ateam-mcp

Previous value: -"Example type: 'skill' = Order Support Agent, 'connector' = stdio MCP connector, 'connector-ui' = UI-capable connector, 'solution' = full 3-skill e-commerce solution, 'script-cache-skill' = fat-tool skill with script_cache opt-in (reference implementation of script-level JIT shortcuts — study this before building any browser-automation skill), 'ui-plugin-native' = complete working React Native (mobile) UI plugin (rn-src/index.tsx + esbuild build:rn → rn-bundle, @adas/plugin-sdk, es2015), 'index' = list all available examples"New value: +"Example type: 'skill' = Order Support Agent, 'connector' = stdio MCP connector, 'connector-ui' = UI-capable connector, 'solution' = full 3-skill e-commerce solution, 'script-cache-skill' = fat-tool skill with script_cache opt-in (reference implementation of script-level JIT shortcuts — study this before building any browser-automation skill), 'ui-plugin-native' = complete working React Native (mobile) UI plugin (rn-src/index.tsx + esbuild build:rn → rn-bundle, @adas/plugin-sdk, es2015), 'ui-plugin-iframe' = complete working web (iframe) UI plugin with the postMessage protocol, 'device-tools' = a solution's OWN tools that execute ON THE PHONE (runtime:\"device\") — BOTH halves and why they must agree: the plugin-bundle implementation, the connector manifest that declares it (Core cannot introspect a phone, so the manifest is the entire contract), and the skill wiring without which the skill gets none of them. Read this before designing anything that needs a LIVE device reading rather than the last synced one, 'index' = list all available examples"

Previous value: -[
-  "skill",
-  "connector",
-  "connector-ui",
-  "solution",
-  "script-cache-skill",
-  "ui-plugin-native",
-  "index"
-]New value: +[
+  "skill",
+  "connector",
+  "connector-ui",
+  "solution",
+  "script-cache-skill",
+  "ui-plugin-native",
+  "ui-plugin-iframe",
+  "device-tools",
+  "index"
+]

Previous value: -"What to fetch: 'capabilities' = START HERE IF YOU ARE NEW — the capability index, organised by what a solution DOES rather than by our build artifacts: can I see what the user sees? talk with them out loud? know where they are and that they are moving? act while they sleep? remember each user? show them something? Each question gets a one-word answer (yes / yes-with-gaps / not yet / unknown) and the topics to read next. Every other topic below is named after an ARTIFACT, so if you do not already know our vocabulary this is the only door you can find by thinking about your own problem. 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory. 'ui-plugins' = the DEEP React Native (mobile) plugin build guide: author in rn-src/, compile with a build:rn esbuild script (format=cjs, target=es2015, external react/react-native/@adas/plugin-sdk) to rn-bundle/index.bundle.js, plain-object export — read this before authoring any MOBILE widget. 'device-capabilities' = THE DEVICE CAPABILITY MATRIX, GENERATED from the mobile SDK's own artefacts and stamped with their hashes: every native.* API (mechanical one-shot verbs), every deviceState.* domain (semantic state a reasoning loop reads, with freshness + confidence) and every server-called device.* tool, each with status (done / partial / shape-only / missing) and what is left. READ THIS before concluding the phone cannot do something — camera, video, scanning, vision, sensors, location, on-device storage. Absence from any other spec topic is NOT evidence. 'monitoring' = THE MONITORING CONTRACT: which tools are safe to call in a poll loop (with cost / poll interval / whether output stays bounded as the run grows), which are not and what to use instead, plus the running ateam-mcp version. Read this BEFORE writing any loop that watches a build — the safe poll is ateam_chain_status, never ateam_get_chain."New value: +"What to fetch: 'realizations' = HOW to build a capability: for each one the valid physical routes with use_when / do_not_use_when / execution / freshness, so device-dependent design picks a route deliberately instead of by accident. 'capabilities' = START HERE IF YOU ARE NEW — the capability index, organised by what a solution DOES rather than by our build artifacts: can I see what the user sees? talk with them out loud? know where they are and that they are moving? act while they sleep? remember each user? show them something? Each question gets a one-word answer (yes / yes-with-gaps / not yet / unknown) and the topics to read next. Every other topic below is named after an ARTIFACT, so if you do not already know our vocabulary this is the only door you can find by thinking about your own problem. 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory. 'ui-plugins' = the DEEP React Native (mobile) plugin build guide: author in rn-src/, compile with a build:rn esbuild script (format=cjs, target=es2015, external react/react-native/@adas/plugin-sdk) to rn-bundle/index.bundle.js, plain-object export — read this before authoring any MOBILE widget. 'device-capabilities' = THE DEVICE CAPABILITY MATRIX, GENERATED from the mobile SDK's own artefacts and stamped with their hashes: every native.* API (mechanical one-shot verbs), every deviceState.* domain (semantic state a reasoning loop reads, with freshness + confidence) and every server-called device.* tool, each with status (done / partial / shape-only / missing) and what is left. READ THIS before concluding the phone cannot do something — camera, video, scanning, vision, sensors, location, on-device storage. Absence from any other spec topic is NOT evidence. 'monitoring' = THE MONITORING CONTRACT: which tools are safe to call in a poll loop (with cost / poll interval / whether output stays bounded as the run grows), which are not and what to use instead, plus the running ateam-mcp version. Read this BEFORE writing any loop that watches a build — the safe poll is ateam_chain_status, never ateam_get_chain."

Previous value: -[
-  "capabilities",
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user",
-  "python_helpers",
-  "widgets",
-  "ui-plugins",
-  "actor-storage",
-  "voice",
-  "voice-native",
-  "triggers",
-  "sub-agent",
-  "consumer-roles",
-  "mobile-connector",
-  "device-capabilities",
-  "monitoring"
-]New value: +[
+  "capabilities",
+  "realizations",
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers",
+  "widgets",
+  "ui-plugins",
+  "actor-storage",
+  "voice",
+  "voice-native",
+  "triggers",
+  "sub-agent",
+  "consumer-roles",
+  "mobile-connector",
+  "device-capabilities",
+  "monitoring"
+]

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory. 'ui-plugins' = the DEEP React Native (mobile) plugin build guide: author in rn-src/, compile with a build:rn esbuild script (format=cjs, target=es2015, external react/react-native/@adas/plugin-sdk) to rn-bundle/index.bundle.js, plain-object export — read this before authoring any MOBILE widget. 'monitoring' = THE MONITORING CONTRACT: which tools are safe to call in a poll loop (with cost / poll interval / whether output stays bounded as the run grows), which are not and what to use instead, plus the running ateam-mcp version. Read this BEFORE writing any loop that watches a build — the safe poll is ateam_chain_status, never ateam_get_chain."New value: +"What to fetch: 'capabilities' = START HERE IF YOU ARE NEW — the capability index, organised by what a solution DOES rather than by our build artifacts: can I see what the user sees? talk with them out loud? know where they are and that they are moving? act while they sleep? remember each user? show them something? Each question gets a one-word answer (yes / yes-with-gaps / not yet / unknown) and the topics to read next. Every other topic below is named after an ARTIFACT, so if you do not already know our vocabulary this is the only door you can find by thinking about your own problem. 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory. 'ui-plugins' = the DEEP React Native (mobile) plugin build guide: author in rn-src/, compile with a build:rn esbuild script (format=cjs, target=es2015, external react/react-native/@adas/plugin-sdk) to rn-bundle/index.bundle.js, plain-object export — read this before authoring any MOBILE widget. 'device-capabilities' = THE DEVICE CAPABILITY MATRIX, GENERATED from the mobile SDK's own artefacts and stamped with their hashes: every native.* API (mechanical one-shot verbs), every deviceState.* domain (semantic state a reasoning loop reads, with freshness + confidence) and every server-called device.* tool, each with status (done / partial / shape-only / missing) and what is left. READ THIS before concluding the phone cannot do something — camera, video, scanning, vision, sensors, location, on-device storage. Absence from any other spec topic is NOT evidence. 'monitoring' = THE MONITORING CONTRACT: which tools are safe to call in a poll loop (with cost / poll interval / whether output stays bounded as the run grows), which are not and what to use instead, plus the running ateam-mcp version. Read this BEFORE writing any loop that watches a build — the safe poll is ateam_chain_status, never ateam_get_chain."

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user",
-  "python_helpers",
-  "widgets",
-  "ui-plugins",
-  "actor-storage",
-  "voice",
-  "voice-native",
-  "triggers",
-  "sub-agent",
-  "consumer-roles",
-  "mobile-connector",
-  "monitoring"
-]New value: +[
+  "capabilities",
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers",
+  "widgets",
+  "ui-plugins",
+  "actor-storage",
+  "voice",
+  "voice-native",
+  "triggers",
+  "sub-agent",
+  "consumer-roles",
+  "mobile-connector",
+  "device-capabilities",
+  "monitoring"
+]

Added value: +{
+  "description": "Optional. WHO is asking. A job belongs to an actor and Core enforces that on per-job reads, so a tenant key alone is refused. Usually unnecessary — the session remembers the actor from ateam_conversation/ateam_test_skill. Pass it to inspect a job run by a DIFFERENT actor (e.g. a real user's).",
+  "type": "string"
+}

Added value: +{
+  "description": "Alias for chain_id — any job in the chain resolves to the chain aggregate. The handler has always accepted it; without this declaration MCP stripped it before the handler could see it.",
+  "type": "string"
+}

Added value: +{
+  "description": "Optional. WHO is asking. A job belongs to an actor and Core enforces that on per-job reads, so a tenant key alone is refused. Usually unnecessary — the session remembers the actor from ateam_conversation/ateam_test_skill. Pass it to inspect a job run by a DIFFERENT actor (e.g. a real user's).",
+  "type": "string"
+}

Added value: +{
+  "description": "THE EXECUTION'S IDENTITY — what ateam_conversation returns and what you actually hold. A chain is the whole run: root job + every handoff + every askAnySkill subcall. Prefer this.",
+  "type": "string"
+}

Previous value: -"The root job ID of the chain to inspect (or any job inside the chain — Core walks up to the root)."New value: +"Alias for chain_id. Any job inside the chain works — Core walks up to the root — but you rarely hold one; prefer chain_id."

Previous value: -[
-  "job_id"
-]New value: +[]

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory. 'ui-plugins' = the DEEP React Native (mobile) plugin build guide: author in rn-src/, compile with a build:rn esbuild script (format=cjs, target=es2015, external react/react-native/@adas/plugin-sdk) to rn-bundle/index.bundle.js, plain-object export — read this before authoring any MOBILE widget."New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory. 'ui-plugins' = the DEEP React Native (mobile) plugin build guide: author in rn-src/, compile with a build:rn esbuild script (format=cjs, target=es2015, external react/react-native/@adas/plugin-sdk) to rn-bundle/index.bundle.js, plain-object export — read this before authoring any MOBILE widget. 'monitoring' = THE MONITORING CONTRACT: which tools are safe to call in a poll loop (with cost / poll interval / whether output stays bounded as the run grows), which are not and what to use instead, plus the running ateam-mcp version. Read this BEFORE writing any loop that watches a build — the safe poll is ateam_chain_status, never ateam_get_chain."

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user",
-  "python_helpers",
-  "widgets",
-  "ui-plugins",
-  "actor-storage",
-  "voice",
-  "voice-native",
-  "triggers",
-  "sub-agent",
-  "consumer-roles",
-  "mobile-connector"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers",
+  "widgets",
+  "ui-plugins",
+  "actor-storage",
+  "voice",
+  "voice-native",
+  "triggers",
+  "sub-agent",
+  "consumer-roles",
+  "mobile-connector",
+  "monitoring"
+]

Added value: +{
+  "description": "Branch to read/write (alias for `ref`). Declared so MCP does not strip it — an undeclared argument is dropped silently, which made a branch:\"dev\" read return `main` with no error.",
+  "type": "string"
+}

Added value: +{
+  "description": "Branch to read/write (alias for `ref`). Declared so MCP does not strip it — an undeclared argument is dropped silently, which made a branch:\"dev\" read return `main` with no error.",
+  "type": "string"
+}

Previous value: -"Where the solution/skill definition lives. 'github' (DEFAULT) — read from and write to the tenant's GitHub repo (GitHub is master; the normal path). 'local' — read from and write to the Builder FS store (no GitHub repo required). Use 'local' ONLY for a repo-less bootstrap tenant (e.g. freshly onboarded from a template, before GitHub is connected). This is a DEDICATED, EXPLICIT switch — never a fallback. Redeploy is local in both modes."New value: +"Where the solution/skill definition lives. Omit (DEFAULT) — prefer the tenant's GitHub repo (GitHub is master), but AUTO-DEGRADE to the Builder FS store if the tenant hasn't connected a repo, so a simple def patch always succeeds (it's pushed to GitHub once connected). 'github' — force GitHub; fails loud if not connected (use when you specifically require the repo write). 'local' — force the Builder FS store, no GitHub (repo-less bootstrap tenant). Redeploy is local in all modes."

Added value: +{
+  "description": "Optional. WHO is asking. A job belongs to an actor and Core enforces that on per-job reads, so a tenant key alone is refused. Usually unnecessary — the session remembers the actor from ateam_conversation/ateam_test_skill. Pass it to inspect a job run by a DIFFERENT actor (e.g. a real user's).",
+  "type": "string"
+}

Added value: +{
+  "description": "THE EXECUTION'S IDENTITY — what ateam_conversation returns and what you actually hold. A chain is the whole run: root job + every handoff + every askAnySkill subcall. Prefer this.",
+  "type": "string"
+}

Previous value: -"The job ID to abort"New value: +"Abort ONE job only. Prefer chain_id: aborting the root leaves handoffs running while reporting the test aborted."

Previous value: -[
-  "solution_id",
-  "skill_id",
-  "job_id"
-]New value: +[
+  "solution_id"
+]

Added value: +{
+  "description": "Optional. WHO is asking. A job belongs to an actor and Core enforces that on per-job reads, so a tenant key alone is refused. Usually unnecessary — the session remembers the actor from ateam_conversation/ateam_test_skill. Pass it to inspect a job run by a DIFFERENT actor (e.g. a real user's).",
+  "type": "string"
+}

Added value: +{
+  "description": "THE EXECUTION'S IDENTITY — what ateam_conversation returns and what you actually hold. A chain is the whole run: root job + every handoff + every askAnySkill subcall. Prefer this.",
+  "type": "string"
+}

Previous value: -"The job ID returned by ateam_test_skill"New value: +"ONE job inside the chain, when you want that job alone. Omit and pass chain_id for the whole run — a root job can be 'completed' while a handoff is still running."

Previous value: -[
-  "solution_id",
-  "skill_id",
-  "job_id"
-]New value: +[
+  "solution_id"
+]

Previous value: -"Files to upload. By default merges with the GitHub state at `ref`. Set replace:true to wipe the connector dir and write only these files."New value: +"Files to upload — each needs 'path' plus ONE of content (inline string) or content_base64 (escape-safe base64; preferred for multi-file connectors). By default merges with the GitHub state at `ref`. Set replace:true to wipe the connector dir and write only these files."

Previous value: -"File content"New value: +"File content as an inline string. Prefer content_base64 when the content has complex escaping (HTML/JS/JSON)."

Added value: +{
+  "description": "File content as a single-line base64 string — escape-safe. PREFERRED for a multi-file connector so large HTML/JS/bundles don't need hand-escaping in the tool call. Provide exactly ONE of content / content_base64 per file.",
+  "type": "string"
+}

Previous value: -[
-  "path",
-  "content"
-]New value: +[
+  "path"
+]

Added value: +{
+  "description": "RECOVERY: respawn the connector + re-inject its CURRENT env even when the source is UNCHANGED. Normally an unchanged-source upload no-ops (unchanged:true) and leaves the process running. But a connector spawned before a shared-secret rotation keeps the STALE secret — it still lists tools (looks healthy) yet 401s on every per-actor call, with no recovery short of a fake source edit. Use `ateam_upload_connector(solution_id, connector_id, github:true, force:true)` to pull the current source and force a fresh respawn (which picks up the current secret). Default: false.",
+  "type": "boolean"
+}

Previous value: -"Example type: 'skill' = Order Support Agent, 'connector' = stdio MCP connector, 'connector-ui' = UI-capable connector, 'solution' = full 3-skill e-commerce solution, 'script-cache-skill' = fat-tool skill with script_cache opt-in (reference implementation of script-level JIT shortcuts — study this before building any browser-automation skill), 'index' = list all available examples"New value: +"Example type: 'skill' = Order Support Agent, 'connector' = stdio MCP connector, 'connector-ui' = UI-capable connector, 'solution' = full 3-skill e-commerce solution, 'script-cache-skill' = fat-tool skill with script_cache opt-in (reference implementation of script-level JIT shortcuts — study this before building any browser-automation skill), 'ui-plugin-native' = complete working React Native (mobile) UI plugin (rn-src/index.tsx + esbuild build:rn → rn-bundle, @adas/plugin-sdk, es2015), 'index' = list all available examples"

Previous value: -[
-  "skill",
-  "connector",
-  "connector-ui",
-  "solution",
-  "script-cache-skill",
-  "index"
-]New value: +[
+  "skill",
+  "connector",
+  "connector-ui",
+  "solution",
+  "script-cache-skill",
+  "ui-plugin-native",
+  "index"
+]

Added value: +{
+  "description": "Optional byte-paging: max bytes of the serialized result to return in this page (pair with 'offset'). Omit both for the whole result (may truncate at the output cap).",
+  "type": "number"
+}

Added value: +{
+  "description": "Optional byte-paging: start returning the serialized result from this byte offset. Use with 'limit' to page a result larger than the ~50KB output cap; the response's _paging.next_offset gives the next page (null when done). Concatenate the `content` slices across pages, then JSON.parse.",
+  "type": "number"
+}

Added value: +{
+  "description": "Optional (with skill_id): return ONLY this section of the skill instead of the whole definition — avoids the ~50KB output truncation on big skills. Dotted paths work (e.g. 'role', 'tools', 'intents.supported', 'policy', 'engine'). Omit for the full skill; use ateam_show_skill_minimal for the slim authoring view.",
+  "type": "string"
+}

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory."New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory. 'ui-plugins' = the DEEP React Native (mobile) plugin build guide: author in rn-src/, compile with a build:rn esbuild script (format=cjs, target=es2015, external react/react-native/@adas/plugin-sdk) to rn-bundle/index.bundle.js, plain-object export — read this before authoring any MOBILE widget."

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user",
-  "python_helpers",
-  "widgets"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers",
+  "widgets",
+  "ui-plugins",
+  "actor-storage",
+  "voice",
+  "voice-native",
+  "triggers",
+  "sub-agent",
+  "consumer-roles",
+  "mobile-connector"
+]

Removed value: -{
-  "description": "Optional: max wait time in ms (default: 60000, max: 300000).",
-  "type": "number"
-}

Removed value: -{
-  "description": "If true (default), wait for completion. If false, return job_id immediately for polling.",
-  "type": "boolean"
-}

Added value: +{
+  "description": "Optional. Read ONE file (e.g. 'server.js', 'ui-dist/panel/index.html'). Omit to get a file manifest (paths + sizes, no content) — a whole connector's source exceeds the ~50KB output limit and truncates, so read files one at a time.",
+  "type": "string"
+}

Added value: +{
+  "description": "If true, return the FULL patched definition. Default false — the result returns a compact patched_summary instead, because the full definition can exceed the ~50KB output limit and truncate the rest of the result (redeploy status, widget_health).",
+  "type": "boolean"
+}

Added value: +{
+  "description": "REQUIRED. Must be exactly true. A missing/false value refuses the call with a recovery hint.",
+  "type": "boolean"
+}

Previous value: -[
-  "solution_id",
-  "connector_id"
-]New value: +[
+  "solution_id",
+  "connector_id",
+  "confirm"
+]

Added value: +{
+  "description": "REQUIRED. Must be exactly true. A missing/false value refuses the call with a recovery hint.",
+  "type": "boolean"
+}

Previous value: -[
-  "solution_id",
-  "skill_id"
-]New value: +[
+  "solution_id",
+  "skill_id",
+  "confirm"
+]

Added value: +{
+  "description": "REQUIRED. Must be exactly true. A missing/false value refuses the call with a recovery hint.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "REQUIRED. Must exactly equal `solution_id`. This defeats typos and hallucinated ids — you can't wipe a solution you couldn't spell.",
+  "type": "string"
+}

Previous value: -[
-  "solution_id"
-]New value: +[
+  "solution_id",
+  "confirm",
+  "confirm_solution_id"
+]

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler)."New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory."

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user",
-  "python_helpers"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers",
+  "widgets"
+]

Added value: +{
+  "description": "If true, apply the patch in memory and return the diff (arrays_merged, arrays_replaced, dropped_ids, added_ids, would_write_bytes) WITHOUT writing to GitHub or redeploying. Preview a change before committing to it.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Where the solution/skill definition lives. 'github' (DEFAULT) — read from and write to the tenant's GitHub repo (GitHub is master; the normal path). 'local' — read from and write to the Builder FS store (no GitHub repo required). Use 'local' ONLY for a repo-less bootstrap tenant (e.g. freshly onboarded from a template, before GitHub is connected). This is a DEDICATED, EXPLICIT switch — never a fallback. Redeploy is local in both modes.",
+  "enum": [
+    "github",
+    "local"
+  ],
+  "type": "string"
+}

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory."New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler)."

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user",
-  "python_helpers",
-  "widgets"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers"
+]

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler)."New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler), 'widgets' = widget (UI plugin) spec: catalog model, how_to_use block shape (solution.json snippet + opener_call + persona_phrasing + binding_notes), and rules for declaring ui_plugins. Pair with ateam_get_widget_catalog for the live per-tenant inventory."

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user",
-  "python_helpers"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers",
+  "widgets"
+]

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide"New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler)."

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers"
+]

Added value: +{
+  "description": "Optional. Max total ms to wait when wait_for:'chain'. Default 300000 (5 min). Long-running chains (skill-factory, large bundle builds) may need higher. Clamped to [10000, 900000].",
+  "type": "number"
+}

Previous value: -"If true (default), wait for completion. If false, return job_id immediately for polling via ateam_test_status."New value: +"Legacy: if false, return job_id immediately for polling. If true or omitted, behaves like wait_for:'root'. Prefer wait_for going forward."

Added value: +{
+  "description": "What to wait for before returning. 'root' (default) = root job done; 'chain' = every chain job terminal (use for multi-skill flows); 'never' = return job_id immediately (poll via ateam_test_status). When 'chain', the response includes the chain tree under response.chain.",
+  "enum": [
+    "root",
+    "chain",
+    "never"
+  ],
+  "type": "string"
+}

Added value: +{
+  "description": "If true, includes response.chain — the full chain tree rooted at this job_id (chainJobs[] with parentJobId/relation/depth, executionSteps[] with tool-nesting). Costs one extra Core call. Default false (back-compat).",
+  "type": "boolean"
+}

Previous value: -"Files to upload. Alternative to github=true."New value: +"Files to upload. By default merges with the GitHub state at `ref`. Set replace:true to wipe the connector dir and write only these files."

Previous value: -"If true, pull connector files from GitHub repo. Default: false."New value: +"If true, pull connector files from GitHub repo at `ref`. Default: false. Combine with files:[] to use GitHub as the base and overlay your files."

Added value: +{
+  "description": "GitHub branch to read from for the BASE state. Default: 'dev' (matches ateam_github_patch). Pass 'main' to read from production. Pre-2026-06-05 callers that relied on the silent-main default must pass ref:'main' explicitly.",
+  "type": "string"
+}

Added value: +{
+  "description": "Opt into FULL REPLACE: wipe the connector dir and write only the provided `files`. Default: false (= merge with GitHub state at `ref`). Use with intent — sending an incomplete file set with replace:true will break the connector.",
+  "type": "boolean"
+}

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler)."New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide"

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user",
-  "python_helpers"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user"
+]

Removed value: -{
-  "description": "Optional. Max total ms to wait when wait_for:'chain'. Default 300000 (5 min). Long-running chains (skill-factory, large bundle builds) may need higher. Clamped to [10000, 900000].",
-  "type": "number"
-}

Previous value: -"Legacy: if false, return job_id immediately for polling. If true or omitted, behaves like wait_for:'root'. Prefer wait_for going forward."New value: +"If true (default), wait for completion. If false, return job_id immediately for polling via ateam_test_status."

Removed value: -{
-  "description": "What to wait for before returning. 'root' (default) = root job done; 'chain' = every chain job terminal (use for multi-skill flows); 'never' = return job_id immediately (poll via ateam_test_status). When 'chain', the response includes the chain tree under response.chain.",
-  "enum": [
-    "root",
-    "chain",
-    "never"
-  ],
-  "type": "string"
-}

Removed value: -{
-  "description": "If true, includes response.chain — the full chain tree rooted at this job_id (chainJobs[] with parentJobId/relation/depth, executionSteps[] with tool-nesting). Costs one extra Core call. Default false (back-compat).",
-  "type": "boolean"
-}

Previous value: -"Files to upload. By default merges with the GitHub state at `ref`. Set replace:true to wipe the connector dir and write only these files."New value: +"Files to upload. Alternative to github=true."

Previous value: -"If true, pull connector files from GitHub repo at `ref`. Default: false. Combine with files:[] to use GitHub as the base and overlay your files."New value: +"If true, pull connector files from GitHub repo. Default: false."

Removed value: -{
-  "description": "GitHub branch to read from for the BASE state. Default: 'dev' (matches ateam_github_patch). Pass 'main' to read from production. Pre-2026-06-05 callers that relied on the silent-main default must pass ref:'main' explicitly.",
-  "type": "string"
-}

Removed value: -{
-  "description": "Opt into FULL REPLACE: wipe the connector dir and write only the provided `files`. Default: false (= merge with GitHub state at `ref`). Use with intent — sending an incomplete file set with replace:true will break the connector.",
-  "type": "boolean"
-}

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide"New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler)."

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers"
+]

Added value: +{
+  "description": "Optional. Max total ms to wait when wait_for:'chain'. Default 300000 (5 min). Long-running chains (skill-factory, large bundle builds) may need higher. Clamped to [10000, 900000].",
+  "type": "number"
+}

Previous value: -"If true (default), wait for completion. If false, return job_id immediately for polling via ateam_test_status."New value: +"Legacy: if false, return job_id immediately for polling. If true or omitted, behaves like wait_for:'root'. Prefer wait_for going forward."

Added value: +{
+  "description": "What to wait for before returning. 'root' (default) = root job done; 'chain' = every chain job terminal (use for multi-skill flows); 'never' = return job_id immediately (poll via ateam_test_status). When 'chain', the response includes the chain tree under response.chain.",
+  "enum": [
+    "root",
+    "chain",
+    "never"
+  ],
+  "type": "string"
+}

Added value: +{
+  "description": "If true, includes response.chain — the full chain tree rooted at this job_id (chainJobs[] with parentJobId/relation/depth, executionSteps[] with tool-nesting). Costs one extra Core call. Default false (back-compat).",
+  "type": "boolean"
+}

Previous value: -"Files to upload. Alternative to github=true."New value: +"Files to upload. By default merges with the GitHub state at `ref`. Set replace:true to wipe the connector dir and write only these files."

Previous value: -"If true, pull connector files from GitHub repo. Default: false."New value: +"If true, pull connector files from GitHub repo at `ref`. Default: false. Combine with files:[] to use GitHub as the base and overlay your files."

Added value: +{
+  "description": "GitHub branch to read from for the BASE state. Default: 'dev' (matches ateam_github_patch). Pass 'main' to read from production. Pre-2026-06-05 callers that relied on the silent-main default must pass ref:'main' explicitly.",
+  "type": "string"
+}

Added value: +{
+  "description": "Opt into FULL REPLACE: wipe the connector dir and write only the provided `files`. Default: false (= merge with GitHub state at `ref`). Use with intent — sending an incomplete file set with replace:true will break the connector.",
+  "type": "boolean"
+}

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler)."New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide"

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user",
-  "python_helpers"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user"
+]

Removed value: -{
-  "description": "Optional. Max total ms to wait when wait_for:'chain'. Default 300000 (5 min). Long-running chains (skill-factory, large bundle builds) may need higher. Clamped to [10000, 900000].",
-  "type": "number"
-}

Previous value: -"Legacy: if false, return job_id immediately for polling. If true or omitted, behaves like wait_for:'root'. Prefer wait_for going forward."New value: +"If true (default), wait for completion. If false, return job_id immediately for polling via ateam_test_status."

Removed value: -{
-  "description": "What to wait for before returning. 'root' (default) = root job done; 'chain' = every chain job terminal (use for multi-skill flows); 'never' = return job_id immediately (poll via ateam_test_status). When 'chain', the response includes the chain tree under response.chain.",
-  "enum": [
-    "root",
-    "chain",
-    "never"
-  ],
-  "type": "string"
-}

Removed value: -{
-  "description": "If true, includes response.chain — the full chain tree rooted at this job_id (chainJobs[] with parentJobId/relation/depth, executionSteps[] with tool-nesting). Costs one extra Core call. Default false (back-compat).",
-  "type": "boolean"
-}

Previous value: -"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide"New value: +"What to fetch: 'overview' = API overview + endpoints, 'skill' = full skill spec, 'solution' = full solution spec, 'enums' = all enum values, 'connector-multi-user' = multi-user connector guide, 'python_helpers' = adas.* helper namespace for run_python_script orchestration (read this when designing personas that read state → call tools → checkpoint → status; without it, scripts hand-roll JSON parsing and tool delegation = 5-10x larger and brittler)."

Previous value: -[
-  "overview",
-  "skill",
-  "solution",
-  "enums",
-  "connector-multi-user"
-]New value: +[
+  "overview",
+  "skill",
+  "solution",
+  "enums",
+  "connector-multi-user",
+  "python_helpers"
+]

Added value: +{
+  "description": "Optional. Max total ms to wait when wait_for:'chain'. Default 300000 (5 min). Long-running chains (skill-factory, large bundle builds) may need higher. Clamped to [10000, 900000].",
+  "type": "number"
+}

Previous value: -"If true (default), wait for completion. If false, return job_id immediately for polling via ateam_test_status."New value: +"Legacy: if false, return job_id immediately for polling. If true or omitted, behaves like wait_for:'root'. Prefer wait_for going forward."

Added value: +{
+  "description": "What to wait for before returning. 'root' (default) = root job done; 'chain' = every chain job terminal (use for multi-skill flows); 'never' = return job_id immediately (poll via ateam_test_status). When 'chain', the response includes the chain tree under response.chain.",
+  "enum": [
+    "root",
+    "chain",
+    "never"
+  ],
+  "type": "string"
+}

Added value: +{
+  "description": "If true, includes response.chain — the full chain tree rooted at this job_id (chainJobs[] with parentJobId/relation/depth, executionSteps[] with tool-nesting). Costs one extra Core call. Default false (back-compat).",
+  "type": "boolean"
+}

Previous value: -"Optional: if true, pull connector source code from the solution's GitHub repo. AUTO-DETECTED: if you omit both mcp_store and github, the system checks if a repo exists and pulls from it automatically. You rarely need to set this explicitly."New value: +"Optional: if true, pull connector source code from main. AUTO-DETECTED: if you omit both mcp_store and github, the system checks if a repo exists and pulls from main automatically."

Previous value: -"Optional after first deploy: skill definitions. If omitted, auto-pulled from GitHub repo (skills/{id}/skill.json)."New value: +"Optional after first deploy: skill definitions. If omitted, auto-pulled from main (skills/{id}/skill.json)."

Previous value: -"Full solution definition. Required on first deploy. After first deploy, just pass solution_id instead — everything is auto-pulled from GitHub."New value: +"Full solution definition. Required on first deploy. After first deploy, just pass solution_id instead — everything is auto-pulled from GitHub main."

Previous value: -"The solution ID. Use this INSTEAD of passing the full solution object — the solution definition is auto-pulled from GitHub. Required if solution object is omitted."New value: +"The solution ID. Use this INSTEAD of passing the full solution object — the solution definition is auto-pulled from main. Required if solution object is omitted."

Previous value: -"Base branch (the target). Default: 'main'."New value: +"Base branch/tag/sha (the target — what you're comparing TO). Default: 'main'."

Previous value: -"Head branch (the source). Default: 'dev'."New value: +"Head branch/tag/sha (the source — what you're comparing FROM). Default: 'dev'."

Added value: +{
+  "default": "main",
+  "description": "Branch to read commits from. Default: 'main'.",
+  "type": "string"
+}

Added value: +{
+  "default": "dev",
+  "description": "Target branch. Default: 'dev' (safe — won't touch prod). Use 'main' only for emergency hotfixes.",
+  "type": "string"
+}

Added value: +{
+  "description": "If true: show the diff (commits + files about to ship) without merging. Default: false.",
+  "type": "boolean"
+}

Previous value: -"Optional: human-readable label for this checkpoint (e.g., 'before refactor', 'v2 stable')"New value: +"Optional: human-readable label for the auto-tag (e.g., 'v2 stable', 'before refactor')"

Added value: +{
+  "description": "If true: merge without creating an auto-tag. Default: false (auto-tag enabled).",
+  "type": "boolean"
+}

Added value: +{
+  "default": "main",
+  "description": "Branch, tag, or commit SHA to read from. Default: 'main' (prod). Use 'dev' to read in-progress work.",
+  "type": "string"
+}

Removed value: -{
-  "description": "Required: checkpoint tag to rollback to (e.g., 'safe-2026-03-11-001')",
-  "type": "string"
-}

Added value: +{
+  "description": "Tag (e.g., 'safe-2026-05-19-001') or commit SHA to revert main to. Use ateam_github_list_versions to find safe-* tags.",
+  "type": "string"
+}

Previous value: -[
-  "solution_id",
-  "tag"
-]New value: +[
+  "solution_id",
+  "target"
+]

Added value: +{
+  "default": "dev",
+  "description": "Target branch. Default: 'dev'.",
+  "type": "string"
+}