agent-friend

[alert] Define a named alert rule. Conditions: gt/gte/lt/lte/eq/ne/between/outside/contains/not_contains/is_empty/is_truthy. Severity: info/warning/error/critical.

[alert] Evaluate a value against a named rule. Returns {fired, severity, value, timestamp}.

[alert] List all alert rules. Returns {rules, count}.

[alert] Get full definition of an alert rule by name.

[alert] Delete an alert rule by name.

[alert] Retrieve fired alert history. Filter by rule name, severity, limit. Returns {events, count, total}.

[alert] Clear alert history for a rule (or all if rule omitted). Returns {cleared, rule}.

[alert] Aggregate stats per rule: fire_count, last_fired. Returns {stats, total_fires}.

[audit] Record a structured audit event. Returns {id, type, actor, resource, timestamp}.

[audit] Filter the audit log. Filters: event_type, actor, resource, severity, outcome, after, before, text. Returns {events, count, total}.

[audit] Retrieve a single event by ID.

[audit] Aggregate stats: by_type, by_actor, by_resource, by_severity, by_outcome.

[audit] Export events as JSON lines. Filter by event_type, after, before. Returns {lines, count}.

[audit] Clear events. before=timestamp to clear only older events. Returns {cleared, remaining}.

[audit] List distinct event types in the log. Returns {types, count}.

[audit] Bucket events by hour or day for trend analysis. Returns {buckets, total}.

[batch] Register a named function. def fn(item): ... for map/filter. def fn(acc, item): ... for reduce (is_reducer=True).

[batch] Apply fn to each item. on_error: null/skip/raise. Returns {results, ok, errors, total, elapsed_ms}.

[batch] Keep items where fn(item) is truthy. Returns {results, total, kept, rejected}.

[batch] Fold items with fn(acc, item). initial=starting accumulator. Built-in reducers: sum/product/max/min/concat.

[batch] Split into passing (truthy) and failing (falsy) lists. Returns {passing, failing, pass_count, fail_count}.

[batch] Split list into chunks of size. Returns {chunks, chunk_count, total}.

[batch] Zip multiple lists into list of dicts with given keys. Returns {results, count}.

[batch] Stats from last batch_map run: ok, errors, total, elapsed_ms.

[batch] List built-in function names (fns + reducers).

[browser] Open a URL and return the page text content.

[cache] Retrieve a previously cached value by key. Returns the value string, or null if the key does not exist or has expired.

[cache] Store a value in the cache under the given key. Use ttl_seconds to control how long the value is valid. Pass ttl_seconds=null for a value that never expires.

[cache] Remove a single key from the cache.

[cache] Remove ALL entries from the cache.

[cache] Return cache statistics: number of active entries, expired entries, and session hit/miss counts.

[chunker] Split text into chunks. mode: chars/tokens/sentences/paragraphs. Returns [{index, text, char_count, token_estimate}].

[chunker] Split a list into batches of size. Returns [{index, items, count}].

[chunker] Split text on a custom separator. Optionally merge parts up to max_chars.

[chunker] Sliding window over text. Returns [{index, text, start, end}].

[chunker] Return stats about text: char_count, token_estimate, line_count, sentence_count, paragraph_count, word_count.

[code] Execute code and return the output. Supported languages: python, bash.

[config] Set a config key (dot-notation OK). Returns {ok, key, value}.

[config] Get a config value. as_type coerces: int/float/bool/str/json.

[config] Set multiple defaults — only sets keys not already present.

[config] Load environment variables into config. prefix filters by prefix.

[config] List all keys, optionally filtered by prefix.

[config] Delete a specific config key.

[config] Export all config as a JSON object.

[config] Assert required keys exist. Returns {ok: bool, missing: [...]}.

[config] Delete an entire named config store.

[config] List all named config stores with key counts.

[crypto] Generate a cryptographically secure random token. Returns a hex string. length is the number of random bytes (output will be 2× as long in hex). Default 32 bytes → 64-char hex.

[crypto] Hash a string using the specified algorithm. Returns the hex digest. Supported: md5, sha1, sha224, sha256, sha384, sha512. Default: sha256.

[crypto] Sign data with a secret key using HMAC. Returns the hex digest. Commonly used to sign webhook payloads. Supported algorithms: sha1, sha224, sha256, sha384, sha512.

[crypto] Verify an HMAC signature against data and a secret key. Returns true if valid, false otherwise. Uses constant-time comparison to prevent timing attacks.

[crypto] Generate a random UUID (version 4). Returns a string like '550e8400-e29b-41d4-a716-446655440000'.

[crypto] Base64-encode a string. Returns the encoded string.

[crypto] Decode a base64-encoded string. Returns the original string.

[crypto] Generate random bytes and return as hex. Useful for nonces, salts, or IVs.

[database] Run a SQL SELECT query and return results as a table of rows.

[database] Run a SQL statement that modifies the database (INSERT, UPDATE, DELETE, CREATE TABLE, DROP TABLE, etc.).

[database] List all tables in the database.

[database] Get the CREATE TABLE statement for a specific table.

[datetime] Return the current date and time as ISO 8601.

[datetime] Parse a date/time string and return ISO 8601.

[datetime] Format a datetime string using a strftime format.

[datetime] Compute the absolute difference between two datetime strings.

[datetime] Add (or subtract) a duration to a datetime.

[datetime] Convert a datetime string from one timezone to another.

[datetime] Convert a datetime string to a Unix timestamp (seconds since epoch).

[datetime] Convert a Unix timestamp to an ISO 8601 datetime string.

[diff] Compare two text strings and return a unified diff. Returns {unified: str, added_lines: int, removed_lines: int, unchanged_lines: int, has_changes: bool}.

[diff] Compare two files and return a unified diff. Returns {unified: str, added_lines: int, removed_lines: int, unchanged_lines: int, has_changes: bool}. Returns an error if either file cannot be read.

[diff] Compare two strings at the word level and return an inline diff. Added words are prefixed with '+', removed words with '-'. Returns {inline: str, added_words: int, removed_words: int}.

[diff] Compute similarity and change statistics between two texts. Returns {similarity: float (0-1), added_chars: int, removed_chars: int, added_lines: int, removed_lines: int, line_similarity: float}.

[diff] Find the most similar strings to a query from a list of candidates. Returns [{text, score}, ...] sorted by similarity, highest first. Useful for fuzzy matching and near-duplicate detection.

[env] Get the value of a single environment variable. Returns the value as a string, or 'null' if not set. Sensitive variables (containing KEY, TOKEN, SECRET, etc.) are hidden and return '[hidden]'.

[env] Set an environment variable for the current process. Visible to child processes spawned after this call. Does not affect the parent shell.

[env] List environment variables as a JSON object. Pass a prefix to filter (e.g. 'AWS_' lists all AWS vars). Sensitive variables are excluded from the output.

[env] Check whether all required environment variables are set. Returns {ok: bool, present: [...], missing: [...]}. Use this to verify API keys before attempting to call external services.

[env] Load key=value pairs from a .env file into the current process environment. Existing variables are not overwritten. Returns {loaded: [...], skipped: [...], errors: [...]}.

[event_bus] Subscribe to a topic. Use topic='*' to receive all events. subscriber is a name string identifying who receives the events.

[event_bus] Unsubscribe from a topic.

[event_bus] Publish an event to a topic. All subscribers (and wildcard subscribers) are notified. Returns {published, event_id, notified: [subscriber names]}.

[event_bus] Return the n most recent events for a topic (oldest first).

[event_bus] List all topics with their subscriber counts and event counts.

[event_bus] List all subscribers to a specific topic.

[event_bus] Return total events published and per-subscriber call counts.

[event_bus] Clear history and subscribers for a topic, or all topics if topic is omitted.

[fetch] Fetch the text content of a URL. HTML pages are automatically converted to readable plain text. Use 'search' to find URLs; use 'fetch' to read a specific URL.

[file] Read a file and return its contents. Files larger than 32 KB are truncated.

[file] Write content to a file, overwriting any existing content.

[file] Append content to an existing file (creates it if missing).

[file] List files and directories at a given path.

[format] Format a byte count: 1234567 → '1.2 MB'. binary=true for KiB/MiB.

[format] Format seconds as a human string: 3661 → '1h 1m 1s'. verbose=true for full words.

[format] Format with thousands separators: 1234567.89 → '1,234,567.89'.

[format] Format as percent: 0.87 → '87.0%'. Ratios (|v|<1) multiplied by 100.

[format] Format as currency: 1234.5 → '$1,234.50'. currency: USD/EUR/GBP/JPY/...

[format] 1 → '1st', 2 → '2nd', 3 → '3rd', 11 → '11th', 21 → '21st'.

[format] Pluralize: format_plural(3, 'item') → '3 items'. Optional custom plural form.

[format] Truncate text to max_length, appending suffix (default '…').

[format] Pad text to width. align: left/right/center.

[format] Render a JSON array of dicts as a plain-text table.