@pellux/goodvibes-agent 1.0.34 → 1.0.35

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (28) hide show
  1. package/CHANGELOG.md +13 -4
  2. package/README.md +5 -3
  3. package/dist/package/{ast-grep-napi.linux-x64-gnu-mkk8xwww.node → ast-grep-napi.linux-x64-gnu-swtppvy9.node} +0 -0
  4. package/dist/package/{ast-grep-napi.linux-x64-musl-ryqtgdv6.node → ast-grep-napi.linux-x64-musl-ttfcdtap.node} +0 -0
  5. package/dist/package/main.js +48488 -49984
  6. package/docs/README.md +2 -2
  7. package/docs/getting-started.md +11 -8
  8. package/docs/release-and-publishing.md +1 -1
  9. package/docs/tools-and-commands.md +5 -1
  10. package/docs/voice-and-live-tts.md +1 -1
  11. package/package.json +1 -1
  12. package/release/live-verification/live-verification.json +13 -13
  13. package/release/live-verification/live-verification.md +17 -17
  14. package/release/release-notes.md +2 -2
  15. package/release/release-readiness.json +33 -33
  16. package/src/runtime/bootstrap-core.ts +2 -0
  17. package/src/runtime/bootstrap.ts +2 -0
  18. package/src/tools/agent-harness-media-posture.ts +1 -1
  19. package/src/tools/agent-harness-metadata.ts +44 -32
  20. package/src/tools/agent-harness-mode-catalog.ts +205 -0
  21. package/src/tools/agent-harness-operator-methods.ts +2 -2
  22. package/src/tools/agent-harness-service-posture.ts +1 -1
  23. package/src/tools/agent-harness-setup-posture.ts +1 -1
  24. package/src/tools/agent-harness-tool-schema.ts +1 -1
  25. package/src/tools/agent-harness-tool.ts +14 -4
  26. package/src/tools/agent-harness-ui-surface-metadata.ts +21 -17
  27. package/src/tools/tool-definition-compaction.ts +49 -0
  28. package/src/version.ts +1 -1
package/docs/README.md CHANGED
@@ -29,11 +29,11 @@ These are the package-facing docs for the GoodVibes Agent `1.0.x` release line.
29
29
 
30
30
  Agent-owned model tools expose the same user-facing harness surfaces:
31
31
 
32
- - `agent_harness` for workspace actions, slash commands, settings, panels, UI surfaces, keybindings, tool schemas, service/daemon posture, connected-host capability/status, release evidence, and posture catalogs.
32
+ - `agent_harness` for searchable mode discovery, workspace actions, slash commands, settings, panels, UI surfaces, keybindings, tool schemas, service/daemon posture, connected-host capability/status, release evidence, and posture catalogs.
33
33
  - `agent_knowledge` and `agent_knowledge_ingest` for isolated Agent Knowledge.
34
34
  - `agent_local_registry` for Agent-local memory, notes, personas, skills, bundles, and routines.
35
35
  - `agent_work_plan` for visible local work-plan state.
36
36
  - `agent_operator_briefing` and `agent_operator_action` for public connected operator state and exact confirmed actions.
37
37
  - `agent_channel_send`, `agent_notify`, `agent_reminder_schedule`, and `agent_media_generate` for explicit confirmed effects.
38
38
 
39
- Catalog modes are compact by default. Detailed schemas, route hints, redacted log tail, release artifact data, and editor fields require `includeParameters:true` or a singular inspect mode. Mutations, external delivery, UI routing, keybinding changes, setting writes, local destructive actions, media generation, reminders, and connected-host operator actions remain confirmation-gated and refuse ambiguous lookup.
39
+ Catalog modes are compact by default. `agent_harness mode:"modes"` searches all harness modes; `mode:"mode"` inspects one mode contract. Detailed schemas, route hints, redacted log tail, release artifact data, and editor fields require `includeParameters:true` or a singular inspect mode. Registered tool definitions use short top-level descriptions and omit nested parameter descriptions from the default model catalog. Mutations, external delivery, UI routing, keybinding changes, setting writes, local destructive actions, media generation, reminders, and connected-host operator actions remain confirmation-gated and refuse ambiguous lookup.
package/docs/getting-started.md CHANGED
@@ -54,7 +54,7 @@ Press `/` inside the Agent workspace to search actions by name, category, comman
54
54
 
55
55
  ## Model Access
56
56
 
57
- The main Agent model can use the same user-facing harness through Agent-owned tools. Use `agent_harness mode:"summary"` for a compact map, then drill into plural catalogs or single-item inspect modes.
57
+ The main Agent model can use the same user-facing harness through Agent-owned tools. Use `agent_harness mode:"summary"` for a compact map, `mode:"modes"` to search every harness mode by task or id, and `mode:"mode"` to inspect one mode contract. Then drill into plural catalogs or single-item inspect modes.
58
58
 
59
59
  Default discovery is intentionally compact:
60
60
 
@@ -66,20 +66,23 @@ Common model routes:
66
66
 
67
67
  | Need | Tool Or Mode |
68
68
  | --- | --- |
69
- | Workspace actions | `agent_harness workspace_actions`, `workspace_action`, `run_workspace_action` |
70
- | Slash commands | `agent_harness commands`, `command`, `run_command` |
71
- | Settings | `agent_harness settings`, `get_setting`, `set_setting`, `reset_setting` |
72
- | Visible UI | `agent_harness panels`, `ui_surfaces`, `open_panel`, `open_ui_surface` |
73
- | Keybindings | `agent_harness shortcuts`, `keybindings`, `keybinding`, `run_keybinding`, `set_keybinding` |
69
+ | Harness mode discovery | `agent_harness mode:"modes"`, `mode:"mode"` |
70
+ | Workspace actions | `agent_harness mode:"workspace_actions"`, `mode:"workspace_action"`, `mode:"run_workspace_action"` |
71
+ | Slash commands | `agent_harness mode:"commands"`, `mode:"command"`, `mode:"run_command"` |
72
+ | Settings | `agent_harness mode:"settings"`, `mode:"get_setting"`, `mode:"set_setting"`, `mode:"reset_setting"` |
73
+ | Visible UI | `agent_harness mode:"panels"`, `mode:"ui_surfaces"`, `mode:"open_panel"`, `mode:"open_ui_surface"` |
74
+ | Keybindings | `agent_harness mode:"shortcuts"`, `mode:"keybindings"`, `mode:"keybinding"`, `mode:"run_keybinding"`, `mode:"set_keybinding"` |
74
75
  | Agent Knowledge | `agent_knowledge`, `agent_knowledge_ingest` |
75
76
  | Local memory/notes/personas/skills/routines | `agent_local_registry` or confirmed workspace actions |
76
77
  | Work plan | `agent_work_plan` |
77
78
  | Channels, notifications, reminders, media | `agent_channel_send`, `agent_notify`, `agent_reminder_schedule`, `agent_media_generate` |
78
- | Operator state/actions | `agent_operator_briefing`, `agent_operator_action`, `operator_methods` |
79
- | Connected host/daemon posture | `service_posture`, `connected_host`, `connected_host_status`, `daemon`, `daemon_status` |
79
+ | Operator state/actions | `agent_operator_briefing`, `agent_operator_action`, `agent_harness mode:"operator_methods"` |
80
+ | Connected host/daemon posture | `agent_harness mode:"service_posture"`, `mode:"connected_host"`, `mode:"connected_host_status"`, `mode:"daemon"`, `mode:"daemon_status"` |
80
81
 
81
82
  All effects require explicit user request and confirmation. Ambiguous lookup is refused with candidates.
82
83
 
84
+ Registered tool definitions are intentionally terse. The default model catalog keeps top-level descriptions short and removes nested parameter descriptions; use `agent_harness mode:"tools"` with `includeParameters:true`, `mode:"tool"`, or the owning harness mode when detailed contracts are needed.
85
+
83
86
  ## Isolated Agent Profiles
84
87
 
85
88
  Use a separate Agent home for isolated local state:
package/docs/release-and-publishing.md CHANGED
@@ -70,7 +70,7 @@ Shared release metadata verification requires `architecture:check` to keep the A
70
70
 
71
71
  Shared release metadata verification requires `perf:check` to load `release/performance-snapshot.json`, validate its render samples and extra SLO/queue/tool/compaction/integration metrics, run the CI performance-budget evaluation, print the formatted report, and exit from the budget result. The release performance snapshot is staged with release metadata so the tag carries the exact non-live fixture used by the branch-CI performance gate.
72
72
 
73
- Shared release metadata verification requires `verification:ledger` to keep JSON and Markdown evidence output plus inventory coverage for settings schema, feature flags, slash commands, built-in panels, top-level CLI commands, external surfaces, onboarding capability bundles, the model-visible release evidence bundle, the model-visible service posture surface, the model-visible channel readiness surface, the model-visible notification target surface, the model-visible provider account surface, the model-visible MCP server surface, the model-visible setup/onboarding surface, the model-visible model routing surface, the model-visible pairing surface, the model-visible delegation surface, the model-visible security/support bundle surface, the model-visible voice/media posture surface, the model-visible sessions/bookmarks surface, the model-visible operator method catalog, and the release-quality dimensions from `release/release-readiness.json`, including local-signal, local-behavior, and external-outcome accounting. Package verification also enforces compact model tool registration, wrapped tool definitions, harness catalog defaults, and schema descriptions so tool metadata stays usable.
73
+ Shared release metadata verification requires `verification:ledger` to keep JSON and Markdown evidence output plus inventory coverage for settings schema, feature flags, slash commands, built-in panels, top-level CLI commands, external surfaces, onboarding capability bundles, the model-visible release evidence bundle, the model-visible service posture surface, the model-visible channel readiness surface, the model-visible notification target surface, the model-visible provider account surface, the model-visible MCP server surface, the model-visible setup/onboarding surface, the model-visible model routing surface, the model-visible pairing surface, the model-visible delegation surface, the model-visible security/support bundle surface, the model-visible voice/media posture surface, the model-visible sessions/bookmarks surface, the model-visible operator method catalog, the model-visible harness mode catalog, and the release-quality dimensions from `release/release-readiness.json`, including local-signal, local-behavior, and external-outcome accounting. Package verification also enforces compact model tool registration, wrapped tool definitions, harness catalog defaults, searchable harness mode discovery, and stripped nested schema descriptions so tool metadata stays usable.
74
74
 
75
75
  Shared release metadata verification requires `verification:live` to keep the external-outcome audit for stable releases: compiled CLI checks, connected-host token/URL discovery, connected-host status/health/model routes, isolated Agent Knowledge status/ask/search/source/node/issue/map/connector route checks plus packaged evidence for item inspection, SDK-version mismatch skip policy, JSON/Markdown report artifacts, strict mode, and Agent Knowledge contamination guards.
76
76
 
package/docs/tools-and-commands.md CHANGED
@@ -48,12 +48,13 @@ High-signal TUI routes:
48
48
 
49
49
  ## `agent_harness`
50
50
 
51
- Use `agent_harness mode:"summary"` first. Summary and plural catalog modes are compact by default. They return counts, ids, labels, state, and short route hints. Use `includeParameters:true` or a singular inspect mode when the model needs full schemas, policy detail, editor fields, redacted log tail, release artifact data, route hints, or tool parameters.
51
+ Use `agent_harness mode:"summary"` first. Use `mode:"modes"` to search every harness mode by task, family, effect type, id, alias, or parameter name. Use `mode:"mode"` to inspect one mode contract. Summary and plural catalog modes are compact by default. They return counts, ids, labels, state, and short route hints. Use `includeParameters:true` or a singular inspect mode when the model needs full schemas, policy detail, editor fields, redacted log tail, release artifact data, route hints, or tool parameters.
52
52
 
53
53
  Discovery modes:
54
54
 
55
55
  | Mode | What It Lists |
56
56
  | --- | --- |
57
+ | `modes` | Searchable catalog of every `agent_harness` mode and its task fit. |
57
58
  | `workspace`, `workspace_categories`, `workspace_actions` | Workspace categories and actions. |
58
59
  | `commands`, `cli_commands` | Slash commands and top-level package CLI mirrors. |
59
60
  | `panels`, `ui_surfaces` | Built-in panels and visible modal/overlay/picker/workspace surfaces. |
@@ -72,6 +73,7 @@ Single-item inspect modes:
72
73
 
73
74
  | Mode | Lookup Fields |
74
75
  | --- | --- |
76
+ | `mode` | `target` or `query` |
75
77
  | `workspace_action` | `actionId`, `command`, `target`, `query` |
76
78
  | `command`, `cli_command` | `command`, `commandName`, `cliCommand`, `target`, `query` |
77
79
  | `panel`, `ui_surface`, `keybinding`, `tool` | Exact id/name or `target`/`query` |
@@ -96,6 +98,8 @@ Effect modes:
96
98
 
97
99
  Every effect mode requires `confirm:true` and `explicitUserRequest`. Ambiguous lookups return candidates before any effect runs.
98
100
 
101
+ Registered model tool definitions are compact by default. Tool descriptions are capped or replaced with short Agent-specific summaries, and nested JSON-schema descriptions are stripped from the default registered catalog. Use `agent_harness mode:"tools"` with `includeParameters:true`, `mode:"tool"`, or a specific harness mode when detailed contracts are needed.
102
+
99
103
  ## Workspace Action Execution
100
104
 
101
105
  `workspace_action` inspection returns editor schemas and `modelExecution` detail. `workspace_actions` can include the same detail with `includeParameters:true`.
package/docs/voice-and-live-tts.md CHANGED
@@ -20,7 +20,7 @@ GoodVibes Agent supports spoken turns as an Agent TUI feature. Text output remai
20
20
 
21
21
  `/config tts` opens the fullscreen configuration workspace for streaming provider, voice, and spoken-turn model routing.
22
22
 
23
- The model can inspect the same settings through `agent_harness` settings modes, open the visible TTS provider or voice picker through `open_ui_surface`, and change Agent-owned TTS settings with explicit confirmation. `media_posture` is compact by default; use `includeParameters:true` or `media_provider` for full provider readiness, generation route hints, picker routes, and media policy detail. Connected-host listener or lifecycle settings remain outside Agent ownership.
23
+ The model can inspect the same settings through `agent_harness mode:"settings"` or `mode:"get_setting"`, open the visible TTS provider or voice picker through `mode:"open_ui_surface"`, and change Agent-owned TTS settings with explicit confirmation. `mode:"media_posture"` is compact by default; use `includeParameters:true` or `mode:"media_provider"` for full provider readiness, generation route hints, picker routes, and media policy detail. Connected-host listener or lifecycle settings remain outside Agent ownership.
24
24
 
25
25
  ## Playback Requirements
26
26
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@pellux/goodvibes-agent",
3
- "version": "1.0.34",
3
+ "version": "1.0.35",
4
4
  "private": false,
5
5
  "description": "GoodVibes personal operator assistant TUI with a proactive Agent product brain, isolated Agent Knowledge, local profiles, routines, skills, personas, and explicit build delegation.",
6
6
  "type": "module",
package/release/live-verification/live-verification.json CHANGED
@@ -1,16 +1,16 @@
1
1
  {
2
- "generatedAt": "2026-06-04T05:40:48.465Z",
2
+ "generatedAt": "2026-06-04T11:02:12.690Z",
3
3
  "homeDir": "[goodvibes-home]",
4
4
  "binaryPath": "[agent-binary]",
5
- "connectedHostBaseUrl": "http://127.0.0.1:37210",
5
+ "connectedHostBaseUrl": "http://127.0.0.1:3421",
6
6
  "strict": true,
7
7
  "checks": [
8
8
  {
9
9
  "id": "verification-ledger",
10
10
  "title": "Verification inventory ledger",
11
11
  "status": "pass",
12
- "summary": "100% local verification signal across 613 inventory items.",
13
- "detail": "84.5% local behavior verified; 95 item(s) require external outcomes."
12
+ "summary": "100% local verification signal across 761 inventory items.",
13
+ "detail": "87.4% local behavior verified; 96 item(s) require external outcomes."
14
14
  },
15
15
  {
16
16
  "id": "compiled-cli-present",
@@ -23,7 +23,7 @@
23
23
  "title": "Agent CLI version command",
24
24
  "status": "pass",
25
25
  "summary": "Agent CLI version returned successfully.",
26
- "detail": "goodvibes-agent 1.0.33"
26
+ "detail": "goodvibes-agent 1.0.35"
27
27
  },
28
28
  {
29
29
  "id": "cli-status-json",
@@ -37,14 +37,14 @@
37
37
  "title": "Agent CLI compatibility JSON command",
38
38
  "status": "pass",
39
39
  "summary": "Agent CLI compatibility returned parseable JSON.",
40
- "detail": "{\n \"ok\": true,\n \"packageVersion\": \"1.0.33\",\n \"sdkPin\": \"0.33.36\",\n \"connectedHost\": {\n \"baseUrl\": \"http://127.0.0.1:37210\",\n \"status\": 200,\n \"version\": \"0.33.36\",\n \"reachable\": true,\n \"compatible\": true\n },\n \"auth\": {\n \"tokenPresent\": true,\n \"tokenPath\": \"env:GOODVIBES_CONNECTED_HOST_TOKEN\"\n },\n \"agentKnowledge\": {\n \"route\": \"/api/goodvibes-agent/knowledge/status\",\n \"ready\": true,\n \"kind\": \"ok\"\n }\n}"
40
+ "detail": "{\n \"ok\": true,\n \"packageVersion\": \"1.0.35\",\n \"sdkPin\": \"0.33.36\",\n \"connectedHost\": {\n \"baseUrl\": \"http://127.0.0.1:3421\",\n \"status\": 200,\n \"version\": \"0.33.36\",\n \"reachable\": true,\n \"compatible\": true\n },\n \"auth\": {\n \"tokenPresent\": true,\n \"tokenPath\": \"env:GOODVIBES_CONNECTED_HOST_TOKEN\"\n },\n \"agentKnowledge\": {\n \"route\": \"/api/goodvibes-agent/knowledge/status\",\n \"ready\": true,\n \"kind\": \"ok\"\n }\n}"
41
41
  },
42
42
  {
43
43
  "id": "cli-agent-knowledge-status",
44
44
  "title": "Agent Knowledge CLI status command",
45
45
  "status": "pass",
46
46
  "summary": "Agent Knowledge status returned parseable JSON.",
47
- "detail": "{\n \"ok\": true,\n \"kind\": \"agentKnowledge.status\",\n \"route\": \"/api/goodvibes-agent/knowledge/status\",\n \"data\": {\n \"ready\": true,\n \"storagePath\": \"[home]/.goodvibes/goodvibes/knowledge-agent.sqlite\",\n \"sourceCount\": 0,\n \"nodeCount\": 0,\n \"edgeCount\": 0,\n \"issueCount\": 0,\n \"extractionCount\": 0,\n \"jobRunCount\": 0,\n \"refinementTaskCount\": 0,\n \"usageCount\": 0,\n \"candidateCount\": 0,\n \"reportCount\": 0,\n \"scheduleCount\": 3,\n \"note\": \"Structured knowledge uses SQL-backed sources, nodes, edges, issues, extractions, and job runs. Markdown is an optional projection, not the source of truth.\"\n }\n}"
47
+ "detail": "{\n \"ok\": true,\n \"kind\": \"agentKnowledge.status\",\n \"route\": \"/api/goodvibes-agent/knowledge/status\",\n \"data\": {\n \"ready\": true,\n \"storagePath\": \"[goodvibes-home]/tui/knowledge-agent.sqlite\",\n \"sourceCount\": 0,\n \"nodeCount\": 12,\n \"edgeCount\": 0,\n \"issueCount\": 0,\n \"extractionCount\": 0,\n \"jobRunCount\": 35,\n \"refinementTaskCount\": 0,\n \"usageCount\": 0,\n \"candidateCount\": 0,\n \"reportCount\": 2,\n \"scheduleCount\": 3,\n \"note\": \"Structured knowledge uses SQL-backed sources, nodes, edges, issues, extractions, and job runs. Markdown is an optional projection, not the source of truth.\"\n }\n}"
48
48
  },
49
49
  {
50
50
  "id": "cli-providers",
@@ -72,21 +72,21 @@
72
72
  "title": "Authenticated connected-host /api/health",
73
73
  "status": "pass",
74
74
  "summary": "Health overall=healthy.",
75
- "detail": "{\"overall\":\"healthy\",\"degradedDomains\":[],\"providerProblems\":[],\"mcpProblems\":{\"degraded\":[],\"quarantined\":[]},\"integrationProblems\":[],\"network\":{\"controlPlane\":{\"surface\":\"controlPlane\",\"host\":\"127.0.0.1\",\"port\":3421,\"mode\":\"off\",\"scheme\":\"http\",\"trustProxy\":false,\"usingDefaultPaths\":false,\"ready\":true,\"errors\":[]},\"httpListener\":{\"surface\":\"httpListener\",\"host\":\"127.0.0.1\",\"port\":3422,\"mode\":\"off\",\"scheme\":\"http\",\"trustProxy\":false,\"usingDefaultPaths\":false,\"ready\":true,\"errors\":[]},\"outbound\":{\"mode\":\"bundled\",\"allowInsecureLocalhost\":false,\"customCaEntryCount\":0,\"effectiveCaStrategy\":\"bun-default\",\"errors\":[]}}}"
75
+ "detail": "{\"overall\":\"healthy\",\"degradedDomains\":[],\"providerProblems\":[],\"mcpProblems\":{\"degraded\":[],\"quarantined\":[]},\"integrationProblems\":[],\"network\":{\"controlPlane\":{\"surface\":\"controlPlane\",\"host\":\"0.0.0.0\",\"port\":3421,\"mode\":\"off\",\"scheme\":\"http\",\"trustProxy\":false,\"usingDefaultPaths\":false,\"ready\":true,\"errors\":[]},\"httpListener\":{\"surface\":\"httpListener\",\"host\":\"0.0.0.0\",\"port\":3422,\"mode\":\"off\",\"scheme\":\"http\",\"trustProxy\":false,\"usingDefaultPaths\":false,\"ready\":true,\"errors\":[]},\"outbound\":{\"mode\":\"bundled\",\"allowInsecureLocalhost\":false,\"customCaEntryCount\":0,\"effectiveCaStrategy\":\"bun-default\",\"errors\":[]}}}"
76
76
  },
77
77
  {
78
78
  "id": "openai-compatible-models",
79
79
  "title": "OpenAI-compatible /v1/models route",
80
80
  "status": "pass",
81
- "summary": "/v1/models returned 2 model(s).",
82
- "detail": "/v1/models returned 2 model(s); model identifiers omitted from release artifact."
81
+ "summary": "/v1/models returned 11 model(s).",
82
+ "detail": "/v1/models returned 11 model(s); model identifiers omitted from release artifact."
83
83
  },
84
84
  {
85
85
  "id": "agent-knowledge-status",
86
86
  "title": "Agent Knowledge isolated /status",
87
87
  "status": "pass",
88
88
  "summary": "Agent Knowledge status route returned parseable isolated JSON.",
89
- "detail": "{\"ready\":true,\"storagePath\":\"[home]/.goodvibes/goodvibes/knowledge-agent.sqlite\",\"sourceCount\":0,\"nodeCount\":0,\"edgeCount\":0,\"issueCount\":0,\"extractionCount\":0,\"jobRunCount\":0,\"refinementTaskCount\":0,\"usageCount\":0,\"candidateCount\":0,\"reportCount\":0,\"scheduleCount\":3,\"note\":\"Structured knowledge uses SQL-backed sources, nodes, edges, issues, extractions, and job runs. Markdown is an optional projection, not the source of truth.\"}"
89
+ "detail": "{\"ready\":true,\"storagePath\":\"[goodvibes-home]/tui/knowledge-agent.sqlite\",\"sourceCount\":0,\"nodeCount\":12,\"edgeCount\":0,\"issueCount\":0,\"extractionCount\":0,\"jobRunCount\":35,\"refinementTaskCount\":0,\"usageCount\":0,\"candidateCount\":0,\"reportCount\":2,\"scheduleCount\":3,\"note\":\"Structured knowledge uses SQL-backed sources, nodes, edges, issues, extractions, and job runs. Markdown is an optional projection, not the source of truth.\"}"
90
90
  },
91
91
  {
92
92
  "id": "agent-knowledge-ask-isolated",
@@ -114,7 +114,7 @@
114
114
  "title": "Agent Knowledge isolated nodes list",
115
115
  "status": "pass",
116
116
  "summary": "Agent Knowledge isolated nodes list stayed on the isolated Agent route.",
117
- "detail": "{\"nodes\":[]}"
117
+ "detail": "{\"nodes\":[{\"id\":\"node-38d4924f\",\"kind\":\"topic\",\"slug\":\"linked-to-26-graph-relation-s\",\"title\":\"linked to 26 graph relation(s)\",\"summary\":\"Topic tag linked to 26 graph relation(s).\",\"aliases\":[\"linked to 26 graph relation(s)\"],\"status\":\"active\",\"confidence\":70,\"metadata\":{\"tag\":\"linked to 26 graph relation(s)\",\"knowledgeSpaceId\":\"goodvibes-agent:default\",\"namespace\":\"goodvibes-agent:default\"},\"createdAt\":1780489632675,\"updatedAt\":1780489632928},{\"id\":\"node-4014fce2\",\"kind\":\"topic\",\"slug\":\"observed-via-2-usage-pattern-s\",\"title\":\"observed via 2 usage pattern(s)\",\"summary\":\"Topic tag observed via 2 usage pattern(s).\",\"aliases\":[\"observed via 2 usage pattern(s)\"],\"status\":\"active\",\"confidence\":70,\"metadata\":{\"tag\":\"observed via 2 usage pattern(s)\",\"knowledgeSpaceId\":\"goodvibes-agent:default\",\"namespace\":\"goodvibes-agent:default\"},\"createdAt\":1780489632666,\"updatedAt\":17804896... [truncated]"
118
118
  },
119
119
  {
120
120
  "id": "agent-knowledge-issues-isolated",
@@ -128,7 +128,7 @@
128
128
  "title": "Agent Knowledge isolated map",
129
129
  "status": "pass",
130
130
  "summary": "Agent Knowledge isolated map stayed on the isolated Agent route.",
131
- "detail": "{\"ok\":true,\"title\":\"Knowledge Map\",\"generatedAt\":1780551648464,\"width\":1280,\"height\":920,\"nodeCount\":0,\"edgeCount\":0,\"totalNodeCount\":0,\"totalEdgeCount\":0,\"facets\":{\"recordKinds\":[],\"nodeKinds\":[],\"sourceTypes\":[],\"sourceStatuses\":[],\"nodeStatuses\":[],\"issueCodes\":[],\"issueStatuses\":[],\"issueSeverities\":[],\"edgeRelations\":[],\"tags\":[]},\"nodes\":[],\"edges\":[],\"svg\":\"<svg xmlns=\\\"http://www.w3.org/2000/svg\\\" width=\\\"1280\\\" height=\\\"920\\\" viewBox=\\\"0 0 1280 920\\\" role=\\\"img\\\" aria-label=\\\"Knowledge Map\\\">\\n<defs>\\n <radialGradient id=\\\"knowledgeMapBg\\\" cx=\\\"50%\\\" cy=\\\"46%\\\" r=\\\"70%\\\">\\n <stop offset=\\\"0%\\\" stop-color=\\\"#f7f4ec\\\" />\\n <stop offset=\\\"60%\\\" stop-color=\\\"#e9eef0\\\" />\\n <stop offset=\\\"100%\\\" stop-color=\\\"#dde6df\\\" />\\n </radialGradient>\\n <filter id=\\\"softShadow\\\" x=\\\"-20%\\\" y=\\\"-20%\\\" width=\\\"140%\\\" height=\\\"140%\\\">\\n <feDropShadow dx=\\\"0\\\" dy=\\\"6\\... [truncated]"
131
+ "detail": "{\"ok\":true,\"title\":\"Knowledge Map\",\"generatedAt\":1780570932688,\"width\":1280,\"height\":920,\"nodeCount\":12,\"edgeCount\":0,\"totalNodeCount\":12,\"totalEdgeCount\":0,\"facets\":{\"recordKinds\":[{\"value\":\"node\",\"count\":12}],\"nodeKinds\":[{\"value\":\"topic\",\"count\":12}],\"sourceTypes\":[],\"sourceStatuses\":[],\"nodeStatuses\":[{\"value\":\"active\",\"count\":12}],\"issueCodes\":[],\"issueStatuses\":[],\"issueSeverities\":[],\"edgeRelations\":[],\"tags\":[]},\"nodes\":[{\"id\":\"node-d2a534ae\",\"recordKind\":\"node\",\"kind\":\"topic\",\"title\":\"linked to 19 graph relation(s)\",\"summary\":\"Topic tag linked to 19 graph relation(s).\",\"x\":720,\"y\":277,\"radius\":23,\"metadata\":{\"tag\":\"linked to 19 graph relation(s)\",\"knowledgeSpaceId\":\"goodvibes-agent:default\",\"namespace\":\"goodvibes-agent:default\"}},{\"id\":\"node-0cc2f686\",\"recordKind\":\"node\",\"kind\":\"topic\",\"title\":\"linked to 20 graph relation(s)\",\"summary\":\"Topic tag linked to 20 gra... [truncated]"
132
132
  },
133
133
  {
134
134
  "id": "agent-knowledge-connectors-isolated",
package/release/live-verification/live-verification.md CHANGED
@@ -1,9 +1,9 @@
1
1
  # GoodVibes Agent Live Verification
2
2
 
3
- Generated: 2026-06-04T05:40:48.465Z
3
+ Generated: 2026-06-04T11:02:12.690Z
4
4
  Home: `[goodvibes-home]`
5
5
  Binary: `[agent-binary]`
6
- Connected host: `http://127.0.0.1:37210`
6
+ Connected host: `http://127.0.0.1:3421`
7
7
 
8
8
  | Status | Count |
9
9
  |---|---:|
@@ -14,7 +14,7 @@ Connected host: `http://127.0.0.1:37210`
14
14
 
15
15
  | Check | Status | Summary |
16
16
  |---|---|---|
17
- | Verification inventory ledger | pass | 100% local verification signal across 613 inventory items. |
17
+ | Verification inventory ledger | pass | 100% local verification signal across 761 inventory items. |
18
18
  | Compiled GoodVibes Agent CLI binary | pass | Found [agent-binary]. |
19
19
  | Agent CLI version command | pass | Agent CLI version returned successfully. |
20
20
  | Agent CLI status JSON command | pass | Agent CLI status returned parseable JSON. |
@@ -24,7 +24,7 @@ Connected host: `http://127.0.0.1:37210`
24
24
  | CLI doctor command | pass | Doctor completed without findings. |
25
25
  | Authenticated connected-host /status | pass | /status returned 200, version 0.33.36. |
26
26
  | Authenticated connected-host /api/health | pass | Health overall=healthy. |
27
- | OpenAI-compatible /v1/models route | pass | /v1/models returned 2 model(s). |
27
+ | OpenAI-compatible /v1/models route | pass | /v1/models returned 11 model(s). |
28
28
  | Agent Knowledge isolated /status | pass | Agent Knowledge status route returned parseable isolated JSON. |
29
29
  | Agent Knowledge isolated ask | pass | Agent Knowledge ask stayed on the isolated Agent route. |
30
30
  | Agent Knowledge isolated search | pass | Agent Knowledge search stayed on the isolated Agent route. |
@@ -39,13 +39,13 @@ Connected host: `http://127.0.0.1:37210`
39
39
  ### Verification inventory ledger
40
40
 
41
41
  ```text
42
- 84.5% local behavior verified; 95 item(s) require external outcomes.
42
+ 87.4% local behavior verified; 96 item(s) require external outcomes.
43
43
  ```
44
44
 
45
45
  ### Agent CLI version command
46
46
 
47
47
  ```text
48
- goodvibes-agent 1.0.33
48
+ goodvibes-agent 1.0.35
49
49
  ```
50
50
 
51
51
  ### Agent CLI status JSON command
@@ -59,10 +59,10 @@ Status JSON command completed; provider/model identifiers omitted from release a
59
59
  ```text
60
60
  {
61
61
  "ok": true,
62
- "packageVersion": "1.0.33",
62
+ "packageVersion": "1.0.35",
63
63
  "sdkPin": "0.33.36",
64
64
  "connectedHost": {
65
- "baseUrl": "http://127.0.0.1:37210",
65
+ "baseUrl": "http://127.0.0.1:3421",
66
66
  "status": 200,
67
67
  "version": "0.33.36",
68
68
  "reachable": true,
@@ -89,17 +89,17 @@ Status JSON command completed; provider/model identifiers omitted from release a
89
89
  "route": "/api/goodvibes-agent/knowledge/status",
90
90
  "data": {
91
91
  "ready": true,
92
- "storagePath": "[home]/.goodvibes/goodvibes/knowledge-agent.sqlite",
92
+ "storagePath": "[goodvibes-home]/tui/knowledge-agent.sqlite",
93
93
  "sourceCount": 0,
94
- "nodeCount": 0,
94
+ "nodeCount": 12,
95
95
  "edgeCount": 0,
96
96
  "issueCount": 0,
97
97
  "extractionCount": 0,
98
- "jobRunCount": 0,
98
+ "jobRunCount": 35,
99
99
  "refinementTaskCount": 0,
100
100
  "usageCount": 0,
101
101
  "candidateCount": 0,
102
- "reportCount": 0,
102
+ "reportCount": 2,
103
103
  "scheduleCount": 3,
104
104
  "note": "Structured knowledge uses SQL-backed sources, nodes, edges, issues, extractions, and job runs. Markdown is an optional projection, not the source of truth."
105
105
  }
@@ -127,19 +127,19 @@ Doctor command completed without findings; provider/model identifiers and creden
127
127
  ### Authenticated connected-host /api/health
128
128
 
129
129
  ```text
130
- {"overall":"healthy","degradedDomains":[],"providerProblems":[],"mcpProblems":{"degraded":[],"quarantined":[]},"integrationProblems":[],"network":{"controlPlane":{"surface":"controlPlane","host":"127.0.0.1","port":3421,"mode":"off","scheme":"http","trustProxy":false,"usingDefaultPaths":false,"ready":true,"errors":[]},"httpListener":{"surface":"httpListener","host":"127.0.0.1","port":3422,"mode":"off","scheme":"http","trustProxy":false,"usingDefaultPaths":false,"ready":true,"errors":[]},"outbound":{"mode":"bundled","allowInsecureLocalhost":false,"customCaEntryCount":0,"effectiveCaStrategy":"bun-default","errors":[]}}}
130
+ {"overall":"healthy","degradedDomains":[],"providerProblems":[],"mcpProblems":{"degraded":[],"quarantined":[]},"integrationProblems":[],"network":{"controlPlane":{"surface":"controlPlane","host":"0.0.0.0","port":3421,"mode":"off","scheme":"http","trustProxy":false,"usingDefaultPaths":false,"ready":true,"errors":[]},"httpListener":{"surface":"httpListener","host":"0.0.0.0","port":3422,"mode":"off","scheme":"http","trustProxy":false,"usingDefaultPaths":false,"ready":true,"errors":[]},"outbound":{"mode":"bundled","allowInsecureLocalhost":false,"customCaEntryCount":0,"effectiveCaStrategy":"bun-default","errors":[]}}}
131
131
  ```
132
132
 
133
133
  ### OpenAI-compatible /v1/models route
134
134
 
135
135
  ```text
136
- /v1/models returned 2 model(s); model identifiers omitted from release artifact.
136
+ /v1/models returned 11 model(s); model identifiers omitted from release artifact.
137
137
  ```
138
138
 
139
139
  ### Agent Knowledge isolated /status
140
140
 
141
141
  ```text
142
- {"ready":true,"storagePath":"[home]/.goodvibes/goodvibes/knowledge-agent.sqlite","sourceCount":0,"nodeCount":0,"edgeCount":0,"issueCount":0,"extractionCount":0,"jobRunCount":0,"refinementTaskCount":0,"usageCount":0,"candidateCount":0,"reportCount":0,"scheduleCount":3,"note":"Structured knowledge uses SQL-backed sources, nodes, edges, issues, extractions, and job runs. Markdown is an optional projection, not the source of truth."}
142
+ {"ready":true,"storagePath":"[goodvibes-home]/tui/knowledge-agent.sqlite","sourceCount":0,"nodeCount":12,"edgeCount":0,"issueCount":0,"extractionCount":0,"jobRunCount":35,"refinementTaskCount":0,"usageCount":0,"candidateCount":0,"reportCount":2,"scheduleCount":3,"note":"Structured knowledge uses SQL-backed sources, nodes, edges, issues, extractions, and job runs. Markdown is an optional projection, not the source of truth."}
143
143
  ```
144
144
 
145
145
  ### Agent Knowledge isolated ask
@@ -163,7 +163,7 @@ Doctor command completed without findings; provider/model identifiers and creden
163
163
  ### Agent Knowledge isolated nodes list
164
164
 
165
165
  ```text
166
- {"nodes":[]}
166
+ {"nodes":[{"id":"node-38d4924f","kind":"topic","slug":"linked-to-26-graph-relation-s","title":"linked to 26 graph relation(s)","summary":"Topic tag linked to 26 graph relation(s).","aliases":["linked to 26 graph relation(s)"],"status":"active","confidence":70,"metadata":{"tag":"linked to 26 graph relation(s)","knowledgeSpaceId":"goodvibes-agent:default","namespace":"goodvibes-agent:default"},"createdAt":1780489632675,"updatedAt":1780489632928},{"id":"node-4014fce2","kind":"topic","slug":"observed-via-2-usage-pattern-s","title":"observed via 2 usage pattern(s)","summary":"Topic tag observed via 2 usage pattern(s).","aliases":["observed via 2 usage pattern(s)"],"status":"active","confidence":70,"metadata":{"tag":"observed via 2 usage pattern(s)","knowledgeSpaceId":"goodvibes-agent:default","namespace":"goodvibes-agent:default"},"createdAt":1780489632666,"updatedAt":17804896... [truncated]
167
167
  ```
168
168
 
169
169
  ### Agent Knowledge isolated issues list
@@ -175,7 +175,7 @@ Doctor command completed without findings; provider/model identifiers and creden
175
175
  ### Agent Knowledge isolated map
176
176
 
177
177
  ```text
178
- {"ok":true,"title":"Knowledge Map","generatedAt":1780551648464,"width":1280,"height":920,"nodeCount":0,"edgeCount":0,"totalNodeCount":0,"totalEdgeCount":0,"facets":{"recordKinds":[],"nodeKinds":[],"sourceTypes":[],"sourceStatuses":[],"nodeStatuses":[],"issueCodes":[],"issueStatuses":[],"issueSeverities":[],"edgeRelations":[],"tags":[]},"nodes":[],"edges":[],"svg":"<svg xmlns=\"http://www.w3.org/2000/svg\" width=\"1280\" height=\"920\" viewBox=\"0 0 1280 920\" role=\"img\" aria-label=\"Knowledge Map\">\n<defs>\n <radialGradient id=\"knowledgeMapBg\" cx=\"50%\" cy=\"46%\" r=\"70%\">\n <stop offset=\"0%\" stop-color=\"#f7f4ec\" />\n <stop offset=\"60%\" stop-color=\"#e9eef0\" />\n <stop offset=\"100%\" stop-color=\"#dde6df\" />\n </radialGradient>\n <filter id=\"softShadow\" x=\"-20%\" y=\"-20%\" width=\"140%\" height=\"140%\">\n <feDropShadow dx=\"0\" dy=\"6\... [truncated]
178
+ {"ok":true,"title":"Knowledge Map","generatedAt":1780570932688,"width":1280,"height":920,"nodeCount":12,"edgeCount":0,"totalNodeCount":12,"totalEdgeCount":0,"facets":{"recordKinds":[{"value":"node","count":12}],"nodeKinds":[{"value":"topic","count":12}],"sourceTypes":[],"sourceStatuses":[],"nodeStatuses":[{"value":"active","count":12}],"issueCodes":[],"issueStatuses":[],"issueSeverities":[],"edgeRelations":[],"tags":[]},"nodes":[{"id":"node-d2a534ae","recordKind":"node","kind":"topic","title":"linked to 19 graph relation(s)","summary":"Topic tag linked to 19 graph relation(s).","x":720,"y":277,"radius":23,"metadata":{"tag":"linked to 19 graph relation(s)","knowledgeSpaceId":"goodvibes-agent:default","namespace":"goodvibes-agent:default"}},{"id":"node-0cc2f686","recordKind":"node","kind":"topic","title":"linked to 20 graph relation(s)","summary":"Topic tag linked to 20 gra... [truncated]
179
179
  ```
180
180
 
181
181
  ### Agent Knowledge isolated connectors list
package/release/release-notes.md CHANGED
@@ -4,11 +4,11 @@
4
4
  - Completed connected-host operator integration without taking host lifecycle ownership: compatibility/status checks, authenticated health and model routes, channel readiness, provider-account posture, approvals, automation snapshots, schedules, work plans, media/voice readiness, pairing, and explicit public-route diagnostics are all visible from Agent.
5
5
  - Completed explicit side-effect boundaries for personal operation: channel sends, notifications, routine schedule promotion, reminders, subscription/auth actions, memory bundle imports/exports, support bundles, MCP configuration, profile changes, and build delegation require explicit confirmation where they mutate state or call external routes.
6
6
  - Completed package and release hardening for the release gate: Bun-only install/run instructions, package-facing text verification, package runtime bundling, packed global install smoke, blocked lifecycle command smoke, source/package boundary checks, architecture checks, recorded performance snapshot checks, verification ledger, strict live verification artifacts, and release-quality readiness inventory dimensions are now part of the validated release path.
7
- - Completed the compact model-visible harness pass: `agent_harness` summary and plural catalogs now default to compact rows, with full schemas, policy blocks, route metadata, editor fields, release artifact detail, redacted log tail, and parameter detail behind `includeParameters:true` or singular inspect modes.
7
+ - Completed the compact model-visible harness pass: `agent_harness` summary and plural catalogs now default to compact rows, `mode:"modes"` searches every harness mode by task/id/effect/parameter, and `mode:"mode"` inspects one mode contract with full schemas, policy blocks, route metadata, editor fields, release artifact detail, redacted log tail, and parameter detail behind `includeParameters:true` or singular inspect modes.
8
8
  - Completed direct model access to user-facing harness operations: workspace actions, slash commands, settings, panels, UI surfaces, keybindings, tool catalogs, channel/notification posture, provider/account posture, MCP posture, setup, model routing, pairing, delegation, security/support bundles, media, sessions, operator methods, release evidence, and connected-host diagnostics are all exposed through Agent tools or harness modes.
9
9
  - Completed connected-host daemon aliases for the model: `daemon` maps to connected-host posture and `daemon_status` maps to live connected-host status while lifecycle control stays outside Agent.
10
10
  - Completed settings parity for the model-facing harness: settings discovery is compact by default, `get_setting` and `includeParameters:true` expose full descriptors, and `set_setting`/`reset_setting` use the same config/secret managers with confirmation and external-host setting locks.
11
- - Completed the tool-description verbosity sweep: first-class Agent tools and wrapped built-in tool definitions now register concise descriptions, while detailed safety rules remain enforced in policy wrappers, confirmation errors, and detailed harness inspection.
11
+ - Completed the tool-description verbosity sweep: first-class Agent tools and wrapped built-in tool definitions now register concise descriptions, nested parameter schema descriptions are stripped from the default model-visible catalog, and detailed safety rules remain enforced in policy wrappers, confirmation errors, and detailed harness inspection.
12
12
  - Completed copyable model route hint cleanup: confirmed harness examples now include the required `confirm:true` and `explicitUserRequest` fields so route hints match the actual execution contract.
13
13
  - Completed resilient shortcut/keybinding discovery: `agent_harness` returns fixed shortcuts and default-fallback keybinding descriptors when the live keybinding manager is absent, while keybinding execution and mutation still fail closed until the runtime manager is available.
14
14
  - Completed the model-visible operator method catalog: `agent_harness` can now list and inspect allowlisted public operator and Agent Knowledge methods with their owning first-class model tools, confirmation policy, and boundaries, without exposing arbitrary route invocation.