ]
+    }
+  ]
+}

package/examples/context-input-evidence/subagent-toolsearch-propagation-receipt.ndjson

@@ -0,0 +1,4 @@
+{"trace_id":"503722a46b27d38ce02b9ba8c7b445f6","span_id":"b338ade0fe167184","name":"subagent.toolsearch.propagation.evaluated","time":"2026-05-25T20:00:01.000Z","attributes":{"session.id":"sess_toolsearch_propagation_demo","gen_ai.conversation.id":"conv_toolsearch_propagation_demo","agent.name":"claude-code","subagent.type_hash":"sha256:f2e40fc1edb7","subagent.spawn.path":"Task","subagent.skill_context_active":false,"subagent.parent_intermediate_tool_call_count_bucket":"zero","subagent.tools.declaration_shape":"enumerated_include","subagent.tools.toolsearch_declared":false,"subagent.tools.toolsearch_exposed":false,"subagent.mcp.parent_server_count_bucket":"under_25","subagent.mcp.available_server_count_bucket":"zero","subagent.mcp.loaded_tool_definition_count_bucket":"zero","subagent.mcp.deferred_tool_definition_count_bucket":"zero","subagent.tools.filter_reason":"frontmatter_tools_policy_or_runtime_filter","subagent.tools.declaration_hash":"sha256:318352b16ca17e43ab5aef62a29dc33fdfd01285efba75a7ba97b4be735d9ef1","privacy.raw_tools_declaration_recorded":false,"privacy.raw_tool_schemas_recorded":false,"privacy.raw_prompts_recorded":false,"privacy.raw_paths_recorded":false}}
+{"trace_id":"503722a46b27d38ce02b9ba8c7b445f6","span_id":"b338ade0fe167184","name":"subagent.toolsearch.propagation.evaluated","time":"2026-05-25T20:00:02.000Z","attributes":{"session.id":"sess_toolsearch_propagation_demo","gen_ai.conversation.id":"conv_toolsearch_propagation_demo","agent.name":"claude-code","subagent.type_hash":"sha256:db45ca5bb406","subagent.spawn.path":"Task","subagent.skill_context_active":false,"subagent.parent_intermediate_tool_call_count_bucket":"zero","subagent.tools.declaration_shape":"wildcard","subagent.tools.toolsearch_declared":true,"subagent.tools.toolsearch_exposed":true,"subagent.mcp.parent_server_count_bucket":"under_25","subagent.mcp.available_server_count_bucket":"under_25","subagent.mcp.loaded_tool_definition_count_bucket":"zero","subagent.mcp.deferred_tool_definition_count_bucket":"under_100","subagent.tools.filter_reason":"wildcard_allows_deferred_tool_channel","subagent.tools.declaration_hash":"sha256:684888c0ebb17f374298b65ee2807526c066094c701bcc7ebbe1c1095f494fc1","privacy.raw_tools_declaration_recorded":false,"privacy.raw_tool_schemas_recorded":false,"privacy.raw_prompts_recorded":false,"privacy.raw_paths_recorded":false}}
+{"trace_id":"503722a46b27d38ce02b9ba8c7b445f6","span_id":"b338ade0fe167184","name":"subagent.toolsearch.propagation.evaluated","time":"2026-05-25T20:00:03.000Z","attributes":{"session.id":"sess_toolsearch_propagation_demo","gen_ai.conversation.id":"conv_toolsearch_propagation_demo","agent.name":"claude-code","subagent.type_hash":"sha256:6f281157ab24","subagent.spawn.path":"Task","subagent.skill_context_active":false,"subagent.parent_intermediate_tool_call_count_bucket":"zero","subagent.tools.declaration_shape":"exclusion_style","subagent.tools.toolsearch_declared":false,"subagent.tools.toolsearch_exposed":false,"subagent.mcp.parent_server_count_bucket":"under_25","subagent.mcp.available_server_count_bucket":"zero","subagent.mcp.loaded_tool_definition_count_bucket":"zero","subagent.mcp.deferred_tool_definition_count_bucket":"zero","subagent.tools.filter_reason":"exclusion_style_did_not_preserve_deferred_tool_channel","subagent.tools.declaration_hash":"sha256:7bceda7b67b76245654ccbe33f1ba47f7ee3608823be750c83112219b205aab3","privacy.raw_tools_declaration_recorded":false,"privacy.raw_tool_schemas_recorded":false,"privacy.raw_prompts_recorded":false,"privacy.raw_paths_recorded":false}}
+{"trace_id":"503722a46b27d38ce02b9ba8c7b445f6","span_id":"b338ade0fe167184","name":"subagent.toolsearch.matrix.completed","time":"2026-05-25T20:00:04.000Z","attributes":{"session.id":"sess_toolsearch_propagation_demo","gen_ai.conversation.id":"conv_toolsearch_propagation_demo","subagent.toolsearch.tested_axis":"tools_frontmatter_shape","subagent.toolsearch.probe_count_bucket":"under_5","subagent.toolsearch.passing_probe_count_bucket":"under_5","subagent.toolsearch.failing_probe_count_bucket":"under_5","subagent.toolsearch.recommended_next_probe_hash":"sha256:4a49fb4516c4","subagent.toolsearch.audit_gap":"proves ToolSearch exposure and MCP count buckets, not semantic tool relevance or runtime tool-call success"}}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pluribus-context",
-  "version": "0.3.27",
+  "version": "0.3.29",
   "description": "AI context and rules sync CLI for Claude.md, Claude Code, Cursor, and Copilot instructions, with privacy-safe context receipts that prove what memory, tools, skills, compactions, and security findings crossed agent boundaries without logging raw content.",
   "type": "module",
   "homepage": "https://github.com/caioribeiroclw-pixel/pluribus#readme",

package/src/utils/version.js

@@ -1 +1 @@
-export const VERSION = '0.3.27'
+export const VERSION = '0.3.29'