@pellux/goodvibes-agent 1.0.35 → 1.0.36

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 Product-facing release notes for GoodVibes Agent.
 
+## 1.0.36 - 2026-06-04
+
+- Workspace navigation now uses distinct category group names instead of repeated setup headings.
+- Onboarding now owns the full terminal viewport and blocks composer-adjacent overlays while setup is active.
+- Onboarding renderer coverage now guards the bottom row so the setup flow cannot leave the input area visually available.
+
 ## 1.0.35 - 2026-06-04
 
 - Added searchable `agent_harness` mode discovery: `mode:"modes"` searches every harness mode by task, family, effect type, id, alias, and parameter name, while `mode:"mode"` inspects one mode contract.
@@ -20,7 +26,7 @@ Product-facing release notes for GoodVibes Agent.
 - 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.
 - 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.
 - 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.
-- 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.
+- Completed direct model access to Agent 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, and connected-host diagnostics are exposed through Agent tools or harness modes; packaged release evidence remains model-inspectable as operator/audit material.
 - 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.
 - 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.
 - 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.
@@ -30,17 +36,17 @@ Product-facing release notes for GoodVibes Agent.
 - Expanded first-class Agent Knowledge reads: `agent_knowledge` now covers status, ask, search, source/node/issue lists, item lookup, map summary, connector list/detail, and connector doctor while staying inside `/api/goodvibes-agent/knowledge/*`.
 - Added fail-closed Agent Knowledge response-scope validation: CLI, model tools, and live verification reject successful-looking payloads that expose default scope metadata or known non-Agent payload markers.
 - Expanded release-route enforcement for Agent Knowledge: architecture/package policy now guards the full route catalog, and live verification definitions include source, node, issue, map, and connector read routes in addition to status, ask, and search.
-- Pinned the release line to `@pellux/goodvibes-sdk@0.33.36` so the packaged connected-host runtime includes Agent Knowledge alias scope normalization and telephony channel surface support.
+- Verified the release line against connected-host public Agent routes for Agent Knowledge alias scope normalization and telephony channel surface support.
 - Renamed active release evidence artifacts to current-release paths under `release/`, including release notes, readiness inventory, performance snapshot, and live-verification reports, so current release metadata no longer depends on stale historical filenames.
 
 ## 1.0.33 - 2026-06-04
 
-- Fixed the release lockfile so frozen CI installs resolve @pellux/goodvibes-sdk@0.33.36 and its published peer packages.
+- Fixed the release lockfile so frozen CI installs resolve the published connected-host route dependency graph.
 - Carries forward the 1.0.32 model-facing harness coverage, compact tool catalog, keybinding discovery fallback, and connected-host release evidence.
 
 ## 1.0.32 - 2026-06-04
 
-- Pin the Agent release line to `@pellux/goodvibes-sdk@0.33.36` so the packaged connected-host runtime includes Agent Knowledge alias scope normalization and telephony channel surface support.
+- Align the Agent release line with connected-host public route support for Agent Knowledge alias scope normalization and telephony channel surface support.
 - Refresh release readiness evidence to match the current strict live verification run: 19 pass, 0 warn, 0 fail, 0 skip.
 - Treat environment-provisioned connected-host operator tokens as first-class status, doctor, auth, pairing, Agent Knowledge, and model-visible connected-host credentials.
 - Expose channel readiness through `agent_harness` with summary/search and single-channel lookup so the model can inspect setup state, delivery posture, risk labels, and safe config-key names before using the explicit confirmed send tool.
@@ -89,7 +95,7 @@ Product-facing release notes for GoodVibes Agent.
 ## 1.0.28 - 2026-06-03
 
 - Expose modelExecution metadata for every Agent workspace editor action, including local-registry, command-backed, direct local-create, profile, and prompt-returning editor flows.
-- Return editor execution-route metadata in workspace action handoffs so the model can complete forms without guessing the bridge.
+- Return editor execution-route metadata in workspace action handoffs so the model can complete forms without guessing the route.
 - Refresh 1.0.x package docs and focused harness coverage for workspace editor execution parity.
 
 ## 1.0.27 - 2026-06-03
@@ -100,7 +106,7 @@ Product-facing release notes for GoodVibes Agent.
 
 ## 1.0.26 - 2026-06-03
 
-- Route confirmed agent_harness panel-close and panel-close-all keybinding runs through the same Agent workspace dismiss bridge as the user shortcut before falling back to legacy panels.
+- Route confirmed agent_harness panel-close and panel-close-all keybinding runs through the same Agent workspace dismiss route as the user shortcut before falling back to panel close handling.
 - Refresh model-operation metadata for panel close keybindings so supported keybinding behavior matches visible shell behavior.
 - Add focused harness coverage for model-triggered Agent workspace dismissal.
 
@@ -205,7 +211,7 @@ Product-facing release notes for GoodVibes Agent.
 ## 1.0.8 - 2026-06-03
 
 - Added model-visible UI surface entries for the panel-picker compatibility route and the security, knowledge, and subscription operator surfaces.
-- Routed those named operator surfaces through Agent Workspace or the existing panel bridge with confirmation.
+- Routed those named operator surfaces through Agent Workspace or the existing panel route with confirmation.
 - Updated package-facing docs and focused harness coverage so the documented 1.0.x model-visible surface map matches the TUI routes.
 
 ## 1.0.7 - 2026-06-03
@@ -215,7 +221,7 @@ Product-facing release notes for GoodVibes Agent.
 
 ## 1.0.6 - 2026-06-03
 
-- Added agent_harness mode connected_host_status for live read-only connected-host readiness: status-route reachability, SDK compatibility, token posture, endpoint bindings, Agent Knowledge route readiness, findings, and lifecycle boundaries.
+- Added agent_harness mode connected_host_status for live read-only connected-host readiness: status-route reachability, host compatibility, token posture, endpoint bindings, Agent Knowledge route readiness, findings, and lifecycle boundaries.
 - Documented the new model-visible connected-host readiness surface and added focused harness coverage proving the raw operator token is not exposed.
 
 ## 1.0.5 - 2026-06-03
@@ -233,7 +239,7 @@ Product-facing release notes for GoodVibes Agent.
 ## 1.0.3 - 2026-06-03
 
 - Model-visible harness discovery now includes top-level CLI mirrors with parser output, blocked command tokens, redacted launch overrides, and preferred in-process routes.
-- Model-visible harness discovery now includes built-in panel catalog/open-state inspection plus confirmation-gated visible panel routing through the Agent shell bridge.
+- Model-visible harness discovery now includes built-in panel catalog/open-state inspection plus confirmation-gated visible panel routing through the Agent operator surface.
 - Harness metadata was split into focused catalog helpers to keep architecture boundaries and source-size limits intact.
 - Documentation now describes CLI mirror and panel harness visibility, including the no-hidden-CLI-process and connected-host boundary rules.
 

package/README.md

@@ -65,9 +65,9 @@ Press `/` inside the workspace to search actions by name, category, command, or
 
 ## Model-Visible Harness
 
-The main Agent model can inspect and operate the same user-facing harness through Agent-owned tools. The important entrypoint is `agent_harness`.
+The main Agent model can inspect and operate the Agent-controlled harness through Agent-owned tools. The important entrypoint is `agent_harness`.
 
-`agent_harness mode:"summary"` is compact by default. It returns counts, status, and a short mode guide. `mode:"modes"` searches every harness mode by task, family, effect type, id, alias, or parameter name; `mode:"mode"` inspects one mode contract. Plural catalog modes are also compact by default: they return ids, labels, counts, safe state, and route hints. Use `includeParameters:true` or a singular inspect mode when the model needs schemas, detailed route hints, full policy blocks, redacted log tail, release artifact data, or editor field definitions.
+`agent_harness mode:"summary"` is compact by default. It returns counts, status, and a short mode guide. `mode:"modes"` searches every harness mode by task, family, effect type, id, alias, or parameter name; `mode:"mode"` inspects one mode contract. Plural catalog modes are also compact by default: they return ids, labels, counts, safe state, effect class, and short route hints. `workspace_actions`, `commands`, `cli_commands`, `panels`, `ui_surfaces`, `shortcuts`, `keybindings`, `tools`, `settings`, connected-host posture/status/capability, and operator/audit rows include compact `modelRoute` or `modelAccess` hints so the model can choose the right first-class tool or confirmed harness route without expanding every row. Use `includeParameters:true` or a singular inspect mode when the model needs schemas, detailed route hints, full policy blocks, redacted log tail, operator/audit artifact data, or editor field definitions.
 
 High-value `agent_harness` mode groups:
 
@@ -76,7 +76,7 @@ High-value `agent_harness` mode groups:
 - User-visible effects: `run_workspace_action`, `run_command`, `open_panel`, `open_ui_surface`, `run_keybinding`, `set_keybinding`, `reset_keybinding`, `set_setting`, `reset_setting`.
 - Product posture: `channels`, `notifications`, `provider_accounts`, `mcp_servers`, `setup_posture`, `model_routing`, `pairing_posture`, `delegation_posture`, `security_posture`, `support_bundles`, `media_posture`, `sessions`.
 - Connected host: `service_posture`, `service_endpoint`, `connected_host`, `connected_host_status`, `connected_host_capability`; `daemon` and `daemon_status` are aliases for connected-host posture/status.
-- Release evidence: `release_evidence`, `release_evidence_artifact`, `release_readiness`, `release_readiness_item`.
+- Operator/audit inspection: `release_evidence`, `release_evidence_artifact`, `release_readiness`, `release_readiness_item`.
 - Operator methods: `operator_methods`, `operator_method`.
 
 Every mutating or externally visible effect requires `confirm:true` plus `explicitUserRequest` unless a narrower first-class tool has its own confirmation contract. Ambiguous lookups return candidates instead of guessing.
@@ -89,7 +89,7 @@ First-class model tools cover common workflows directly:
 - `agent_operator_briefing` and `agent_operator_action` for connected work/approval/automation/schedule posture and exact confirmed actions.
 - `agent_channel_send`, `agent_notify`, `agent_reminder_schedule`, and `agent_media_generate` for confirmed delivery, notification, reminder, and media generation.
 
-Registered model tool definitions are compact by default. Top-level descriptions are short, and nested parameter descriptions are omitted from the default model catalog. The model can inspect detailed contracts through `agent_harness mode:"tools"` with `includeParameters:true`, `mode:"tool"`, or the owning harness mode.
+Registered model tool definitions are compact by default. Top-level descriptions are short, nested parameter descriptions are omitted from the default model catalog, and tool catalog rows include direct harness inspection routes. The model can inspect detailed contracts through `agent_harness mode:"tools"` with `includeParameters:true`, `mode:"tool"`, or the owning harness mode.
 
 ## Local Behavior
 
@@ -116,7 +116,7 @@ Agent Knowledge is its own product segment. Agent uses only:
 
 Agent does not fall back to default knowledge or other product-specific knowledge routes. Successful connected-host responses are checked for scope contamination before rendering.
 
-The Knowledge workspace and model tools support status, ask/search, source/node/issue lists, item lookup, map review, connector inspection, URL/file/URL-list/bookmark/browser-history/connector ingest, review queue, and reindex.
+The Knowledge workspace and model tools support status, ask/search, source/node/issue lists, item lookup, map review, connector inspection, URL/file/URL-list/bookmark/browser-history/connector ingest, issue review, prompt packet/explain previews, consolidation, review queue, and reindex.
 
 Artifacts are first-class runtime objects for uploaded files, generated media, and delegated outputs. Generated media is stored as GoodVibes artifacts and reported by artifact id and metadata, not inline base64.
 
@@ -135,8 +135,8 @@ Agent reports unavailable, unauthenticated, or incompatible host state from Agen
 Model-visible diagnostics are read-only:
 
 - `service_posture` and `service_endpoint` expose endpoint binding, network-facing posture, issues, optional probes, and redacted log tail.
-- `connected_host` and `daemon` are compact posture maps by default; `includeParameters:true` adds route families, allowed capabilities, blocked lifecycle/non-Agent surfaces, and first-class tool availability. `connected_host_capability` inspects one capability.
-- `connected_host_status` and `daemon_status` run live readiness checks for host status, SDK compatibility, token posture, endpoint binding, and isolated Agent Knowledge readiness.
+- `connected_host` and `daemon` are compact posture maps by default with direct `modelRoute` hints; `includeParameters:true` adds route families, allowed capabilities, blocked lifecycle/non-Agent surfaces, and first-class tool availability. `connected_host_capability` inspects one capability and returns the matching allowed or blocked route hint.
+- `connected_host_status` and `daemon_status` run live readiness checks for host status, host compatibility, token posture, endpoint binding, isolated Agent Knowledge readiness, and the model route to inspect or act on findings.
 
 Host lifecycle stays outside GoodVibes Agent.
 
@@ -148,6 +148,7 @@ GoodVibes TUI owns coding execution: file edits, git/worktree workflows, coding
 
 ## Package Docs
 
+- [Docs Index](docs/README.md)
 - [Getting Started](docs/getting-started.md)
 - [Connected Host](docs/connected-host.md)
 - [Knowledge, Artifacts, and Multimodal](docs/knowledge-artifacts-and-multimodal.md)