Skip to content

configure() — Customize the Session

The configure tool manages your Gasoline session — filter noise, store data, query the DOM, compare snapshots, validate API contracts, and control streaming.

configure({action: "noise_rule", noise_action: "auto_detect"}) // Auto-filter noise
configure({action: "query_dom", selector: ".error-banner"}) // Query live DOM
configure({action: "store", store_action: "save", key: "baseline", data: {...}}) // Save data
configure({action: "clear", buffer: "all"}) // Clear all buffers
configure({action: "health"}) // Server health
configure({action: "diff_sessions", session_action: "capture", name: "v1"}) // Snapshot

Manages noise rules that suppress irrelevant errors — browser extension noise, analytics failures, framework internals.

configure({action: "noise_rule", noise_action: "auto_detect"})

Scans current errors and identifies patterns that are likely noise (extension errors, analytics, third-party scripts). Creates rules automatically.

configure({action: "noise_rule",
noise_action: "add",
pattern: "analytics\\.google",
category: "console",
reason: "Google Analytics noise"})
ParameterTypeDescription
noise_actionstringadd, remove, list, reset, auto_detect
patternstringRegex pattern to match against error messages
categorystringBuffer: console, network, or websocket
reasonstringHuman-readable explanation of why this is noise
rulesarrayBatch-add multiple rules at once
rule_idstringID of rule to remove (for remove action)
configure({action: "noise_rule", noise_action: "list"})
configure({action: "noise_rule", noise_action: "remove", rule_id: "rule-123"})
configure({action: "noise_rule", noise_action: "reset"})

Save and load JSON data that persists across sessions. Useful for storing baselines, configuration, or any data the AI needs to remember.

configure({action: "store",
store_action: "save",
namespace: "baselines",
key: "homepage-vitals",
data: {lcp: 1200, cls: 0.05}})
configure({action: "store",
store_action: "load",
namespace: "baselines",
key: "homepage-vitals"})
configure({action: "store", store_action: "list"})
configure({action: "store", store_action: "list", namespace: "baselines"})
configure({action: "store", store_action: "delete", key: "homepage-vitals"})
configure({action: "store", store_action: "stats"})
ParameterTypeDescription
store_actionstringsave, load, list, delete, stats
namespacestringLogical grouping for keys
keystringStorage key
dataobjectJSON data to persist (for save)

Query the live DOM using CSS selectors. Returns element details: tag, attributes, text content, visibility, and children.

configure({action: "query_dom", selector: ".error-banner"})
configure({action: "query_dom", selector: "nav a", tab_id: 123})
configure({action: "query_dom", selector: "[role='alert']"})
configure({action: "query_dom", selector: "form input[type='email']"})
ParameterTypeDescription
selectorstringCSS selector to query
tab_idnumberTarget specific tab (omit for active tab)
FieldDescription
Tag namediv, button, input, etc.
Class listCurrent CSS classes
Text contentVisible text
Attributesid, role, aria-, data-, type, value
Computed stateVisibility, disabled status
ChildrenChild elements (limited depth)

Remove captured data from memory.

configure({action: "clear", buffer: "all"})
configure({action: "clear", buffer: "network"})
configure({action: "clear", buffer: "logs"})
ParameterTypeDescription
bufferstringnetwork, websocket, actions, logs, all

diff_sessions — Session Snapshots & Comparison

Section titled “diff_sessions — Session Snapshots & Comparison”

Capture named snapshots of the current session state and compare them to detect changes.

configure({action: "diff_sessions", session_action: "capture", name: "before-deploy"})
configure({action: "diff_sessions",
session_action: "compare",
compare_a: "before-deploy",
compare_b: "after-deploy"})
configure({action: "diff_sessions", session_action: "list"})
configure({action: "diff_sessions", session_action: "delete", name: "old-snapshot"})
ParameterTypeDescription
session_actionstringcapture, compare, list, delete
namestringSnapshot name
compare_astringFirst snapshot (baseline)
compare_bstringSecond snapshot (comparison target)

Infer API schemas from captured traffic and validate consistency.

configure({action: "validate_api", operation: "analyze"})
configure({action: "validate_api", operation: "report", url: "/api/users"})
configure({action: "validate_api", operation: "clear"})
ParameterTypeDescription
operationstringanalyze (infer schemas), report (show results), clear (reset)
urlstringFilter by URL substring
ignore_endpointsarrayURL substrings to exclude from analysis

View a log of all MCP tool calls made during the session. Useful for debugging, compliance, and understanding AI agent behavior.

configure({action: "audit_log"})
configure({action: "audit_log", tool_name: "observe", limit: 20})
configure({action: "audit_log", since: "2026-02-07T10:00:00Z"})
ParameterTypeDescription
tool_namestringFilter by tool name
session_idstringFilter by MCP session ID
sincestringOnly entries after this ISO 8601 timestamp
limitnumberMaximum entries to return

Enable or disable real-time event notifications. When enabled, Gasoline proactively notifies the AI about errors, performance regressions, and security issues as they happen.

configure({action: "streaming", streaming_action: "enable",
events: ["errors", "performance", "security"],
severity_min: "warning",
throttle_seconds: 5})
configure({action: "streaming", streaming_action: "disable"})
configure({action: "streaming", streaming_action: "status"})
ParameterTypeDescription
streaming_actionstringenable, disable, status
eventsarrayCategories: errors, network_errors, performance, user_frustration, security, regression, anomaly, ci, all
severity_minstringMinimum severity: info, warning, error
throttle_secondsintegerMinimum seconds between notifications (1-60)

Check the Gasoline server’s status, uptime, buffer usage, and connected clients.

configure({action: "health"})

No additional parameters. Returns server version, uptime, buffer occupancy, client count, and rate limit status.


test_boundary_start / test_boundary_end — Test Boundaries

Section titled “test_boundary_start / test_boundary_end — Test Boundaries”

Mark the start and end of a test run. Events within boundaries can be correlated for test-specific analysis.

configure({action: "test_boundary_start", test_id: "checkout-flow", label: "Guest Checkout Test"})
// ... run the test ...
configure({action: "test_boundary_end", test_id: "checkout-flow"})
ParameterTypeDescription
test_idstringUnique identifier for the test
labelstringHuman-readable description