healthcloud-cli 3.3.0__tar.gz → 3.4.0__tar.gz

{healthcloud_cli-3.3.0 → healthcloud_cli-3.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: healthcloud-cli
-Version: 3.3.0
+Version: 3.4.0
 Summary: Command-line interface for the HealthCloud MCP gateway, generated from the shared MCP tool manifest.
 Project-URL: Issues, https://github.com/healthcloudservices/healthcloud-services/issues
 Project-URL: Repository, https://github.com/healthcloudservices/healthcloud-services
@@ -69,10 +69,10 @@ _HC_COMPLETE=bash_complete COMP_WORDS="hc ams inspect --o" COMP_CWORD=3 uv run -
 ```
 
 Operational validation starts only when Click invokes an AMS leaf callback.
-`discover` then validates its explicit environment and tenant arguments; the
-other leaves require `--target-file` and apply the existing root, target, and
-authentication checks described below. Deferring preflight does not relax
-those safety requirements.
+`discover`, `agents`, `departments`, `teams`, `organization`, `skills`, and `policies` then
+validate their explicit environment and tenant arguments; the remaining leaves
+require `--target-file`. All apply the root, target, and authentication checks
+described below. Deferring preflight does not relax those safety requirements.
 
 The bundled tool manifest (`healthcloud_cli/contracts/mcp-tools.manifest.json`)
 is a copy of `packages/cli/contracts/mcp-tools.manifest.json`. Re-sync it
@@ -280,16 +280,47 @@ uv sync --frozen --extra dev
 uv run --frozen hc ams --help
 ```
 
-Bootstrap candidate IDs with the public SDK discovery endpoint. Both flags are
-required; no MCP defaults, admin login, or automatic candidate selection are used:
+Create one private tenant-admin session before interactive AMS work, inspect its
+non-secret binding, and remove it when finished:
+
+```bash
+uv run --frozen hc login --environment dev --tenant-id TENANT_ID
+uv run --frozen hc login --status
+uv run --frozen hc logout
+```
+
+`hc login` reads `HC_AMS_ADMIN_EMAIL` and `HC_AMS_ADMIN_PASSWORD` when present,
+otherwise it prompts (with hidden password input). It stores only the email,
+tenant/environment binding, access/refresh tokens and expiry in the strict
+owner-only `~/.healthcloud/cli/ams-session.json`; it never stores the password.
+AMS commands may omit both target flags while this session is present, except
+that a `prod` session still needs `--environment prod` on every command. Explicit
+flags and target files must match it exactly. A session within 60 seconds of
+expiry is refreshed once before the operation, under a lock so concurrent
+commands never spend the same refresh token (a second command waits up to 30 seconds, then stops), and
+atomically replaced. Refresh
+failure stops without an AMS call or password fallback and asks for a new login.
+If the refreshed session cannot be saved, the current command still finishes and
+prints a warning to run `hc login` again.
+
+`~/.healthcloud` and `~/.healthcloud/cli` must be directories you own with mode
+700; the CLI creates them that way, and refuses (naming the directory and the
+`chmod 700` fix) if an existing one is shared. `hc logout` deletes the local file
+only and reports `"server_session_revoked": false`: issued tokens stay valid
+until they expire.
+
+Bootstrap candidate IDs with the public SDK discovery endpoint. Without a saved
+session both flags are required; a saved session supplies both together. No MCP
+defaults, admin login, or automatic candidate selection are used:
 
 ```bash
 uv run --frozen hc ams discover --environment dev --tenant-id TENANT_ID
 ```
 
-Read-only agent listing, inspection and export also take explicit flags instead
-of a target file, and log in as tenant admin (`HC_AMS_ADMIN_EMAIL` /
-`HC_AMS_ADMIN_PASSWORD`). Stdout carries bounded metadata only; `adapter` shows
+Read-only agent listing, inspection and export take flags instead of a target
+file; both may be omitted together when a matching saved session exists. Without
+one, they log in as tenant admin using `HC_AMS_ADMIN_EMAIL` /
+`HC_AMS_ADMIN_PASSWORD`. Stdout carries bounded metadata only; `adapter` shows
 whether an agent runs from the `file` or `db` config adapter (`unknown` when the
 server does not say). `export` first re-checks the agent/tenant identity, then
 saves the server's own JSON/YAML export byte-for-byte to a new owner-only `--out`
@@ -335,6 +366,61 @@ or inferring missing relationships:
 uv run --frozen hc ams organization hierarchy --environment dev --tenant-id TENANT_ID
 ```
 
+Read-only skill catalog listing and inspection are complete and unpaged. The
+bounded projection includes only skill IDs, names, tool IDs, and audit timestamps;
+it omits descriptions, tenant identity, creator identity, arbitrary response
+fields, and tool details. Tool-ID order is preserved:
+
+```bash
+uv run --frozen hc ams skills list --environment dev --tenant-id TENANT_ID
+uv run --frozen hc ams skills get --environment dev --tenant-id TENANT_ID --skill-id SKILL_ID
+```
+
+The CLI does not create, update, delete, or assign skills. Skill commands do not
+read guardrails. They make exactly one catalog GET after tenant-admin login
+and does not paginate, retry, cache, join, or infer additional catalog data.
+Skill reads refuse target files, root credentials or base URLs, raw output,
+blank or dot-segment skill IDs, and installed SDKs that do not provide both
+skill list and get methods. These local refusals happen before tenant-admin login
+or catalog reads.
+
+Read-only policy catalog listing and inspection are complete and unpaged. The
+bounded projection includes only policy IDs, names, department IDs, guardrail
+IDs, active status, and audit timestamps. It never emits protected policy
+content, descriptions, tenant or creator identity, arbitrary response fields,
+or joined department/guardrail details. Guardrail-ID order is preserved:
+
+```bash
+uv run --frozen hc ams policies list --environment dev --tenant-id TENANT_ID
+uv run --frozen hc ams policies get --environment dev --tenant-id TENANT_ID --policy-id POLICY_ID
+```
+
+The CLI does not export protected policy content; create, update, delete, or
+assign policies; or join guardrail records. It makes exactly one catalog GET after
+tenant-admin login and does not paginate, retry, cache, join, or infer referenced
+resources. Policy reads refuse target files, root credentials or base URLs, raw
+output, blank or dot-segment policy IDs, and installed SDKs without both policy
+methods before tenant-admin login or catalog reads. Successful reads make no
+assignment, deployment, serving, enforcement, or effectiveness claim.
+
+Read-only guardrail catalog listing and inspection are complete and unpaged.
+The bounded projection includes only guardrail IDs, names, and audit timestamps.
+It never emits protected rules, descriptions, tenant or creator identity,
+arbitrary response fields, or joined policy/agent details:
+
+```bash
+uv run --frozen hc ams guardrails list --environment dev --tenant-id TENANT_ID
+uv run --frozen hc ams guardrails get --environment dev --tenant-id TENANT_ID \
+  --guardrail-id GUARDRAIL_ID
+```
+
+The CLI does not export rules; create, update, delete, assign, deploy, or enforce
+guardrails; or claim they are active or effective. It makes exactly one catalog
+GET after tenant-admin login and does not paginate, retry, cache, join, or infer
+additional data. Guardrail reads refuse target files, root credentials or base
+URLs, raw output, blank or dot-segment guardrail IDs, and installed SDKs without
+both guardrail methods before tenant-admin login or catalog reads.
+
 Every other command requires an explicit local, non-secret target JSON file.
 Only the canonical HTTPS AMS origin for that environment is accepted; custom
 origins require separately verified support. Target and nested qualification keys
@@ -403,11 +489,11 @@ configuration and recheck it before apply and selected-field restore. This is an
 operator prerequisite: the current CLI does not automatically attest deployment
 or all-writer coverage, and the record adds no server authorization boundary.
 
-Credentials enter only through `HC_AMS_ADMIN_EMAIL` and `HC_AMS_ADMIN_PASSWORD`
-in the current process, intended for composition with the existing
-`onepassword-env` wrapper. Each invocation logs in through `HCTenantAdminSDK`;
-tokens remain private in memory. There is no token cache, fallback identity,
-secret argument, resolved env file, or browser credential bridge. Root MCP
+For CI and scripts with no saved session, credentials may still enter through
+`HC_AMS_ADMIN_EMAIL` and `HC_AMS_ADMIN_PASSWORD` in the current process, intended
+for composition with the existing `onepassword-env` wrapper; that compatibility
+path logs in once per invocation. There is no fallback identity, secret argument,
+arbitrary token import, resolved env file, keychain, or browser credential bridge. Root MCP
 `--access-token`, `--base-url`, their environment equivalents, and token/base-URL
 profiles are refused for AMS. Root profile environment values do not select AMS.
 

{healthcloud_cli-3.3.0 → healthcloud_cli-3.4.0}/README.md

@@ -51,10 +51,10 @@ _HC_COMPLETE=bash_complete COMP_WORDS="hc ams inspect --o" COMP_CWORD=3 uv run -
 ```
 
 Operational validation starts only when Click invokes an AMS leaf callback.
-`discover` then validates its explicit environment and tenant arguments; the
-other leaves require `--target-file` and apply the existing root, target, and
-authentication checks described below. Deferring preflight does not relax
-those safety requirements.
+`discover`, `agents`, `departments`, `teams`, `organization`, `skills`, and `policies` then
+validate their explicit environment and tenant arguments; the remaining leaves
+require `--target-file`. All apply the root, target, and authentication checks
+described below. Deferring preflight does not relax those safety requirements.
 
 The bundled tool manifest (`healthcloud_cli/contracts/mcp-tools.manifest.json`)
 is a copy of `packages/cli/contracts/mcp-tools.manifest.json`. Re-sync it
@@ -262,16 +262,47 @@ uv sync --frozen --extra dev
 uv run --frozen hc ams --help
 ```
 
-Bootstrap candidate IDs with the public SDK discovery endpoint. Both flags are
-required; no MCP defaults, admin login, or automatic candidate selection are used:
+Create one private tenant-admin session before interactive AMS work, inspect its
+non-secret binding, and remove it when finished:
+
+```bash
+uv run --frozen hc login --environment dev --tenant-id TENANT_ID
+uv run --frozen hc login --status
+uv run --frozen hc logout
+```
+
+`hc login` reads `HC_AMS_ADMIN_EMAIL` and `HC_AMS_ADMIN_PASSWORD` when present,
+otherwise it prompts (with hidden password input). It stores only the email,
+tenant/environment binding, access/refresh tokens and expiry in the strict
+owner-only `~/.healthcloud/cli/ams-session.json`; it never stores the password.
+AMS commands may omit both target flags while this session is present, except
+that a `prod` session still needs `--environment prod` on every command. Explicit
+flags and target files must match it exactly. A session within 60 seconds of
+expiry is refreshed once before the operation, under a lock so concurrent
+commands never spend the same refresh token (a second command waits up to 30 seconds, then stops), and
+atomically replaced. Refresh
+failure stops without an AMS call or password fallback and asks for a new login.
+If the refreshed session cannot be saved, the current command still finishes and
+prints a warning to run `hc login` again.
+
+`~/.healthcloud` and `~/.healthcloud/cli` must be directories you own with mode
+700; the CLI creates them that way, and refuses (naming the directory and the
+`chmod 700` fix) if an existing one is shared. `hc logout` deletes the local file
+only and reports `"server_session_revoked": false`: issued tokens stay valid
+until they expire.
+
+Bootstrap candidate IDs with the public SDK discovery endpoint. Without a saved
+session both flags are required; a saved session supplies both together. No MCP
+defaults, admin login, or automatic candidate selection are used:
 
 ```bash
 uv run --frozen hc ams discover --environment dev --tenant-id TENANT_ID
 ```
 
-Read-only agent listing, inspection and export also take explicit flags instead
-of a target file, and log in as tenant admin (`HC_AMS_ADMIN_EMAIL` /
-`HC_AMS_ADMIN_PASSWORD`). Stdout carries bounded metadata only; `adapter` shows
+Read-only agent listing, inspection and export take flags instead of a target
+file; both may be omitted together when a matching saved session exists. Without
+one, they log in as tenant admin using `HC_AMS_ADMIN_EMAIL` /
+`HC_AMS_ADMIN_PASSWORD`. Stdout carries bounded metadata only; `adapter` shows
 whether an agent runs from the `file` or `db` config adapter (`unknown` when the
 server does not say). `export` first re-checks the agent/tenant identity, then
 saves the server's own JSON/YAML export byte-for-byte to a new owner-only `--out`
@@ -317,6 +348,61 @@ or inferring missing relationships:
 uv run --frozen hc ams organization hierarchy --environment dev --tenant-id TENANT_ID
 ```
 
+Read-only skill catalog listing and inspection are complete and unpaged. The
+bounded projection includes only skill IDs, names, tool IDs, and audit timestamps;
+it omits descriptions, tenant identity, creator identity, arbitrary response
+fields, and tool details. Tool-ID order is preserved:
+
+```bash
+uv run --frozen hc ams skills list --environment dev --tenant-id TENANT_ID
+uv run --frozen hc ams skills get --environment dev --tenant-id TENANT_ID --skill-id SKILL_ID
+```
+
+The CLI does not create, update, delete, or assign skills. Skill commands do not
+read guardrails. They make exactly one catalog GET after tenant-admin login
+and does not paginate, retry, cache, join, or infer additional catalog data.
+Skill reads refuse target files, root credentials or base URLs, raw output,
+blank or dot-segment skill IDs, and installed SDKs that do not provide both
+skill list and get methods. These local refusals happen before tenant-admin login
+or catalog reads.
+
+Read-only policy catalog listing and inspection are complete and unpaged. The
+bounded projection includes only policy IDs, names, department IDs, guardrail
+IDs, active status, and audit timestamps. It never emits protected policy
+content, descriptions, tenant or creator identity, arbitrary response fields,
+or joined department/guardrail details. Guardrail-ID order is preserved:
+
+```bash
+uv run --frozen hc ams policies list --environment dev --tenant-id TENANT_ID
+uv run --frozen hc ams policies get --environment dev --tenant-id TENANT_ID --policy-id POLICY_ID
+```
+
+The CLI does not export protected policy content; create, update, delete, or
+assign policies; or join guardrail records. It makes exactly one catalog GET after
+tenant-admin login and does not paginate, retry, cache, join, or infer referenced
+resources. Policy reads refuse target files, root credentials or base URLs, raw
+output, blank or dot-segment policy IDs, and installed SDKs without both policy
+methods before tenant-admin login or catalog reads. Successful reads make no
+assignment, deployment, serving, enforcement, or effectiveness claim.
+
+Read-only guardrail catalog listing and inspection are complete and unpaged.
+The bounded projection includes only guardrail IDs, names, and audit timestamps.
+It never emits protected rules, descriptions, tenant or creator identity,
+arbitrary response fields, or joined policy/agent details:
+
+```bash
+uv run --frozen hc ams guardrails list --environment dev --tenant-id TENANT_ID
+uv run --frozen hc ams guardrails get --environment dev --tenant-id TENANT_ID \
+  --guardrail-id GUARDRAIL_ID
+```
+
+The CLI does not export rules; create, update, delete, assign, deploy, or enforce
+guardrails; or claim they are active or effective. It makes exactly one catalog
+GET after tenant-admin login and does not paginate, retry, cache, join, or infer
+additional data. Guardrail reads refuse target files, root credentials or base
+URLs, raw output, blank or dot-segment guardrail IDs, and installed SDKs without
+both guardrail methods before tenant-admin login or catalog reads.
+
 Every other command requires an explicit local, non-secret target JSON file.
 Only the canonical HTTPS AMS origin for that environment is accepted; custom
 origins require separately verified support. Target and nested qualification keys
@@ -385,11 +471,11 @@ configuration and recheck it before apply and selected-field restore. This is an
 operator prerequisite: the current CLI does not automatically attest deployment
 or all-writer coverage, and the record adds no server authorization boundary.
 
-Credentials enter only through `HC_AMS_ADMIN_EMAIL` and `HC_AMS_ADMIN_PASSWORD`
-in the current process, intended for composition with the existing
-`onepassword-env` wrapper. Each invocation logs in through `HCTenantAdminSDK`;
-tokens remain private in memory. There is no token cache, fallback identity,
-secret argument, resolved env file, or browser credential bridge. Root MCP
+For CI and scripts with no saved session, credentials may still enter through
+`HC_AMS_ADMIN_EMAIL` and `HC_AMS_ADMIN_PASSWORD` in the current process, intended
+for composition with the existing `onepassword-env` wrapper; that compatibility
+path logs in once per invocation. There is no fallback identity, secret argument,
+arbitrary token import, resolved env file, keychain, or browser credential bridge. Root MCP
 `--access-token`, `--base-url`, their environment equivalents, and token/base-URL
 profiles are refused for AMS. Root profile environment values do not select AMS.
 

{healthcloud_cli-3.3.0 → healthcloud_cli-3.4.0}/healthcloud_cli/ams/agents/commands.py

@@ -9,16 +9,16 @@ import click
 from ..compatibility import safe_errors
 from ..context import AmsDependencies, pass_ams, preflight_agents
 from ..output import metadata
-from ..target import TenantTarget
+from ..session import resolve_tenant_target
 from .operations import AgentReadRefused, export_agent, get_agent, list_agents
 
 
 def _environment(function):
-    return click.option("--environment", type=click.Choice(["dev", "uat", "prod"]), required=True)(function)
+    return click.option("--environment", type=click.Choice(["dev", "uat", "prod"]))(function)
 
 
 def _tenant(function):
-    return click.option("--tenant-id", required=True)(function)
+    return click.option("--tenant-id")(function)
 
 
 def _agent(function):
@@ -38,9 +38,9 @@ def create_list_command(dependencies: AmsDependencies) -> click.Command:
     @_tenant
     @pass_ams
     @safe_errors
-    def command(invocation, environment: str, tenant_id: str) -> None:
+    def command(invocation, environment: str | None, tenant_id: str | None) -> None:
         preflight_agents(invocation)
-        metadata(_run(list_agents, dependencies, TenantTarget(environment, tenant_id)))
+        metadata(_run(list_agents, dependencies, resolve_tenant_target(environment, tenant_id)))
 
     return command
 
@@ -52,9 +52,9 @@ def create_get_command(dependencies: AmsDependencies) -> click.Command:
     @_agent
     @pass_ams
     @safe_errors
-    def command(invocation, environment: str, tenant_id: str, agent_id: str) -> None:
+    def command(invocation, environment: str | None, tenant_id: str | None, agent_id: str) -> None:
         preflight_agents(invocation)
-        metadata(_run(get_agent, dependencies, TenantTarget(environment, tenant_id), agent_id))
+        metadata(_run(get_agent, dependencies, resolve_tenant_target(environment, tenant_id), agent_id))
 
     return command
 
@@ -70,14 +70,14 @@ def create_export_command(dependencies: AmsDependencies) -> click.Command:
     @safe_errors
     def command(
         invocation,
-        environment: str,
-        tenant_id: str,
+        environment: str | None,
+        tenant_id: str | None,
         agent_id: str,
         out: Path,
         export_format: str,
     ) -> None:
         preflight_agents(invocation)
-        target = TenantTarget(environment, tenant_id)
+        target = resolve_tenant_target(environment, tenant_id)
         metadata(_run(export_agent, dependencies, target, agent_id, out, export_format))
 
     return command

healthcloud_cli-3.4.0/healthcloud_cli/ams/auth.py

@@ -0,0 +1,91 @@
+"""Saved-session or environment tenant-admin authentication."""
+
+import os
+from contextlib import contextmanager
+from datetime import UTC, datetime
+
+import click
+
+from healthcloud import HCSDK
+from healthcloud_tenantadmin import HCTenantAdminSDK
+
+from .session import load_session, refreshed_session, save_session, session_lock
+from .target import AmsTarget, TenantTarget
+
+
+@contextmanager
+def authenticated_sdk(target: AmsTarget | TenantTarget):
+    sdk = HCSDK(environment=target.environment, tenant_id=target.tenant_id)
+    try:
+        if not hasattr(sdk, "ams_admin"):
+            raise click.ClickException(
+                "SDK missing ams_admin; use the reviewed local editable SDK checkout (see CLI README)."
+            )
+        if isinstance(target, TenantTarget) and not hasattr(sdk.ams_admin, "list_agents"):
+            raise click.ClickException(
+                "SDK missing ams_admin agent listing; use the reviewed local editable SDK checkout (see CLI README)."
+            )
+        session = load_session()
+        if session is not None:
+            if (target.environment, target.tenant_id) != (session.environment, session.tenant_id):
+                raise click.ClickException(
+                    "AMS target does not match the saved session; stopped before authentication."
+                )
+            token = _saved_session_token(target)
+        else:
+            email = os.environ.get("HC_AMS_ADMIN_EMAIL")
+            password = os.environ.get("HC_AMS_ADMIN_PASSWORD")
+            if not email or not password:
+                raise click.ClickException(
+                    "Run hc login or inject HC_AMS_ADMIN_EMAIL and HC_AMS_ADMIN_PASSWORD into this process."
+                )
+            with HCTenantAdminSDK(environment=target.environment, tenant_id=target.tenant_id) as admin:
+                result = admin.admin.login_tenant_admin(email=email, password=password, tenant_id=target.tenant_id)
+                token = result.get("access_token") if isinstance(result, dict) else None
+                if not isinstance(token, str) or not token.strip():
+                    raise click.ClickException("Tenant-admin login returned no access token; stopped without fallback.")
+        sdk.set_access_token(token)
+        try:
+            yield sdk
+        finally:
+            sdk.set_access_token(None)
+
+    finally:
+        sdk.close()
+
+
+def _saved_session_token(target: AmsTarget | TenantTarget) -> str:
+    with session_lock():
+        # Re-read under the lock: another command may have refreshed while this one waited.
+        session = load_session()
+        if session is None or (target.environment, target.tenant_id) != (session.environment, session.tenant_id):
+            raise click.ClickException("Saved AMS session changed; run hc login.")
+        if not session.needs_refresh(datetime.now(UTC)):
+            return session.access_token
+        try:
+            with HCTenantAdminSDK(environment=target.environment, tenant_id=target.tenant_id) as admin:
+                result = admin.admin.refresh_tenant_admin_token(
+                    refresh_token=session.refresh_token, tenant_id=target.tenant_id
+                )
+        except Exception:
+            raise click.ClickException("Saved AMS session refresh failed; run hc login.") from None
+        session = refreshed_session(session, result, datetime.now(UTC))
+        try:
+            save_session(session)
+        except click.ClickException:
+            # The refresh already succeeded; the old refresh token may be spent. Finish this
+            # command with the new access token and say the saved session is no longer usable.
+            click.echo(
+                "Warning: refreshed AMS session could not be saved; run hc login before the next command.",
+                err=True,
+            )
+        return session.access_token
+
+
+def selected_agent(sdk, target: AmsTarget):
+    agent = sdk.ams_admin.get_agent(target.agent_id)
+    if agent is None or agent.id != target.agent_id or agent.tenant_id != target.tenant_id:
+        raise click.ClickException("Agent/tenant identity mismatch; stopped.")
+    if type(agent.config_version) is not int or agent.config_version < 1:
+        raise click.ClickException("Agent configuration version unavailable; stopped.")
+    return agent

{healthcloud_cli-3.3.0 → healthcloud_cli-3.4.0}/healthcloud_cli/ams/compatibility.py

@@ -71,15 +71,17 @@ def default_dependencies() -> AmsDependencies:
 
 def create_discover_command(dependencies: AmsDependencies) -> click.Command:
     @click.command("discover")
-    @click.option("--environment", type=click.Choice(["dev", "uat", "prod"]), required=True)
-    @click.option("--tenant-id", required=True)
+    @click.option("--environment", type=click.Choice(["dev", "uat", "prod"]))
+    @click.option("--tenant-id")
     @pass_ams
     @safe_errors
     def discover(invocation, environment, tenant_id):
         """Public candidate IDs only; never infer or select an agent."""
         preflight_discovery(invocation)
-        if not tenant_id.strip():
-            raise click.ClickException("Explicit tenant ID required.")
+        from .session import resolve_tenant_target
+
+        target = resolve_tenant_target(environment, tenant_id)
+        environment, tenant_id = target.environment, target.tenant_id
         with dependencies.public_sdk_factory(environment=environment) as sdk:
             agents = sdk.ams.get_agents_for_tenant(tenant_id)
         if not isinstance(agents, dict) or any(

{healthcloud_cli-3.3.0 → healthcloud_cli-3.4.0}/healthcloud_cli/ams/context.py

@@ -134,10 +134,79 @@ def preflight_organization(invocation: AmsContext, target: TenantTarget) -> None
         sdk.close()
 
 
+def preflight_skills(invocation: AmsContext, target: TenantTarget) -> None:
+    """Validate local skill-read compatibility before login or data reads."""
+
+    _check_root(invocation)
+    if invocation.target_file is not None:
+        raise click.ClickException("Skills requires explicit environment/tenant flags, without a target file.")
+    sdk = HCSDK(environment=target.environment, tenant_id=target.tenant_id)
+    try:
+        resource = getattr(getattr(sdk, "ams_admin", None), "skills", None)
+        if (
+            resource is None
+            or not callable(getattr(resource, "list", None))
+            or not callable(getattr(resource, "get", None))
+        ):
+            raise click.ClickException(
+                "SDK missing ams_admin skills; use the reviewed SDK version required by this CLI."
+            )
+    finally:
+        sdk.close()
+
+
+def preflight_policies(invocation: AmsContext, target: TenantTarget) -> None:
+    """Validate local policy-read compatibility before login or data reads."""
+
+    _check_root(invocation)
+    if invocation.target_file is not None:
+        raise click.ClickException("Policies requires explicit environment/tenant flags, without a target file.")
+    sdk = HCSDK(environment=target.environment, tenant_id=target.tenant_id)
+    try:
+        resource = getattr(getattr(sdk, "ams_admin", None), "policies", None)
+        if (
+            resource is None
+            or not callable(getattr(resource, "list", None))
+            or not callable(getattr(resource, "get", None))
+        ):
+            raise click.ClickException(
+                "SDK missing ams_admin policies; use the reviewed SDK version required by this CLI."
+            )
+    finally:
+        sdk.close()
+
+
+def preflight_guardrails(invocation: AmsContext, target: TenantTarget) -> None:
+    """Validate local guardrail-read compatibility before login or data reads."""
+
+    _check_root(invocation)
+    if invocation.target_file is not None:
+        raise click.ClickException("Guardrails requires explicit environment/tenant flags, without a target file.")
+    sdk = HCSDK(environment=target.environment, tenant_id=target.tenant_id)
+    try:
+        resource = getattr(getattr(sdk, "ams_admin", None), "guardrails", None)
+        if (
+            resource is None
+            or not callable(getattr(resource, "list", None))
+            or not callable(getattr(resource, "get", None))
+        ):
+            raise click.ClickException(
+                "SDK missing ams_admin guardrails; use the reviewed SDK version required by this CLI."
+            )
+    finally:
+        sdk.close()
+
+
 def require_target(invocation: AmsContext) -> AmsTarget:
     """Validate root options and load the explicitly selected AMS target."""
 
     _check_root(invocation)
     if invocation.target_file is None:
         raise click.ClickException("AMS requires an explicit --target-file.")
-    return load_target(invocation.target_file)
+    target = load_target(invocation.target_file)
+    from .session import load_session
+
+    session = load_session()
+    if session is not None and (target.environment, target.tenant_id) != (session.environment, session.tenant_id):
+        raise click.ClickException("AMS target does not match the saved session; stopped before authentication.")
+    return target

{healthcloud_cli-3.3.0 → healthcloud_cli-3.4.0}/healthcloud_cli/ams/departments/commands.py

@@ -6,16 +6,16 @@ import click
 
 from ..context import AmsDependencies, pass_ams, preflight_departments
 from ..errors import run_domain
-from ..target import TenantTarget
+from ..session import resolve_tenant_target
 from .operations import get_department, list_departments
 
 
 def _environment(function):
-    return click.option("--environment", type=click.Choice(["dev", "uat", "prod"]), required=True)(function)
+    return click.option("--environment", type=click.Choice(["dev", "uat", "prod"]))(function)
 
 
 def _tenant(function):
-    return click.option("--tenant-id", required=True)(function)
+    return click.option("--tenant-id")(function)
 
 
 def create_list_command(dependencies: AmsDependencies) -> click.Command:
@@ -23,11 +23,12 @@ def create_list_command(dependencies: AmsDependencies) -> click.Command:
     @_environment
     @_tenant
     @pass_ams
-    def command(invocation, environment: str, tenant_id: str) -> None:
+    def command(invocation, environment: str | None, tenant_id: str | None) -> None:
         target_data = {"environment": environment, "tenant_id": tenant_id}
 
         def execute():
-            target = TenantTarget(environment, tenant_id)
+            target = resolve_tenant_target(environment, tenant_id)
+            target_data.update(environment=target.environment, tenant_id=target.tenant_id)
             preflight_departments(invocation, target)
             return list_departments(dependencies, target)
 
@@ -42,7 +43,7 @@ def create_get_command(dependencies: AmsDependencies) -> click.Command:
     @_tenant
     @click.option("--department-id", required=True)
     @pass_ams
-    def command(invocation, environment: str, tenant_id: str, department_id: str) -> None:
+    def command(invocation, environment: str | None, tenant_id: str | None, department_id: str) -> None:
         target_data = {
             "environment": environment,
             "tenant_id": tenant_id,
@@ -50,7 +51,8 @@ def create_get_command(dependencies: AmsDependencies) -> click.Command:
         }
 
         def execute():
-            target = TenantTarget(environment, tenant_id)
+            target = resolve_tenant_target(environment, tenant_id)
+            target_data.update(environment=target.environment, tenant_id=target.tenant_id)
             preflight_departments(invocation, target)
             return get_department(dependencies, target, department_id)
 

{healthcloud_cli-3.3.0 → healthcloud_cli-3.4.0}/healthcloud_cli/ams/errors.py

@@ -28,7 +28,13 @@ _MESSAGE_TEMPLATES = {
 
 def _message(operation: str, category: str) -> str:
     prefix = operation.split(".", 1)[0]
-    domain = {"teams": "Team", "organization": "Organization"}.get(prefix, "Department")
+    domain = {
+        "teams": "Team",
+        "organization": "Organization",
+        "skills": "Skill",
+        "policies": "Policy",
+        "guardrails": "Guardrail",
+    }.get(prefix, "Department")
     return _MESSAGE_TEMPLATES[category].format(domain=domain, domain_lower=domain.lower())
 
 
@@ -38,7 +44,11 @@ def _http_category(operation: str, status: object) -> str:
         403: "authorization",
         409: "conflict",
     }
-    if operation.split(".", 1)[0] in {"teams", "organization"} and status in {400, 404, 422}:
+    if operation.split(".", 1)[0] in {"teams", "organization", "skills", "policies", "guardrails"} and status in {
+        400,
+        404,
+        422,
+    }:
         return "validation"
     return shared_categories.get(status, "transport")
 

healthcloud_cli-3.4.0/healthcloud_cli/ams/guardrails/__init__.py

@@ -0,0 +1,5 @@
+"""Read-only AMS guardrail catalog command domain."""
+
+from .group import create_guardrails_group
+
+__all__ = ["create_guardrails_group"]