Inspectors

The right panel of the Flow Designer changes based on what you select on the canvas (or which toolbar button you press). All edits stay in the current draft; they are not live until you publish.

Node Inspector

Opens when you click any conversation node on the canvas. The inspector has a header (icon, node type, label, delete / duplicate actions), a body split into tabs that depend on the node type, and a transitions section at the bottom.

Inspector specialisations:

Node type	Headline tabs
Voice agent	Instructions, Tools, Provider override, Action capabilities, Variables used, Transitions.
STT transcribe	Source, Chunking, Translations, Transitions.
Interpretation transform	Prompt, Target language, Cache, Transitions.
LLM query	Prompt, Result variable, Transitions.
TTS playback	Text, Voice override, Transitions.
DTMF collect	Settings (max digits, terminator, timeout), Result variable, Transitions.
Action request	Action, Wait for result, Result variable, Transitions.
Webhook	Request (method, URL, headers, body), Response (parsing into variables), Transitions.
Condition	Decision rows (variable, operator, value → target), Default transition.
Transfer	Target, Method, Transitions.
End	Reason.
Managed LLM	Provider, Channel Data Forwarding, Managed actions, Transitions.
Managed action	Enabled state, Action settings, Outcome transitions.

Transitions are the bottom section on every conversation node and reuse the same UI: a list of outbound edges with label, condition, and target dropdown.

Screenshotguide/users/flow-designer/node-inspectorneeds_review

Node Inspector open on a voice_agent node

Highlight: Instructions editor, Tools list, Action capabilities chips, Transitions section at the bottom

Reason: TelWeb v0.9.14 i18n and UI refactors changed labels/layout; screenshot needs visual review.

Endpoint Inspector

Opens when you click an Entry Point chip. One inspector per endpoint type:

• Phone — base number, extension code, egress base number.
• Web Voice — slug, allowed origins, allowed IPs, egress base number. ⚑Featurewebrtc
• Web Chat — slug, allowed origins, allowed IPs.

Audio codecs are not selected here — the Asterisk ↔ TelPhi link picks them automatically from the voice agent's provider configuration (STT-first for modular pipelines; output-native for unified realtime). Advanced users can pin audio.linkFormat from the source view.

Removing an endpoint here also removes its entry-point chip from the canvas; the flow itself is unaffected.

Flow Settings

Opens when you click the Start node or any Default Provider chip. It's a drawer with the cross-cutting configuration that doesn't belong to a single node.

Section	What it does
Endpoints	The same list of endpoints that renders as Entry Point chips. Add, remove, reorder; clicking an entry opens the Endpoint Inspector.
App settings	App-level toggles such as recording (controls audio capture and transcript retention — see Conversations), language detection mode, default voice.
Language	Default flow language used by STT / TTS providers that ship language defaults.
Default provider	The STT / LLM / TTS (or Realtime) configuration used by every voice agent that doesn't override. See Provider config below.
Managed LLM	Adapter-specific settings for the managed LLM integration (when in use), including Channel Data Forwarding / SIP header context rules. ⚑FeatureadditionalProviders See SIP header context rules.
Error handling	Flow-level bot-delay comfort messages, provider exhaustion behavior, and call-level failover actions.

The Flow Settings drawer is the only place where endpoints can be created or edited.

Managed LLM inspector

The Managed LLM inspector is different from a normal voice-agent inspector: it edits the adapter-owned conversation block rather than a prompt-only node. Use it to review the provider identity, callback behavior, Channel Data Forwarding, and the managed actions the provider is allowed to trigger.

Typical sections:

• Provider configuration — the managed provider, bot name or endpoint identifier, and adapter-specific options.
• Channel Data Forwarding — rules for inbound SIP headers and outbound bot/channel data. Open Manage to edit presets or switch to JSON mode for advanced rules.
• Managed actions — transfer and hangup capabilities exposed by this provider integration. Each action can be enabled or disabled per flow.
• Transitions — the handles that decide where the flow continues after the managed provider returns control or a managed action completes.

⚑Feature required: additionalProviders

Managed LLM integrations and their special inspector sections are shown only when the extended provider catalogue is enabled.

Screenshotguide/users/flow-designer/managed-llm-inspectorplaceholder

Managed LLM inspector showing provider settings, Channel Data Forwarding, and managed action configuration

Highlight: provider section, Channel Data Forwarding accordion, transfer/hangup managed action rows

Managed action inspector

Managed action child nodes open a smaller inspector focused on the one action. The inspector shows whether the action is enabled, which action settings apply, and which outcome transition will run after the action finishes.

For transfer, check the transfer method, destination source, caller ID, announcement message, confirmation behavior, ring timeout, and outbound header rules. For hangup, check whether the call should wait for silence, which farewell message is used, and whether the provider may override that message. These settings are still constrained by platform and team policy; if a transfer restriction blocks a destination, enabling the action here does not bypass that restriction.

Screenshotguide/users/flow-designer/managed-action-inspectorplaceholder

Managed action inspector for a transfer or hangup child node

Highlight: enabled toggle, transfer method or hangup wait-for-silence setting, outcome transitions

Transfer managed action

The Transfer action inspector controls how a provider-requested handoff becomes a SIP/PSTN transfer:

Field	What to check
Enabled	Whether this flow permits provider-triggered transfer.
Method	SIP transfer style, such as sip_refer, sip_refer_replace, or sip_invite.
Target	Fixed destination or a destination selected from call/flow context.
Message / play message	Optional announcement before starting the transfer.
Confirmation	Whether the provider may ask for confirmation before transfer.
Max ring time	How long the outbound leg may ring before the action fails or follows fallback behavior.
Caller ID	Optional caller ID for the outbound leg when the trunk supports it.
Header rules	Outbound Channel Data Forwarding rules for transfer-specific SIP headers.

Transfer actions are validated again at runtime. Platform or team transfer restrictions, missing egress trunks, blocked destinations, and TelPro routing failures can still stop the action after the provider requests it.

If the flow's default provider is a modular pipeline, attended transfer methods that need a live AI mini-session, plus transfer announcements that play a provider-generated message, require a dedicated realtime attended-transfer provider. The Flow Builder readiness panel warns before publish when that provider is missing.

Hangup managed action

The Hangup action inspector controls how a provider-requested call end is executed:

Field	What to check
Enabled	Whether this flow permits provider-triggered hangup.
Wait for silence	Whether Delphi waits for active TTS playback to finish before disconnecting.
Delay bot disconnect	Extra milliseconds after silence wait before hangup (0–30000).
Farewell message	Optional fallback message to play before the call ends.
Allow message override	Whether the provider may replace the configured farewell message.

Use hangup when the managed provider decides the conversation is complete. Use an End node when the flow graph itself reaches a terminal branch.

Playback queueing and hangup order: Speech playback and hangup.

For the underlying JSON fields, see Source view → Managed gateway settings. For callback fields a bot/provider may send during the call, see Managed callback actions.

Failover and readiness settings

Managed LLM flows can also define failure handling outside the individual action child nodes:

Setting	Where to use it
Failover	Runtime failure handling after the managed interaction has started, for example transfer on bot_timeout or hangup on tts_error.
Inbound readiness	Pre-answer behavior for inbound calls, for example wait for provider setup before SIP 200 OK, then reject, hang up, or transfer if setup times out.
Bot delay handling	Intermediate comfort message behavior while the flow waits for a managed bot/LLM response, plus the final give-up timeout.

These settings inherit from platform and team resilience defaults unless the flow overrides them. Failover and readiness reuse the same managed transfer and hangup action shapes. See Managed callback actions → Failover activities and Managed callback actions → Bot readiness.

Screenshotguide/users/flow-designer/resilience-overviewplaceholder

Flow Designer resilience overview panel with provider resilience, bot-delay handling, and error actions

Highlight: resilience overview panel and links into Error handling settings

Screenshotguide/users/flow-designer/error-handlingplaceholder

Flow Settings → Error handling section with bot-delay comfort actions and failover triggers

Highlight: bot-delay handling, final give-up timeout, and transfer/hangup failover actions

Provider config editor

Embedded inside Flow Settings (default provider) and inside voice-agent inspectors (per-node override). The saved-provider picker has been removed; the editor writes the selected provider configuration inline into the flow. The editor adapts to the chosen mode:

• Realtime — single provider running STT, LLM, and TTS in one connection (OpenAI Realtime, Azure Realtime, …). Pick the model, voice, transcription model, VAD, tools, audio noise reduction.
• Pipeline — separate STT + LLM + TTS providers wired into a pipeline. Independent vendor + model choices per stage.

Common subsections:

• STT — provider, language, recognition mode; Advanced STT includes Endpoint URL (custom hostname or IP). See Custom STT/TTS endpoints.
• LLM — provider, model, tool-choice policy, temperature; advanced Base URL on OpenAI Chat and TOBi.
• TTS — provider, voice, model; Advanced includes Endpoint URL on Azure and Inworld.
• Realtime — unified provider; Advanced Settings includes custom URL on OpenAI/Grok, Realtime URL on Gemini, required URL on Pythia, URL mode on Azure Realtime.
• Resilience — timeout, retry, retry delay, backoff, and retry conditions for the selected provider role.

Some providers and audio features are gated:

⚑Feature required: additionalProviders

Hides providers beyond the core OpenAI + Azure set.

⚑Feature required: audioPreprocessing

Hides the noise-reduction options in the provider editor.

Variable Catalogue panel

Opens from the toolbar. Lists every flow variable derived from the current definition, plus team variables and secrets.

• Catalogue — auto-discovered variables from node outputs (e.g. DTMF result variables, webhook response parses).
• Custom variables — define your own with a key, type, label, description and optional default.
• References — quick links into the nodes that read / write each variable, useful for renames.
• Team variables and secrets — pull-in from Team admin → Variables so the flow editor can drop them into prompts and headers.

Version History drawer

Opens from the toolbar. Lists every saved version of the flow definition with status (DRAFT, PUBLISHED, ARCHIVED), version number, creator and timestamp.

• Load a previous version into the editor as a new draft.
• Revert the current draft to a previous version (re-runs validation).
• Restore an older published version as the next draft so you can test and publish it as a controlled rollback.
• Delete draft when the current draft should be discarded.
• Compare by loading + flipping the source view.

The current PUBLISHED version is the one served to the live endpoint.

Tool editor

Opened from the Voice agent's Tools tab. It edits a single tool — name, description, parameters schema (JSON-schema-style fields), and the JavaScript handler. Tools can also be attached from the team / platform catalogue instead of edited locally.

See Tools (team admin) and Managed tools (platform admin) for the upstream definitions.

See also

• Nodes
• Source view
• Draft and publish