mammoth-cli 2.2.80__tar.gz → 2.2.82__tar.gz

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mammoth-cli
-Version: 2.2.80
+Version: 2.2.82
 Summary: Command-line interface for the Mammoth Analytics platform
 Project-URL: homepage, https://mammoth.io
 Project-URL: repository, https://github.com/EdgeMetric/mammothsdk
@@ -69,7 +69,7 @@ mammoth --version
 
 The installer bootstraps its own `uv` tool environment when needed and installs
 the bundled agent skill. For an exact, reproducible release use `--version
-X.Y.Z`; the installer has no normal prompts. See
+X.Y.Z` (a pinned install is not auto-updated); the installer has no normal prompts. See
 [Installation](https://github.com/EdgeMetric/mammothsdk/blob/main/mammoth-cli/docs/installation.md) for that option and the SDK-only pip
 installation path.
 
@@ -245,14 +245,17 @@ mammoth skill install --input '{"agents": ["codex"], "scope": "project"}'
 Use `mammoth skill update` after a CLI upgrade. It refreshes copies owned by the
 installer and reports modified copies instead of silently replacing them.
 
-The CLI keeps itself up to date. At most once a day, after a command has
+In an interactive terminal the CLI keeps itself up to date. At most once a day, after a command has
 finished and written its output, a detached process asks PyPI and installs a
 newer release through the same package manager as `mammoth upgrade`. It never
 delays or fails a command, prints nothing, and writes any failure to the run
 log. `meta.update_available` (and the stderr line in human output) appears only
-when a newer release exists and will not be installed by itself. Set
-`MAMMOTH_NO_AUTO_UPDATE=1` to keep the check but never install (CI, containers,
-pinned environments), or `MAMMOTH_NO_UPDATE_CHECK=1` to turn the check off (see
+when a newer release exists and will not be installed by itself (auto-update off,
+a pinned install, a failed install, or a session that is not interactive). Nothing
+is installed in CI (`CI`, `GITHUB_ACTIONS`, `GITLAB_CI`, ...) or when stdin or
+stdout is not a terminal (agents, pipes); the check and the hint still run there.
+`MAMMOTH_AUTO_UPGRADE=1` forces the install on anyway, `MAMMOTH_NO_AUTO_UPDATE=1`
+keeps the check but never installs, or `MAMMOTH_NO_UPDATE_CHECK=1` to turn the check off (see
 [Upgrade](https://github.com/EdgeMetric/mammothsdk/blob/main/mammoth-cli/docs/upgrade.md)).
 
 ## What you can do

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/README.md

@@ -40,7 +40,7 @@ mammoth --version
 
 The installer bootstraps its own `uv` tool environment when needed and installs
 the bundled agent skill. For an exact, reproducible release use `--version
-X.Y.Z`; the installer has no normal prompts. See
+X.Y.Z` (a pinned install is not auto-updated); the installer has no normal prompts. See
 [Installation](https://github.com/EdgeMetric/mammothsdk/blob/main/mammoth-cli/docs/installation.md) for that option and the SDK-only pip
 installation path.
 
@@ -216,14 +216,17 @@ mammoth skill install --input '{"agents": ["codex"], "scope": "project"}'
 Use `mammoth skill update` after a CLI upgrade. It refreshes copies owned by the
 installer and reports modified copies instead of silently replacing them.
 
-The CLI keeps itself up to date. At most once a day, after a command has
+In an interactive terminal the CLI keeps itself up to date. At most once a day, after a command has
 finished and written its output, a detached process asks PyPI and installs a
 newer release through the same package manager as `mammoth upgrade`. It never
 delays or fails a command, prints nothing, and writes any failure to the run
 log. `meta.update_available` (and the stderr line in human output) appears only
-when a newer release exists and will not be installed by itself. Set
-`MAMMOTH_NO_AUTO_UPDATE=1` to keep the check but never install (CI, containers,
-pinned environments), or `MAMMOTH_NO_UPDATE_CHECK=1` to turn the check off (see
+when a newer release exists and will not be installed by itself (auto-update off,
+a pinned install, a failed install, or a session that is not interactive). Nothing
+is installed in CI (`CI`, `GITHUB_ACTIONS`, `GITLAB_CI`, ...) or when stdin or
+stdout is not a terminal (agents, pipes); the check and the hint still run there.
+`MAMMOTH_AUTO_UPGRADE=1` forces the install on anyway, `MAMMOTH_NO_AUTO_UPDATE=1`
+keeps the check but never installs, or `MAMMOTH_NO_UPDATE_CHECK=1` to turn the check off (see
 [Upgrade](https://github.com/EdgeMetric/mammothsdk/blob/main/mammoth-cli/docs/upgrade.md)).
 
 ## What you can do

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/mammoth_cli/__init__.py

@@ -6,7 +6,7 @@ not implement a second HTTP client and does not call private SDK members.
 
 from __future__ import annotations
 
-__version__ = "2.2.80"
+__version__ = "2.2.82"
 
 # The versioned machine output envelope contract.
 SCHEMA_VERSION = 1

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/mammoth_cli/app.py

@@ -357,6 +357,10 @@ def _output_mode_from_argv(argv: Sequence[str] | None) -> str:
         elif token.startswith("-o") and len(token) > 2:
             mode = token[2:]
         index += 1
+    if mode not in SELECTABLE_OUTPUTS:
+        # A value the command would reject (``--output xml``) must not turn the
+        # error into prose: judge it by where stdout goes, like the default.
+        mode = OUTPUT_AUTO
     return resolve_output(mode, is_tty=sys.stdout.isatty())
 
 
@@ -940,6 +944,18 @@ def _shared_option_params() -> list[inspect.Parameter]:
                 ),
             ],
         ),
+        opt(
+            "overwrite",
+            False,
+            Annotated[
+                bool,
+                typer.Option(
+                    "--overwrite",
+                    help="Replace a local file the command writes to when it already exists.",
+                    rich_help_panel="Safety",
+                ),
+            ],
+        ),
         opt(
             "standing",
             False,
@@ -1079,6 +1095,7 @@ def _execute(invocation: Invocation) -> None:
     # resolving the mutable selected-profile pointer after an interrupt.
     from mammoth_cli.context import profiles
     from mammoth_cli.runtime import executor, validate
+    from mammoth_cli.runtime.confirm import refuse_mismatched_confirm
     from mammoth_cli.runtime.dataset_health import with_dataset_health
     from mammoth_cli.runtime.intent_only import refuse_hand_crafted_write
     from mammoth_cli.runtime.locked_files import with_locked_files
@@ -1094,6 +1111,7 @@ def _execute(invocation: Invocation) -> None:
         validate.validate_invocation(invocation)
         validate_extra_args(invocation.command_id, invocation.extra_args)
         validate.validate_positional_ids(invocation.command_id, invocation.extra_args)
+        refuse_mismatched_confirm(invocation)
         # Admit structured input before resolving a handler or opening a
         # service.  Handlers retain ``load_input`` for compatibility, but it
         # now returns this invocation-local prepared value.
@@ -1607,7 +1625,7 @@ _ROOT_LEAF_HELP: dict[str, str] = {
     ),
     "upgrade": (
         "Upgrade the mammoth CLI to the latest (or a specified) version from PyPI."
-        "\n\nExample: mammoth upgrade"
+        "\n\nExample: mammoth upgrade --yes"
     ),
     "version": "Example: mammoth version",
 }

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/mammoth_cli/bundled_skill/mammoth-cli/SKILL.md

@@ -32,9 +32,11 @@ mammoth project ensure 'PROJECT NAME'   # active project
 Never proceed if `doctor` fails.
 On a 502, 504 or timeout, `mammoth doctor --input '{"wait": 300}'`
 re-probes that long; continue once it passes. Production is the `app` endpoint; use `release` only
-when named, and check `meta.profile`/`auth status` `endpoint` match. If no profile has credentials, run `mammoth auth login --device` (`--profile NAME`), show the user its
-link and code and wait for it to exit ([auth](references/auth.md)). Run no other login
-method, and never ask for the token in chat or read one from a file/env var. If an envelope carries `meta.update_available`, run its `command` first.
+when named, and check `meta.profile`/`auth status` `endpoint` match. With no credentials,
+run `mammoth auth login --device` (`--profile NAME`), show the user its link and code;
+wait for it to exit ([auth](references/auth.md)); never ask for a token in chat, read one from
+a file/env var, or use another login. If an envelope carries
+`meta.update_available`, run its `command` first unless `--version` is pinned.
 
 Piped stdout is compact JSON with prompts off; if not piped, `export
 MAMMOTH_OUTPUT=json MAMMOTH_NO_INPUT=1` once.
@@ -171,7 +173,7 @@ your report. If no column links the files, ask before you combine them.
   unmatched) means the previous step went wrong; stop and re-inspect it.
 - `column_warnings` on a data read and `join_check` on a join are findings,
   not decoration: fix each the deliverable depends on, or say why kept.
-  `view data get` pages with `{"offset": 51, "limit": 50}`.
+  `view data get` pages with `{"offset": 50, "limit": 50}` (`paging.next_command`).
 - A timeout, exit 7 or interruption does not prove failure; reconcile an
   `outcome_unknown` (`job get`, `view task list`) before replaying.
 - Check an answer with no write against the question (a trend: time

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/mammoth_cli/bundled_skill/mammoth-cli/references/commands/addon.md

@@ -6,7 +6,7 @@ Every command returns the standard JSON envelope. On nonzero exit, read the erro
 
 Run: `mammoth addon connector add`. Exact input fields: `mammoth schema get addon.connector.add`.
 
-Example: `mammoth addon connector add --input '{"connector_id": 42}'`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
+Example: `mammoth addon connector add --input '{"connector_id": 42}' --yes`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
 
 Result: `AddonConnectorAddResult`; mutation `high_impact`, confirmation `confirm_target`, wait policy `not_async`.
 
@@ -16,7 +16,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth addon connector remove`. Exact input fields: `mammoth schema get addon.connector.remove`.
 
-Example: `mammoth addon connector remove --input '{"connector_id": 42}'`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
+Example: `mammoth addon connector remove --input '{"connector_id": 42}' --yes`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
 
 Result: `AddonConnectorRemoveResult`; mutation `high_impact`, confirmation `confirm_target`, wait policy `not_async`.
 
@@ -36,7 +36,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth addon storage add`. Exact input fields: `mammoth schema get addon.storage.add`.
 
-Example: `mammoth addon storage add --input '{"additional_storage_gb": 1}'`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
+Example: `mammoth addon storage add --input '{"additional_storage_gb": 1}' --yes`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
 
 Result: `AddonStorageAddResult`; mutation `high_impact`, confirmation `confirm_target`, wait policy `not_async`.
 
@@ -46,7 +46,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth addon storage remove`. Exact input fields: `mammoth schema get addon.storage.remove`.
 
-Example: `mammoth addon storage remove --input '{"removal_storage_gb": 1}'`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
+Example: `mammoth addon storage remove --input '{"removal_storage_gb": 1}' --yes`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
 
 Result: `AddonStorageRemoveResult`; mutation `high_impact`, confirmation `confirm_target`, wait policy `not_async`.
 
@@ -56,7 +56,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth addon user add`. Exact input fields: `mammoth schema get addon.user.add`.
 
-Example: `mammoth addon user add`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
+Example: `mammoth addon user add --yes`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
 
 Result: `AddonUserAddResult`; mutation `high_impact`, confirmation `confirm_target`, wait policy `not_async`.
 
@@ -66,7 +66,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth addon user remove`. Exact input fields: `mammoth schema get addon.user.remove`.
 
-Example: `mammoth addon user remove --input '{"user_count": 1}'`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
+Example: `mammoth addon user remove --input '{"user_count": 1}' --yes`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
 
 Result: `AddonUserRemoveResult`; mutation `high_impact`, confirmation `confirm_target`, wait policy `not_async`.
 

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/mammoth_cli/bundled_skill/mammoth-cli/references/commands/agent.md

@@ -6,7 +6,7 @@ Every command returns the standard JSON envelope. On nonzero exit, read the erro
 
 Run: `mammoth agent access set`. Exact input fields: `mammoth schema get agent.access.set`.
 
-Example: `mammoth agent access set sample --input '{"role": "member", "propose": true}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent access set revenue-assistant --input '{"role": "member", "propose": true}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentAccessSetResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -16,7 +16,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent action delete`. Exact input fields: `mammoth schema get agent.action.delete`.
 
-Example: `mammoth agent action delete resource-123`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth agent action delete resource-123 --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AgentActionDeleteResult`; mutation `destructive`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -36,7 +36,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent charter get`. Exact input fields: `mammoth schema get agent.charter.get`.
 
-Example: `mammoth agent charter get sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent charter get revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentCharterGetResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 
@@ -46,7 +46,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent charter restore`. Exact input fields: `mammoth schema get agent.charter.restore`.
 
-Example: `mammoth agent charter restore sample 123`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent charter restore revenue-assistant 123`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentCharterRestoreResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -56,7 +56,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent charter set`. Exact input fields: `mammoth schema get agent.charter.set`.
 
-Example: `mammoth agent charter set sample --input '{"charter": "Watch weekly margin and report the three biggest drops."}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent charter set revenue-assistant --input '{"charter": "Watch weekly margin and report the three biggest drops."}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentCharterSetResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -66,7 +66,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent charter versions`. Exact input fields: `mammoth schema get agent.charter.versions`.
 
-Example: `mammoth agent charter versions sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent charter versions revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentCharterVersionsResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 
@@ -96,7 +96,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent delete`. Exact input fields: `mammoth schema get agent.delete`.
 
-Example: `mammoth agent delete sample`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth agent delete revenue-assistant --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AgentDeleteResult`; mutation `destructive`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -106,7 +106,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent disable`. Exact input fields: `mammoth schema get agent.disable`.
 
-Example: `mammoth agent disable sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent disable revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentDisableResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -116,7 +116,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent feedback list`. Exact input fields: `mammoth schema get agent.feedback.list`.
 
-Example: `mammoth agent feedback list sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent feedback list revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentFeedbackListResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 
@@ -126,7 +126,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent get`. Exact input fields: `mammoth schema get agent.get`.
 
-Example: `mammoth agent get sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent get revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentGetResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 
@@ -136,7 +136,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent goldens add`. Exact input fields: `mammoth schema get agent.goldens.add`.
 
-Example: `mammoth agent goldens add sample --input '{"question": "Summarize revenue by region", "expected": "sample"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent goldens add revenue-assistant --input '{"question": "Summarize revenue by region", "expected": "Quarterly revenue summary"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentGoldensAddResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -146,7 +146,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent goldens list`. Exact input fields: `mammoth schema get agent.goldens.list`.
 
-Example: `mammoth agent goldens list sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent goldens list revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentGoldensListResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 
@@ -156,7 +156,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent goldens remove`. Exact input fields: `mammoth schema get agent.goldens.remove`.
 
-Example: `mammoth agent goldens remove sample 123`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth agent goldens remove revenue-assistant 123 --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AgentGoldensRemoveResult`; mutation `destructive`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -166,7 +166,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent goldens run`. Exact input fields: `mammoth schema get agent.goldens.run`.
 
-Example: `mammoth agent goldens run sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent goldens run revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentGoldensRunResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -176,7 +176,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent goldens status`. Exact input fields: `mammoth schema get agent.goldens.status`.
 
-Example: `mammoth agent goldens status sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent goldens status revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentGoldensStatusResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 
@@ -196,7 +196,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent memory add`. Exact input fields: `mammoth schema get agent.memory.add`.
 
-Example: `mammoth agent memory add sample --input '{"name": "Revenue report", "content": "sample"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent memory add revenue-assistant --input '{"name": "Revenue report", "content": "Quarterly revenue summary"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentMemoryAddResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -206,7 +206,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent memory list`. Exact input fields: `mammoth schema get agent.memory.list`.
 
-Example: `mammoth agent memory list sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent memory list revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentMemoryListResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 
@@ -216,7 +216,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent memory remove`. Exact input fields: `mammoth schema get agent.memory.remove`.
 
-Example: `mammoth agent memory remove sample 123`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth agent memory remove revenue-assistant 123 --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AgentMemoryRemoveResult`; mutation `destructive`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -226,7 +226,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent message set-request-kind`. Exact input fields: `mammoth schema get agent.message.set-request-kind`.
 
-Example: `mammoth agent message set-request-kind 'Summarize revenue by region' --input '{"request_kind": "sample"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent message set-request-kind 'Summarize revenue by region' --input '{"request_kind": "ask"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentMessageSetRequestKindResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -236,7 +236,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent plan approve`. Exact input fields: `mammoth schema get agent.plan.approve`.
 
-Example: `mammoth agent plan approve resource-123`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth agent plan approve resource-123 --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AgentPlanApproveResult`; mutation `benign_mutation`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -246,9 +246,9 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent plan discard`. Exact input fields: `mammoth schema get agent.plan.discard`.
 
-Example: `mammoth agent plan discard resource-123`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent plan discard resource-123 --yes`. Illustrative only: append `--yes` after observing an owned target.
 
-Result: `AgentPlanDiscardResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
+Result: `AgentPlanDiscardResult`; mutation `benign_mutation`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
 Status on release: untried; no live run recorded.
 
@@ -256,7 +256,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent plan edit-proposal`. Exact input fields: `mammoth schema get agent.plan.edit-proposal`.
 
-Example: `mammoth agent plan edit-proposal --input '{"plan_id": "resource-123", "action": "sample", "key": "Status"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent plan edit-proposal --input '{"plan_id": "resource-123", "action": "rename", "key": "Status"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentPlanEditProposalResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -276,9 +276,9 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent projects clear`. Exact input fields: `mammoth schema get agent.projects.clear`.
 
-Example: `mammoth agent projects clear sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent projects clear revenue-assistant --yes`. Illustrative only: append `--yes` after observing an owned target.
 
-Result: `AgentProjectsClearResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
+Result: `AgentProjectsClearResult`; mutation `benign_mutation`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
 Status on release: untried; no live run recorded.
 
@@ -286,7 +286,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent projects set`. Exact input fields: `mammoth schema get agent.projects.set`.
 
-Example: `mammoth agent projects set sample --input '{"project_ids": [12, 15]}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent projects set revenue-assistant --input '{"project_ids": [12, 15]}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentProjectsSetResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -296,7 +296,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent publish`. Exact input fields: `mammoth schema get agent.publish`.
 
-Example: `mammoth agent publish sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent publish revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentPublishResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -386,7 +386,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent run retry`. Exact input fields: `mammoth schema get agent.run.retry`.
 
-Example: `mammoth agent run retry resource-123`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth agent run retry resource-123 --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AgentRunRetryResult`; mutation `benign_mutation`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -426,7 +426,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent run units set`. Exact input fields: `mammoth schema get agent.run.units.set`.
 
-Example: `mammoth agent run units set resource-123 --input '{"step": 1, "kind": "sample", "units": [{"sample_key": "Status"}]}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent run units set resource-123 --input '{"step": 1, "kind": "dataset", "units": [{"id": 12, "name": "Sales", "project_id": 3}]}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentRunUnitsSetResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -436,7 +436,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent scratch clear`. Exact input fields: `mammoth schema get agent.scratch.clear`.
 
-Example: `mammoth agent scratch clear sample 'Revenue report'`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth agent scratch clear revenue-assistant 'Revenue report' --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AgentScratchClearResult`; mutation `destructive`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -446,7 +446,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent scratch get`. Exact input fields: `mammoth schema get agent.scratch.get`.
 
-Example: `mammoth agent scratch get sample 'Revenue report'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent scratch get revenue-assistant 'Revenue report'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentScratchGetResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 
@@ -456,7 +456,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent scratch list`. Exact input fields: `mammoth schema get agent.scratch.list`.
 
-Example: `mammoth agent scratch list sample`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent scratch list revenue-assistant`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentScratchListResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 
@@ -466,7 +466,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent scratch set`. Exact input fields: `mammoth schema get agent.scratch.set`.
 
-Example: `mammoth agent scratch set sample 'Revenue report' --input '{"content": "sample"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent scratch set revenue-assistant 'Revenue report' --input '{"content": "Quarterly revenue summary"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentScratchSetResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -476,7 +476,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent session delete`. Exact input fields: `mammoth schema get agent.session.delete`.
 
-Example: `mammoth agent session delete resource-123`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth agent session delete resource-123 --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AgentSessionDeleteResult`; mutation `destructive`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -506,7 +506,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent session set-visibility`. Exact input fields: `mammoth schema get agent.session.set-visibility`.
 
-Example: `mammoth agent session set-visibility resource-123 --input '{"visibility": "sample"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent session set-visibility resource-123 --input '{"visibility": "shared"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentSessionSetVisibilityResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -516,7 +516,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent team set`. Exact input fields: `mammoth schema get agent.team.set`.
 
-Example: `mammoth agent team set sample --input '{"team": {"agents": ["margin-watch"], "max_rounds": 4}}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent team set revenue-assistant --input '{"team": {"agents": ["margin-watch"], "max_rounds": 4}}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentTeamSetResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -536,7 +536,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth agent update`. Exact input fields: `mammoth schema get agent.update`.
 
-Example: `mammoth agent update sample --input '{"name": "Margin watch"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth agent update revenue-assistant --input '{"name": "Margin watch"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AgentUpdateResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/mammoth_cli/bundled_skill/mammoth-cli/references/commands/ai.md

@@ -16,7 +16,7 @@ Status on release: ran once on CLI 2.0.14 — write sweep 2026-09-18: exit 0 on
 
 Run: `mammoth ai expression generate`. Exact input fields: `mammoth schema get ai.expression.generate`.
 
-Example: `mammoth ai expression generate 123 --input '{"intent": "Summarize revenue by region", "mode": "sample"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth ai expression generate 123 --input '{"intent": "Summarize revenue by region", "mode": "math"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AiExpressionGenerateResult`; mutation `read`, confirmation `none`, wait policy `not_async`.
 

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/mammoth_cli/bundled_skill/mammoth-cli/references/commands/annotation.md

@@ -6,7 +6,7 @@ Every command returns the standard JSON envelope. On nonzero exit, read the erro
 
 Run: `mammoth annotation comment add`. Exact input fields: `mammoth schema get annotation.comment.add`.
 
-Example: `mammoth annotation comment add 123 --input '{"body": "sample"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth annotation comment add 123 --input '{"body": "Quarterly revenue summary"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AnnotationCommentAddResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -16,7 +16,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth annotation create`. Exact input fields: `mammoth schema get annotation.create`.
 
-Example: `mammoth annotation create --input '{"target_type": "sample", "target_id": 1, "body": "sample"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth annotation create --input '{"target_type": "dataview", "target_id": 1, "body": "Quarterly revenue summary"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AnnotationCreateResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 
@@ -26,7 +26,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth annotation delete`. Exact input fields: `mammoth schema get annotation.delete`.
 
-Example: `mammoth annotation delete 123`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth annotation delete 123 --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AnnotationDeleteResult`; mutation `destructive`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -46,7 +46,7 @@ Status on release: ran once on CLI 1.1.10 — Bounded release read with publishe
 
 Run: `mammoth annotation update`. Exact input fields: `mammoth schema get annotation.update`.
 
-Example: `mammoth annotation update 123 --input '{"status": "sample"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
+Example: `mammoth annotation update 123 --input '{"status": "resolved"}'`. Placeholders are illustrative; resolve IDs and input from observed reads.
 
 Result: `AnnotationUpdateResult`; mutation `benign_mutation`, confirmation `none`, wait policy `not_async`.
 

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/mammoth_cli/bundled_skill/mammoth-cli/references/commands/auth.md

@@ -16,7 +16,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth auth connected-apps revoke`. Exact input fields: `mammoth schema get auth.connected-apps.revoke`.
 
-Example: `mammoth auth connected-apps revoke 123`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
+Example: `mammoth auth connected-apps revoke 123 --yes --confirm 123`. Illustrative only: append `--yes --confirm <EXACT_TARGET>` after observing the target.
 
 Result: `AuthConnectedAppsRevokeResult`; mutation `high_impact`, confirmation `confirm_target`, wait policy `not_async`.
 

{mammoth_cli-2.2.80 → mammoth_cli-2.2.82}/mammoth_cli/bundled_skill/mammoth-cli/references/commands/automation.md

@@ -16,7 +16,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth automation create`. Exact input fields: `mammoth schema get automation.create`.
 
-Example: `mammoth automation create 'Revenue report' --input '{"description": "sample", "tasks": [{"task_type": "run_data_retrieval"}]}'`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth automation create 'Revenue report' --input '{"description": "Quarterly revenue summary", "tasks": [{"task_type": "run_data_retrieval", "details": {"ds_details": [{"ds_id": 42}]}}]}' --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AutomationCreateResult`; mutation `external_effect`, confirmation `yes_always`, wait policy `not_async`.
 
@@ -26,7 +26,7 @@ Status on release: ran once on CLI 2.0.18 — fixture-lifecycle sweep 2026-09-19
 
 Run: `mammoth automation delete`. Exact input fields: `mammoth schema get automation.delete`.
 
-Example: `mammoth automation delete 123`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth automation delete 123 --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AutomationDeleteResult`; mutation `destructive`, confirmation `prompt_or_yes`, wait policy `not_async`.
 
@@ -76,7 +76,7 @@ Status on release: untried; no live run recorded.
 
 Run: `mammoth automation update`. Exact input fields: `mammoth schema get automation.update`.
 
-Example: `mammoth automation update 123 --input '{"patch": [{"op": "replace", "path": "details", "value": "sample"}]}'`. Illustrative only: append `--yes` after observing an owned target.
+Example: `mammoth automation update 123 --input '{"patch": [{"op": "replace", "path": "details", "value": {"name": "Daily revenue export"}}]}' --yes`. Illustrative only: append `--yes` after observing an owned target.
 
 Result: `AutomationUpdateResult`; mutation `external_effect`, confirmation `yes_always`, wait policy `not_async`.