codeer-cli 0.1.1__tar.gz → 0.1.2__tar.gz

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/.gitignore

@@ -35,3 +35,4 @@ Thumbs.db
 
 # Local assistant/tool settings
 .claude/settings.local.json
+.codeer/

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codeer-cli
-Version: 0.1.1
+Version: 0.1.2
 Summary: Command line tools for managing Codeer agents over the Codeer API.
 Project-URL: Homepage, https://www.codeer.ai
 Author: Codeer.AI
@@ -22,25 +22,35 @@ Standalone CLI for managing Codeer agents over the Codeer API.
 
 ## User install
 
-After the package is published to PyPI, install the CLI as an isolated command
-line tool:
+Install the CLI from PyPI with `pipx`:
 
 ```bash
-uv tool install codeer-cli
+pipx install codeer-cli
 ```
 
-Until the package is published, install directly from this repository:
+Verify that the command is available:
 
 ```bash
-uv tool install 'git+https://github.com/<org>/codeer-skills.git#subdirectory=codeer-cli'
+codeer --help
 ```
 
-Replace `<org>` with the GitHub organization or user that hosts this repository.
+If `pipx` is not installed:
 
-Verify that the command is available:
+```bash
+python -m pip install --user pipx
+python -m pipx ensurepath
+```
+
+Then restart the terminal and run:
 
 ```bash
-codeer --help
+pipx install codeer-cli
+```
+
+As a fallback, you can install into your user Python environment:
+
+```bash
+python -m pip install --user codeer-cli
 ```
 
 ## Credentials
@@ -107,6 +117,21 @@ Validate setup before API work:
 codeer check
 ```
 
+## Upgrade and uninstall
+
+Upgrade the CLI:
+
+```bash
+pipx upgrade codeer-cli
+codeer check
+```
+
+Remove the CLI:
+
+```bash
+pipx uninstall codeer-cli
+```
+
 ## Output policy for coding agents
 
 The CLI is optimized for Codex, Claude Code, Claude Cowork, and similar coding
@@ -133,6 +158,28 @@ Avoid piping large raw JSON directly into agent chat. Prefer `--out`, then ask
 the coding agent to inspect targeted summaries, IDs, failing cases, or selected
 snippets from the saved file.
 
+## Website crawler KBs
+
+Website-backed KB folders can be created and updated with `codeer kb crawl-*`.
+Always preview crawler mutations with `--dry-run` first:
+
+```bash
+codeer kb crawl-create \
+    --url https://example.com/docs \
+    --folder-name "Product Docs" \
+    --include-path "/docs*" \
+    --exclude-path "/docs/private*" \
+    --limit 250 \
+    --max-depth 3 \
+    --only-main-content \
+    --dry-run
+```
+
+`--include-path` and `--exclude-path` are repeatable clean path patterns. Quote
+paths containing `*` so the shell passes the wildcard to the CLI. Advanced
+settings can still be passed through `--config-json`; explicit crawler flags
+override matching JSON keys.
+
 ## Context Object FAQ
 
 Use Context Object FAQ entries to route high-value questions to a canonical KB

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/README.md

@@ -4,25 +4,35 @@ Standalone CLI for managing Codeer agents over the Codeer API.
 
 ## User install
 
-After the package is published to PyPI, install the CLI as an isolated command
-line tool:
+Install the CLI from PyPI with `pipx`:
 
 ```bash
-uv tool install codeer-cli
+pipx install codeer-cli
 ```
 
-Until the package is published, install directly from this repository:
+Verify that the command is available:
 
 ```bash
-uv tool install 'git+https://github.com/<org>/codeer-skills.git#subdirectory=codeer-cli'
+codeer --help
 ```
 
-Replace `<org>` with the GitHub organization or user that hosts this repository.
+If `pipx` is not installed:
 
-Verify that the command is available:
+```bash
+python -m pip install --user pipx
+python -m pipx ensurepath
+```
+
+Then restart the terminal and run:
 
 ```bash
-codeer --help
+pipx install codeer-cli
+```
+
+As a fallback, you can install into your user Python environment:
+
+```bash
+python -m pip install --user codeer-cli
 ```
 
 ## Credentials
@@ -89,6 +99,21 @@ Validate setup before API work:
 codeer check
 ```
 
+## Upgrade and uninstall
+
+Upgrade the CLI:
+
+```bash
+pipx upgrade codeer-cli
+codeer check
+```
+
+Remove the CLI:
+
+```bash
+pipx uninstall codeer-cli
+```
+
 ## Output policy for coding agents
 
 The CLI is optimized for Codex, Claude Code, Claude Cowork, and similar coding
@@ -115,6 +140,28 @@ Avoid piping large raw JSON directly into agent chat. Prefer `--out`, then ask
 the coding agent to inspect targeted summaries, IDs, failing cases, or selected
 snippets from the saved file.
 
+## Website crawler KBs
+
+Website-backed KB folders can be created and updated with `codeer kb crawl-*`.
+Always preview crawler mutations with `--dry-run` first:
+
+```bash
+codeer kb crawl-create \
+    --url https://example.com/docs \
+    --folder-name "Product Docs" \
+    --include-path "/docs*" \
+    --exclude-path "/docs/private*" \
+    --limit 250 \
+    --max-depth 3 \
+    --only-main-content \
+    --dry-run
+```
+
+`--include-path` and `--exclude-path` are repeatable clean path patterns. Quote
+paths containing `*` so the shell passes the wildcard to the CLI. Advanced
+settings can still be passed through `--config-json`; explicit crawler flags
+override matching JSON keys.
+
 ## Context Object FAQ
 
 Use Context Object FAQ entries to route high-value questions to a canonical KB

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "codeer-cli"
-version = "0.1.1"
+version = "0.1.2"
 description = "Command line tools for managing Codeer agents over the Codeer API."
 readme = "README.md"
 requires-python = ">=3.11"

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/src/codeer_cli/agents.py

@@ -153,3 +153,8 @@ def get_version(client: CodeerClient, agent_id: str, history_id: str) -> dict:
 def check_impact(client: CodeerClient, agent_id: str) -> dict:
     """List downstream agents that call this one. Call before publishing breaking changes."""
     return client.get(f"/external/agents/{agent_id}/impact")
+
+
+def publish_version(client: CodeerClient, agent_id: str, history_id: str) -> dict:
+    """Promote one AgentHistory version to the published runtime version."""
+    return client.post(f"/external/agents/{agent_id}/versions/{history_id}:publish", json={})

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/src/codeer_cli/client.py

@@ -85,8 +85,7 @@ class CodeerClient:
         if not api_key:
             raise AuthError(
                 0,
-                "Missing API key. Export CODEER_API_KEY or run `codeer profile add <name>` "
-                "and `codeer profile use <name>`.",
+                "Missing API key. Export CODEER_API_KEY or run `codeer profile add <name>`.",
             )
 
         overrides.pop("workspace_id", None)

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/src/codeer_cli/commands/agent.py

@@ -69,6 +69,21 @@ def register(subparsers):
                    help="Write stripped full version snapshots to this file; stdout stays compact.")
     p.set_defaults(func=run_versions)
 
+    p = sub.add_parser("impact", help="Check downstream agents affected by this agent")
+    p.add_argument("--agent", required=True)
+    p.add_argument("--out", default=None, help="Write full impact detail to this file too")
+    p.set_defaults(func=run_impact)
+
+    p = sub.add_parser("publish", help="Publish an agent version; run --dry-run first")
+    p.add_argument("--agent", required=True)
+    g = p.add_mutually_exclusive_group(required=True)
+    g.add_argument("--history", default=None, help="AgentHistory UUID to publish")
+    g.add_argument("--version", type=int, default=None, help="AgentHistory version_number to publish")
+    p.add_argument("--dry-run", action="store_true",
+                   help="Resolve target version and print intended mutation without writing server state.")
+    p.add_argument("--out", default=None, help="Write result JSON to this file too")
+    p.set_defaults(func=run_publish)
+
 
 def _tool_summary(tools: list[dict] | None) -> list[dict]:
     out = []
@@ -229,6 +244,62 @@ def run_versions(args, client) -> int:
     return 0
 
 
+def run_impact(args, client) -> int:
+    result = strip_noisy_fields(agents_mod.check_impact(client, args.agent))
+    write_json(args.out, result)
+    print_json(result)
+    return 0
+
+
+def _resolve_history_for_publish(
+    client: CodeerClient,
+    agent_id: str,
+    history_id: Optional[str],
+    version: Optional[int],
+) -> dict:
+    if history_id:
+        return agents_mod.get_version(client, agent_id, history_id)
+    if version is not None:
+        for candidate in agents_mod.list_versions(client, agent_id):
+            if candidate.get("version_number") == version:
+                return agents_mod.get_version(client, agent_id, candidate["id"])
+        raise SystemExit(f"no version {version} on agent {agent_id}")
+    raise SystemExit("must pass --history or --version")
+
+
+def run_publish(args, client) -> int:
+    history = _resolve_history_for_publish(client, args.agent, args.history, args.version)
+    history_id = history["id"]
+    summary = {
+        "agent_id": args.agent,
+        "history_id": history_id,
+        "version_number": history.get("version_number"),
+        "status": history.get("status"),
+        "was_published": history.get("was_published"),
+        "version_note": history.get("version_note") or "",
+    }
+
+    if args.dry_run:
+        result = {
+            "dry_run": True,
+            "operation": "agent_publish",
+            "method": "POST",
+            "path": f"/external/agents/{args.agent}/versions/{history_id}:publish",
+            "target": summary,
+            "would_write_server_state": True,
+            "next_step": "Review this summary, then rerun without --dry-run after approval.",
+        }
+        print_json(result)
+        write_json(args.out, result)
+        return 0
+
+    result = strip_noisy_fields(agents_mod.publish_version(client, args.agent, history_id))
+    output = {"target": summary, "response": result}
+    print_json(output)
+    write_json(args.out, output)
+    return 0
+
+
 
 # --- diff helpers ---
 

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/src/codeer_cli/commands/kb.py

@@ -11,6 +11,42 @@ POLL_INTERVAL = 3
 POLL_TIMEOUT = 600
 
 
+def _add_crawl_config_args(parser):
+    parser.add_argument("--config-json", default=None, help="JSON object for crawl_config")
+    parser.add_argument("--limit", type=int, default=None, help="Maximum pages to crawl (backend max: 5000)")
+    parser.add_argument("--max-depth", type=int, default=None, help="Maximum crawl depth (backend max: 10)")
+    parser.add_argument(
+        "--include-path",
+        action="append",
+        dest="include_paths",
+        default=None,
+        help="Clean path pattern to include; repeatable. Supports * wildcards.",
+    )
+    parser.add_argument(
+        "--exclude-path",
+        action="append",
+        dest="exclude_paths",
+        default=None,
+        help="Clean path pattern to exclude; repeatable. Supports * wildcards.",
+    )
+    parser.add_argument("--allow-subdomains", action="store_true", default=None,
+                        help="Allow crawling subdomains of the start URL host")
+    parser.add_argument("--allow-external-links", action="store_true", default=None,
+                        help="Allow crawling links outside the start URL host")
+    parser.add_argument("--ignore-query-parameters", action="store_true", dest="ignore_query_parameters", default=None,
+                        help="Treat URLs that differ only by query string as the same page")
+    parser.add_argument("--use-query-parameters", action="store_false", dest="ignore_query_parameters",
+                        help="Treat URLs with different query strings as distinct pages")
+    parser.add_argument("--ignore-sitemap", action="store_true", dest="ignore_sitemap", default=None,
+                        help="Skip sitemap discovery")
+    parser.add_argument("--use-sitemap", action="store_false", dest="ignore_sitemap",
+                        help="Allow sitemap discovery")
+    parser.add_argument("--only-main-content", action="store_true", dest="only_main_content", default=None,
+                        help="Extract only the main content area")
+    parser.add_argument("--include-page-chrome", action="store_false", dest="only_main_content",
+                        help="Keep page navigation, footer, and other chrome")
+
+
 def register(subparsers):
     k = subparsers.add_parser("kb", help="Knowledge base operations")
     sub = k.add_subparsers(dest="action", required=True)
@@ -92,6 +128,51 @@ def register(subparsers):
     p.add_argument("--out", default=None, help="Write result JSON to this file too")
     p.set_defaults(func=run_faq_delete)
 
+    p = sub.add_parser("crawl-create", help="Create a website-crawler KB folder; run --dry-run first")
+    p.add_argument("--url", required=True, help="Starting URL to crawl")
+    p.add_argument("--folder-name", default=None, help="KB folder name")
+    _add_crawl_config_args(p)
+    p.add_argument("--dry-run", action="store_true",
+                   help="Print intended request without writing server state.")
+    p.add_argument("--out", default=None, help="Write result JSON to this file too")
+    p.set_defaults(func=run_crawl_create)
+
+    p = sub.add_parser("crawl-update", help="Update a website crawl target; run --dry-run first")
+    p.add_argument("--target-id", type=int, required=True)
+    p.add_argument("--url", required=True, help="Updated starting URL")
+    _add_crawl_config_args(p)
+    p.add_argument("--dry-run", action="store_true",
+                   help="Print intended request without writing server state.")
+    p.add_argument("--out", default=None, help="Write result JSON to this file too")
+    p.set_defaults(func=run_crawl_update)
+
+    p = sub.add_parser("crawl-state", help="Read website crawl state for a crawler folder")
+    p.add_argument("--folder-id", required=True, help="KnowledgeNode folder UUID")
+    p.add_argument("--out", default=None, help="Write result JSON to this file too")
+    p.set_defaults(func=run_crawl_state)
+
+    p = sub.add_parser("crawl-sync", help="Start a website crawl sync job; run --dry-run first")
+    p.add_argument("--target-id", type=int, required=True)
+    p.add_argument("--dry-run", action="store_true",
+                   help="Print intended request without writing server state.")
+    p.add_argument("--out", default=None, help="Write result JSON to this file too")
+    p.set_defaults(func=run_crawl_sync)
+
+    p = sub.add_parser("crawl-cancel", help="Cancel the active website crawl job; run --dry-run first")
+    p.add_argument("--target-id", type=int, required=True)
+    p.add_argument("--dry-run", action="store_true",
+                   help="Print intended request without writing server state.")
+    p.add_argument("--out", default=None, help="Write result JSON to this file too")
+    p.set_defaults(func=run_crawl_cancel)
+
+    p = sub.add_parser("crawl-failures", help="List failed pages for a website crawl job")
+    p.add_argument("--job-id", type=int, required=True)
+    p.add_argument("--status", default="DOWNLOAD_FAILED,FAILED")
+    p.add_argument("--limit", type=int, default=50)
+    p.add_argument("--offset", type=int, default=0)
+    p.add_argument("--out", default=None, help="Write result JSON to this file too")
+    p.set_defaults(func=run_crawl_failures)
+
 
 def _node_summary(node: dict) -> dict:
     return {
@@ -130,6 +211,40 @@ def _dry_run(path: str | None, result: dict) -> int:
     return 0
 
 
+def _parse_config_json(config_json: str | None) -> dict | None:
+    if not config_json:
+        return None
+    value = json.loads(config_json)
+    if not isinstance(value, dict):
+        raise SystemExit("--config-json must decode to a JSON object")
+    return value
+
+
+def _crawl_config_from_args(args) -> dict | None:
+    config = _parse_config_json(args.config_json)
+    has_config = config is not None
+    if config is None:
+        config = {}
+
+    for key, attr in (
+        ("limit", "limit"),
+        ("maxDepth", "max_depth"),
+        ("includePaths", "include_paths"),
+        ("excludePaths", "exclude_paths"),
+        ("allowSubdomains", "allow_subdomains"),
+        ("allowExternalLinks", "allow_external_links"),
+        ("ignoreQueryParameters", "ignore_query_parameters"),
+        ("ignoreSitemap", "ignore_sitemap"),
+        ("onlyMainContent", "only_main_content"),
+    ):
+        value = getattr(args, attr)
+        if value is not None:
+            config[key] = value
+            has_config = True
+
+    return config if has_config else None
+
+
 def run_list(args, client) -> int:
     workspace_id, organization_id = client.resolve_scope()
     nodes = kb_mod.list_nodes(
@@ -348,3 +463,127 @@ def run_faq_delete(args, client) -> int:
     response = strip_noisy_fields(kb_mod.delete_context_obj_faq(client, faq_id=args.faq_id))
     _print_and_write(args.out, response)
     return 0
+
+
+def run_crawl_create(args, client) -> int:
+    crawl_config = _crawl_config_from_args(args)
+    body: dict[str, object] = {"start_url": args.url}
+    if args.folder_name is not None:
+        body["folder_name"] = args.folder_name
+    if crawl_config is not None:
+        body["crawl_config"] = crawl_config
+
+    if args.dry_run:
+        return _dry_run(
+            args.out,
+            {
+                "dry_run": True,
+                "operation": "kb_crawl_create",
+                "method": "POST",
+                "path": "/external/knowledge-bases/website-crawls",
+                "body": body,
+                "would_write_server_state": True,
+                "next_step": "Review this summary, then rerun without --dry-run after approval.",
+            },
+        )
+
+    response = strip_noisy_fields(
+        kb_mod.create_website_crawl(
+            client,
+            start_url=args.url,
+            folder_name=args.folder_name,
+            crawl_config=crawl_config,
+        )
+    )
+    _print_and_write(args.out, response)
+    return 0
+
+
+def run_crawl_update(args, client) -> int:
+    crawl_config = _crawl_config_from_args(args)
+    body: dict[str, object] = {"start_url": args.url}
+    if crawl_config is not None:
+        body["crawl_config"] = crawl_config
+
+    if args.dry_run:
+        return _dry_run(
+            args.out,
+            {
+                "dry_run": True,
+                "operation": "kb_crawl_update",
+                "method": "PATCH",
+                "path": f"/external/knowledge-bases/website-crawls/{args.target_id}",
+                "body": body,
+                "would_write_server_state": True,
+                "next_step": "Review this summary, then rerun without --dry-run after approval.",
+            },
+        )
+
+    response = strip_noisy_fields(
+        kb_mod.update_website_crawl(
+            client,
+            target_id=args.target_id,
+            start_url=args.url,
+            crawl_config=crawl_config,
+        )
+    )
+    _print_and_write(args.out, response)
+    return 0
+
+
+def run_crawl_state(args, client) -> int:
+    response = strip_noisy_fields(kb_mod.get_website_crawl_state(client, folder_id=args.folder_id))
+    _print_and_write(args.out, response)
+    return 0
+
+
+def run_crawl_sync(args, client) -> int:
+    if args.dry_run:
+        return _dry_run(
+            args.out,
+            {
+                "dry_run": True,
+                "operation": "kb_crawl_sync",
+                "method": "POST",
+                "path": f"/external/knowledge-bases/website-crawls/{args.target_id}:sync",
+                "would_write_server_state": True,
+                "next_step": "Review this summary, then rerun without --dry-run after approval.",
+            },
+        )
+
+    response = strip_noisy_fields(kb_mod.sync_website_crawl(client, target_id=args.target_id))
+    _print_and_write(args.out, response)
+    return 0
+
+
+def run_crawl_cancel(args, client) -> int:
+    if args.dry_run:
+        return _dry_run(
+            args.out,
+            {
+                "dry_run": True,
+                "operation": "kb_crawl_cancel",
+                "method": "POST",
+                "path": f"/external/knowledge-bases/website-crawls/{args.target_id}:cancel",
+                "would_write_server_state": True,
+                "next_step": "Review this summary, then rerun without --dry-run after approval.",
+            },
+        )
+
+    response = strip_noisy_fields(kb_mod.cancel_website_crawl(client, target_id=args.target_id))
+    _print_and_write(args.out, response)
+    return 0
+
+
+def run_crawl_failures(args, client) -> int:
+    response = strip_noisy_fields(
+        kb_mod.get_website_crawl_failures(
+            client,
+            job_id=args.job_id,
+            status=args.status,
+            limit=args.limit,
+            offset=args.offset,
+        )
+    )
+    _print_and_write(args.out, response)
+    return 0

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/src/codeer_cli/commands/profile.py

@@ -124,7 +124,7 @@ def run_add(args, client=None) -> int:
         data["default"] = args.name
     _write_profiles(data)
     print(f"Saved profile {args.name}")
-    return 0
+    return run_use(args)
 
 
 def run_use(args, client=None) -> int:

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/src/codeer_cli/constants.py

@@ -19,6 +19,7 @@ UNIFIED_TOOL_TYPES: frozenset[str] = frozenset({
     "payment",
     "memory",
     "http_request",
+    "text2speech",
 })
 
 # Valid type values for a field inside ``custom_form_schema.fields[]``.

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/src/codeer_cli/kb.py

@@ -36,7 +36,7 @@ def _guess_mime(filename: str) -> str:
     return guess or "application/octet-stream"
 
 
-def _base(organization_id: str, workspace_id: str) -> str:
+def _base(organization_id: str = "", workspace_id: str = "") -> str:
     return "/external/knowledge-bases"
 
 
@@ -276,3 +276,57 @@ def update_context_obj_faq(
 
 def delete_context_obj_faq(client: CodeerClient, *, faq_id: int) -> dict:
     return client.delete(f"{_faq_base()}/{faq_id}")
+
+
+def create_website_crawl(
+    client: CodeerClient,
+    *,
+    start_url: str,
+    folder_name: Optional[str] = None,
+    crawl_config: Optional[dict[str, Any]] = None,
+) -> dict:
+    body: dict[str, Any] = {"start_url": start_url}
+    if folder_name is not None:
+        body["folder_name"] = folder_name
+    if crawl_config is not None:
+        body["crawl_config"] = crawl_config
+    return client.post(f"{_base()}/website-crawls", json=body)
+
+
+def update_website_crawl(
+    client: CodeerClient,
+    *,
+    target_id: int,
+    start_url: str,
+    crawl_config: Optional[dict[str, Any]] = None,
+) -> dict:
+    body: dict[str, Any] = {"start_url": start_url}
+    if crawl_config is not None:
+        body["crawl_config"] = crawl_config
+    return client.patch(f"{_base()}/website-crawls/{target_id}", json=body)
+
+
+def sync_website_crawl(client: CodeerClient, *, target_id: int) -> dict:
+    return client.post(f"{_base()}/website-crawls/{target_id}:sync", json={})
+
+
+def cancel_website_crawl(client: CodeerClient, *, target_id: int) -> dict:
+    return client.post(f"{_base()}/website-crawls/{target_id}:cancel", json={})
+
+
+def get_website_crawl_state(client: CodeerClient, *, folder_id: str) -> dict:
+    return client.get(f"{_base()}/nodes/{folder_id}/website-crawl-state")
+
+
+def get_website_crawl_failures(
+    client: CodeerClient,
+    *,
+    job_id: int,
+    status: str = "DOWNLOAD_FAILED,FAILED",
+    limit: int = 50,
+    offset: int = 0,
+) -> dict:
+    return client.get(
+        f"{_base()}/website-crawl-jobs/{job_id}/failures",
+        params={"status": status, "limit": limit, "offset": offset},
+    )

{codeer_cli-0.1.1 → codeer_cli-0.1.2}/uv.lock

@@ -26,7 +26,7 @@ wheels = [
 
 [[package]]
 name = "codeer-cli"
-version = "0.1.0"
+version = "0.1.2"
 source = { editable = "." }
 dependencies = [
     { name = "httpx" },