> ## Documentation Index
> Fetch the complete documentation index at: https://koreai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# ABL errors and warnings

Look up an error or warning code that the ABL compiler, the parser, or Studio reports. Each entry gives the meaning and the fix.

Codes that start with `E` or `W` and a number come from the parser. Named codes come from the compiler. An error blocks compile or publish. A warning does not.

This page lists the codes that authors meet most often. It is not the full set.

## E394

Severity: error

**Meaning.** SET\_INTERACTION\_LANGUAGE switches the conversation language when the action fires, and its value must be a valid BCP-47 tag. The authored value did not canonicalize to one, so the language switch is dropped while the rest of the action still runs.

**Fix.** Use a valid BCP-47 tag, a language code, optionally with a region suffix, such as `en`, `en-US` or `pt-BR`.

## E395

Severity: error

**Meaning.** CLEAR\_INTERACTION\_LANGUAGE resets the conversation back to the default language and is a bare directive: naming it is the whole instruction. A value after the colon has no meaning, so the parser rejects the line instead of silently discarding what was authored there.

**Fix.** Write the directive as "- CLEAR\_INTERACTION\_LANGUAGE:" with nothing after the colon.

## E396

Severity: error

**Meaning.** set\_interaction\_language switches the conversation language when the action fires, and its value must be a string carrying a valid BCP-47 tag. A non-string value or a string that does not canonicalize to a tag drops the language switch while the rest of the action still applies.

**Fix.** Set the key to a valid BCP-47 tag string, a language code, optionally with a region suffix, such as "en", "en-US" or "pt-BR".

## E492

Severity: error

**Meaning.** FORMAT declared the kind of value a session field holds, and drove kind inference for MATCH\_SCORE, MATCHES and MATCH\_RESULT. Nothing applied it once DERIVED was removed, so it changed no behaviour. The key is rejected rather than ignored so a file cannot look as if it configures matching when it does not.

**Fix.** Delete the FORMAT line and pass the kind as the third argument of MATCH\_SCORE, MATCHES or MATCH\_RESULT where the comparison is written.

## E493

Severity: error

**Meaning.** SOURCE: tool made a session field writable only by tool bindings and refused a model write. It was removed. The key is rejected rather than ignored so a field that looks write-protected is not silently left writable by the model.

**Fix.** Replace SOURCE: tool with READONLY: true on the field. Authored writes (SET, on\_result, hooks) still write a READONLY field.

## E498

Severity: error

**Meaning.** DERIVED declared a session field the runtime recomputed after every session write. It was removed because the recompute cost grew with every write. The protection it gave, that the model can never set the field, is what READONLY: true provides, and the value itself is computed by an authored hook SET. The key is rejected rather than ignored so a field that nothing computes cannot compile.

**Fix.** Replace DERIVED: `<expression>` with READONLY: true on the field, and compute the value with a SET (SET: field = `<expression>`) in a hook that runs when its inputs change.

## E580

Severity: error

**Meaning.** PARALLEL is a block. Write its calls, and in the full form its options, on indented lines below it. A value on the same line is rejected.

**Fix.** Move the value to indented lines, for example `PARALLEL:` then `  - CALL: get_balance`.

## E581

Severity: error

**Meaning.** A PARALLEL block accepts only its own options (WAIT, FAIL\_FAST, MAX\_CONCURRENCY, TIMEOUT, STATUS\_AS, CALLS). Each call accepts only CALL, WITH, AS, WHEN, REQUIRED, TIMEOUT, RETRY, RETRY\_DELAY, RETRY\_BACKOFF, SET, DEFAULT, ERROR\_AS, FALLBACK, AFTER, FOR\_EACH, ITEM\_AS, INDEX\_AS, FILTER, MAX\_ITEMS, and KEY\_BY. Keys are upper case. An unknown key is rejected so a misspelled control is never ignored.

**Fix.** Check the spelling and case of the key, or remove it.

## E582

Severity: error

**Meaning.** Each key can appear once in the PARALLEL options and once per call. A repeat would let one value silently win over the other.

**Fix.** Keep one occurrence of the key. Use the block form of SET for several assignments.

## E583

Severity: error

**Meaning.** In the list form, every line under PARALLEL starts a call with `- CALL:` or continues one. In the full form, options and CALLS sit at one indent, and calls are list items under CALLS. Do not mix list items and options at the same level. Each call key must line up with the CALL key above it.

**Fix.** List the calls directly under PARALLEL, or put the options and a `CALLS:` list under it. Align each call key under CALL.

## E584

Severity: error

**Meaning.** The value does not have the form this PARALLEL key takes. Durations are `1500ms`, `2s`, or a whole number of milliseconds. Counts are whole numbers. Flags are `true` or `false`. DEFAULT is single-line JSON. Names are identifiers.

**Fix.** Write the value in the form quoted in the message.

## E585

Severity: error

**Meaning.** Each call in a PARALLEL block is a list item whose first key is CALL with a bare tool name. Inline arguments such as `tool(a: b)` and `tool AS x` are not accepted.

**Fix.** Write `- CALL: tool_name`, then WITH, AS, and the other keys on the lines below it.

## E586

Severity: error

**Meaning.** A PARALLEL block must hold at least one call, either as list items or under CALLS.

**Fix.** Add at least one `- CALL: tool_name` item.

## E587

Severity: error

**Meaning.** PARALLEL blocks work only in ABL text. YAML would ignore an unknown step key and run the step without its calls, so the compiler rejects the key.

**Fix.** Convert the agent to ABL text, or move the calls into separate CALL steps.

## W170

Severity: warning

**Meaning.** The key is indented under a GATHER field but is not one the field parser reads, so its value is discarded. This used to happen silently, it is how authored EXTRACTION\_HINTS vanished, and the warning exists so a misspelt property surfaces at compile time instead of as a field that never extracts. A near-match suggestion is appended when the key looks like a known one.

**Fix.** Correct the key to the property you meant, the suggestion in the message when there is one, or delete the line if it was left over from an earlier shape of the field.

## W174

Severity: warning

**Meaning.** A FLOW GATHER field reads VALIDATE as a single regular expression on the same line. A VALIDATE block (type, rule and error lines, or a "|" / ">" block scalar) is not read: it is skipped whole, so its lines never become field properties, and it adds no validation. VALIDATION\_PROCESS, RETRY\_PROMPT and MAX\_RETRIES only mean something next to a rule, so the compiler ignores them for a field that, merged with the agent-level GATHER field of the same name, has no rule (no non-blank VALIDATE, and no enum values on a type: enum field). That includes retry settings inherited from the agent-level field.

**Fix.** Put the regular expression on the VALIDATE line itself, and keep RETRY\_PROMPT and MAX\_RETRIES as field properties: VALIDATE: "^\[0-9]\{10}\$", RETRY\_PROMPT: "...", MAX\_RETRIES: 3.

## W175

Severity: warning

**Meaning.** A FLOW GATHER field reads VALIDATE as a single regular expression. An inline object such as \{ pattern: "..." } or a list is not parsed: the whole text, braces included, becomes the regex, so valid input is rejected or invalid input passes.

**Fix.** Replace the object or list with the regular expression itself: VALIDATE: "^\[0-9]\{10}\$".

## W208

Severity: warning

**Meaning.** A SECURE\_INPUT block accepts MODE, FIELDS, MAX\_ATTEMPTS, CANCEL, SAFE\_DETAILS\_AS, PROGRESS\_PROMPT, the delivery CALL with its AS, RESULT\_FIELDS and SUCCESS\_WHEN, and the four outcome routes. Any other line had no field to land in and was silently discarded. The common case is a RESPOND written under ON\_SUCCESS: the route was left empty, so after the payment went through the flow had nowhere to go and the caller heard the empty-response fallback.

**Fix.** Name a FLOW step in the outcome route (ON\_SUCCESS: payment\_done) and write the RESPOND in that step.

## W210

Severity: warning

**Meaning.** A SECURE\_INPUT field is read as PROMPT, RETRY\_PROMPT, NO\_INPUT\_PROMPT, COLLECT, VALIDATE, READ\_ONCE, PROGRESS\_PROMPT, SAVE\_AS, the readable-value marker, and the readable-field settings MODE, RECORD and SPEECH\_AS (see the SECURE\_INPUT reference) only. Any other line had nowhere to land and was silently discarded. The common case is a MESSAGE\_KEY written under a field: it was dropped, so the caller heard the PROMPT text (often a placeholder) instead of the localized message the author pointed at.

**Fix.** Reference the locale entry from the prompt itself: PROMPT: "\{\{locale.PAYMENT\_ENTER\_CARD\_NUMBER}}", or a language map such as PROMPT: \{ en: "...", es: "..." }.

## W211

Severity: warning

**Meaning.** RESULT\_FIELDS and SUCCESS\_WHEN are read from the same line only. A list or map written on the following lines left the value empty, so the compiler then reported a missing allowlist or an empty condition instead of pointing at the layout.

**Fix.** Write the list or map on one line: RESULT\_FIELDS: \[Status, TransactionIdentifier] and SUCCESS\_WHEN: \{ Status: "Success" }.

## W212

Severity: warning

**Meaning.** A SECURE\_INPUT PROGRESS\_PROMPT block is read as TEXT (the line to speak), AFTER (the wait before it), REPEAT\_EVERY (the repeat interval) and REPEAT\_TEXT (the line for each repeat). Any other line had nowhere to land and was discarded, so the caller would not hear what the author wrote.

**Fix.** Write the hold line as TEXT: "\{\{locale.PAYMENT\_PROCESSING}}" or TEXT: \{ en: "Please hold." }, and the timing as AFTER: 2s and REPEAT\_EVERY: 10s.

## W213

Severity: warning

**Meaning.** PROGRESS\_PROMPT AFTER and REPEAT\_EVERY take a whole number followed by s or ms. A value without a unit or with another unit could not be read, so the default was used instead: AFTER waits 0 s on the block and 2 s on a field, and without REPEAT\_EVERY the line is spoken once.

**Fix.** Write AFTER: 2s or REPEAT\_EVERY: 10s.

## W214

Severity: warning

**Meaning.** Branch, ON\_START, action handler, SUB\_INTENTS, hook, and escalation SET blocks keep one value per name. When a name is assigned twice, the later line replaces the earlier one while the file is read. The earlier line never runs. A FLOW step SET is different: it keeps every line and runs them in written order.

**Fix.** Keep one assignment per name. To build a value over several lines, move the lines to a FLOW step SET, for example in the step this block goes to.

## W217

Severity: warning

**Meaning.** A FLOW step header is recognised only as a bare name: line with nothing after the colon, written at column 0 or at two spaces under FLOW:. A header written at another indentation, for example after a comment block, or with a comment after the colon (or trailing spaces at two spaces), was read as an unknown property of the step above it and dropped. The step never existed; its REASONING, ON\_RESULT, THEN and other properties were applied to the step above, replacing the properties that step already had, and routes to the missing step could no longer resolve. Nothing reported it at parse, validate or import preview.

**Fix.** Write the header as a bare name: line at the same level as the other FLOW step headers (column 0 or two spaces under FLOW:), with no comment or trailing spaces after the colon.

## W218

Severity: warning

**Meaning.** A step has one slot for each of REASONING, GOAL, THEN, ON\_INPUT, ON\_RESULT, CALL, RESPOND and the other single-value properties. Writing one a second time silently kept only one of the two values, normally the later, so authored logic, including a whole ON\_RESULT branch list, could disappear with no message. This often follows a mis-indented step header (W217), whose properties land on the step above.

**Fix.** Keep one value per property in each step, or move the second one into its own step and route to it with THEN.

## W324

Severity: warning

**Meaning.** HAND\_BACK takes `after_reply` or `when_finished`. A handoff with any other value keeps the `after_reply` behavior. A reasoning specialist with no COMPLETE condition is handed back after its reply.

**Fix.** Use `HAND_BACK: after_reply` or `HAND_BACK: when_finished`, or remove the line. See [Handing back](https://koreai.mintlify.site/agent-platform/abl/reference/multi-agent-and-supervisor.md#handing-back-hand_back).

## W325

Severity: warning

**Meaning.** HAND\_BACK sets when a returnable handoff hands the customer back to this agent. A handoff without `EXPECT_RETURN: true` is a permanent transfer, so there is nothing to hand back. The line has no effect.

**Fix.** Add `EXPECT_RETURN: true` to the handoff, or remove HAND\_BACK.

## W362

Severity: warning

**Meaning.** `COMPLETE:` holds a list of conditions, and each one starts with `- WHEN:`. RESPOND, SET, STORE, TERMINAL, and response payloads are properties of one condition. The runtime reads them only when they are indented under that `- WHEN:` line. Anything written directly under `COMPLETE:` is ignored. The agent never completes from it, and the goodbye it holds is never spoken.

**Fix.** Start the block with a condition line, such as `- WHEN: true`, and indent RESPOND, SET, and the other properties under it. Use a condition that is true when the agent is done. You can also end a FLOW step with `THEN: COMPLETE`.

## W363

Severity: warning

**Meaning.** A COMPLETE condition reads RESPOND, MODEL\_CONTEXT, SET, STORE, TERMINAL, and response payload blocks. For compatibility, the runtime still reads a property written at or left of the indent of its `- WHEN:` line into that condition. For example, `TERMINAL: false` there keeps the session open. This layout looks like content written directly under `COMPLETE:`, which is otherwise ignored.

**Fix.** Indent the property under its `- WHEN:` line. If it belongs to a different condition, move it there. If it is not needed, remove it.

## W380

Severity: warning

**Meaning.** A DO: list under an ON\_START BRANCHES entry uses the same grammar as a FLOW step DO:. An entry that grammar cannot read is reported here as a warning instead of an error, because an ON\_START branch DO: was ignored before, and the rest of the list still runs.

**Fix.** Write each entry as a "- SET:", "- CALL:" or "- HANDOFF:" line, as in a FLOW step DO: list.

## W388

Severity: warning

**Meaning.** The top-level on\_start do list hands off at most once, to a named agent. An empty handoff, or a second one, is ignored.

**Fix.** Keep one handoff entry that names the target agent.

## W408

Severity: warning

**Meaning.** A ROW groups the action items that share one line. A ROW with no BUTTON, SELECT, INPUT, SUBMIT or TEXT item under it places nothing, so it is dropped from the layout.

**Fix.** Indent the items that belong on this line under the ROW, or remove the empty ROW.

## W409

Severity: warning

**Meaning.** A layout is a list of lines, and a ROW is one line. A ROW inside a ROW has no meaning, so the nested ROW is skipped together with every item under it.

**Fix.** Move the nested items into the outer ROW, or make them a separate ROW at the ACTIONS level.

## W410

Severity: warning

**Meaning.** WIDTH is an item's share of its ROW relative to the other items on that line: an item with WIDTH 2 takes twice the space of an item with WIDTH 1. Any other value is ignored and the item uses the default share of 1.

**Fix.** Set WIDTH to a whole number from 1 to 12, for example WIDTH: 2.

## W411

Severity: warning

**Meaning.** A form has one submit button, so the SUBMIT marker can place it only once. Every SUBMIT after the first is ignored.

**Fix.** Keep one SUBMIT marker where the submit button should appear.

## W412

Severity: warning

**Meaning.** The SUBMIT marker only places the submit button. The button itself is declared by SUBMIT\_LABEL (its text) and SUBMIT\_ID (the action id ON\_ACTION handles). Without both there is no button to place, so the marker is removed.

**Fix.** Add SUBMIT\_LABEL and SUBMIT\_ID to the ACTIONS block, or remove the SUBMIT marker.

## W413

Severity: warning

**Meaning.** A TEXT item shows a line of static text inside the form. An empty TEXT shows nothing, so it is dropped from the layout.

**Fix.** Write the text after TEXT:, for example - TEXT: "Need help? Call support."

## W414

Severity: warning

**Meaning.** The SUBMIT marker only decides where the submit button sits. Its text always comes from SUBMIT\_LABEL and its action id from SUBMIT\_ID, so a value written after SUBMIT: is ignored. The marker itself still places the button.

**Fix.** Write - SUBMIT on its own and put the text in SUBMIT\_LABEL, for example SUBMIT\_LABEL: "Sign in".

## W494

Severity: warning

**Meaning.** A FEEDBACK block can override the voice settings of the survey template it references: the spoken prompts (voice\_prompts: keypad\_instruction, retry\_invalid, timeout, error), the number of retries after a wrong key (voice\_retries, 0 to 3) and the no-input timeout in seconds (voice\_timeout, 3 to 30). A value the template rules would refuse is not used, so callers hear the template's setting, or the platform default when the template has none.

**Fix.** Use a listed prompt name, remove any \{\{...}} placeholder from the prompt text, or bring the number into its range.

## W496

Severity: warning

**Meaning.** On ON\_START and HOOKS calls, WHEN: guards whether the tool call runs only when it is indented under the CALL: it belongs to. Written as a sibling of CALL: nothing reads it, so the call runs unconditionally, exactly as it did before the nested guard existed.

**Fix.** Indent WHEN: one level under the CALL: it should guard, or remove it.

## W497

Severity: warning

**Meaning.** The opt-in EXECUTION keys accept a fixed set of values. `escalation_recheck_after_tools` and `guardrail_builtins` take `true` or `false`. `set_expression_failure` takes `keep_text` or `unset`. `prompt_cache_key` takes `true`, `false`, or a name of up to 64 letters, digits, underscores, dots, colons, or hyphens. `prompt_cache_retention` takes `in_memory` or `24h`. `prompt_version` takes `v1` or `v2`. The older values `off` and `auto` read as `v1` and `v2`. The compiler drops any other value, so the key behaves as if it were absent and uses its default. For `set_expression_failure` the default is `unset`, so a misspelled `keep_text` does not keep the text.

**Fix.** Use one of the values listed above.

## W498

Severity: warning

**Meaning.** A step `PERSONA:` line, or step behavior-profile syntax in a YAML flow step (`persona` or `use_behavior_profile` keys) or in legacy `STEPS:`, is ignored. A step has no persona setting of its own, and these forms do not attach a profile. In a text FLOW step, `USE BEHAVIOR_PROFILE:` is supported and does not report this code.

**Fix.** Remove the line. In a text FLOW step, attach the profile with `USE BEHAVIOR_PROFILE:`. Or attach it at agent level and target channels or callers with the profile WHEN. Put step-specific wording in the step GOAL or BEHAVIOR, step rules in STEP\_CONSTRAINTS, the step tool list in AVAILABLE\_TOOLS, and step voice handling in the step VOICE block. See [Where profiles apply](https://koreai.mintlify.site/agent-platform/abl/reference/behavior-profiles.md#where-profiles-apply).

## W562

Severity: warning

**Meaning.** A provider rejects a request that carries more stop sequences than it allows, which would fail the turn. The runtime therefore leaves the whole list out of any call to a provider whose limit it exceeds, and the reply is generated without stop sequences.

**Fix.** Keep stop\_sequences to four entries or fewer so every supported provider receives them.

## W563

Severity: warning

**Meaning.** Named execution profiles are not supported. A step EXECUTION takes the same keys as the agent EXECUTION section, written one per line under it. The step keeps the agent settings.

**Fix.** Write the settings as indented keys, for example `EXECUTION:` then `  model: gpt-4o-mini` on the next line.

## W564

Severity: warning

**Meaning.** A step EXECUTION value is outside the range the parameter accepts. It is not clamped or coerced. The step uses the agent value for this key and keeps its other step keys.

**Fix.** Set a value that satisfies the constraint quoted in the message, or remove the key.

## W565

Severity: warning

**Meaning.** A step EXECUTION value has the wrong type, is not one of the allowed words, or is null. A quoted number is text, not a number. The step uses the agent value for this key and keeps its other step keys.

**Fix.** Write the value in the shape quoted in the message, or remove the key.

## W566

Severity: warning

**Meaning.** An EXECUTION header with no keys under it changes nothing for the step.

**Fix.** Add indented keys under EXECUTION:, or remove the header.

## W567

Severity: warning

**Meaning.** fallback\_model and conversation\_history\_window apply to the whole agent turn and history, so a step value has no consistent meaning.

**Fix.** Set it in the agent EXECUTION section instead, or remove it from the step.

## W568

Severity: warning

**Meaning.** A step EXECUTION key is not recognized. A step block reads the model, the reasoning effort, the output length limit, the sampling settings (temperature, top\_p, top\_k, the two penalties, and seed), verbosity, the thinking settings, stop\_sequences, llm\_timeout, and tool\_timeout.

**Fix.** Check the spelling against that list, or remove the key.

## W569

Severity: warning

**Meaning.** Loop limits, queueing, budgets, compaction, operation models, and voice settings govern the whole agent, not one step.

**Fix.** Set it in the agent EXECUTION section instead, or remove it from the step.

## W573

Severity: warning

**Meaning.** Every key in a step EXECUTION block must start at the column of the first key. A line at another column, or one that is not a `key: value` pair, is skipped with anything nested under it.

**Fix.** Align the key with the other keys in the block.

## STEP\_EXECUTION\_MODEL\_CAPABILITY

Severity: warning

**Meaning.** A step EXECUTION names a model the platform's capability registry knows, and sets a parameter that model does not accept, for example reasoning\_effort on a model without reasoning, or temperature on a model that disables it. The runtime removes or adjusts the parameter for that model, so the authored value has no effect.

**Fix.** Remove the parameter from the step, or choose a model that supports it. Models given as `{{config.KEY}}` templates are not checked at compile time.

## STEP\_EXECUTION\_NON\_REASONING\_STEP

Severity: warning

**Meaning.** A FLOW step that is not a REASONING step carries an EXECUTION block. Only REASONING steps call a model with step settings, so the block has no effect and is left out of the compiled agent.

**Fix.** Add REASONING: true to the step if it should reason with these settings, or remove the EXECUTION block.

## STEP\_EXECUTION\_STOP\_SEQUENCES\_WITH\_TOOLS

Severity: warning

**Meaning.** A REASONING step sets stop\_sequences but offers the model tools. The runtime never sends stop sequences on a call that offers tools, because a match in the text would end generation before the tool call. The list takes effect only on the step's calls made without tools.

**Fix.** Remove stop\_sequences from the step, or give the step AVAILABLE\_TOOLS: \[] if it should answer without tools.

## AGENT\_EXECUTION\_ROLE\_CONFLICT

Severity: error

**Meaning.** The declared BEHAVIOR role contradicts another declaration on the same agent, either the deprecated canRespondDirectly flag or the fact that the document is a SUPERVISOR.

**Fix.** Keep one source of truth: delete the deprecated canRespondDirectly field, or change role to the value it implies. Supervisors must use role "router" or "orchestrator".

## AGENT\_RETURNED\_WORK\_REQUIRES\_ORCHESTRATOR

Severity: error

**Meaning.** The agent declares DELEGATE targets but its BEHAVIOR role is not "orchestrator". Only an orchestrator is allowed to receive delegated work back and synthesize a response from it.

**Fix.** Set BEHAVIOR role to "orchestrator", or replace DELEGATE with HANDOFF if the other agent should own the conversation from that point on.

## CALLER\_HOLD\_HOOK\_RESPOND\_UNSUPPORTED

Severity: error

**Meaning.** An `on_caller_hold_limit` hook has a RESPOND, a WHEN reply, or rich content. The caller is on hold and the call can end right after the hook, so nobody would hear it.

**Fix.** Remove RESPOND, WHEN replies, and rich content from the hook. Use CALL, SET, and HANDOFF only.

## CALLER\_HOLD\_TRANSFER\_TARGET\_MISSING

Severity: warning

**Meaning.** A project import turned caller hold off. Caller hold transfers the caller to a SIP or phone number target at the hold limit. The project has no valid target of that kind in its Agent Transfer settings.

**Fix.** Add the target in Agent Transfer. Then turn caller hold on.

## CALL\_WITH\_REQUIRED\_PARAM\_EMPTY

Severity: warning

**Meaning.** A `CALL` `WITH:` block binds an empty value (`""` or `''`) to a parameter the tool declares as required. The runtime treats an empty required input as missing. It does not call the tool, and the step takes its failure path with the error code `TOOL_REQUIRED_INPUT_MISSING`. The warning skips a parameter that has a default, a non-model source, or hidden model visibility. It also skips a parameter that `process.before` fills, and the session values `session_id`, `tenant_id`, and `project_id`. An empty `user_id` still warns, because a session with no user has no `user_id`.

**Fix.** If an empty value is valid, declare the parameter optional in the tool signature (`name?: string`) so the runtime sends it. Otherwise bind a value that is never empty, or branch on `__errorCode == "TOOL_REQUIRED_INPUT_MISSING"` in `ON_FAILURE`.

## CEL\_CONDITION\_UNRESOLVED\_CALL

Severity: warning

**Meaning.** A condition parses as CEL but calls a function or method the evaluator has no overload for, such as CONTAINS(x, "y") written as a bare function call or x\[0].has(field). At runtime the call cannot be evaluated, the evaluator falls back and the condition always evaluates false, so the branch, guard, or trigger it controls never fires. It is a warning, not an error, so agents already deployed keep compiling. (MATCHES(...) and MATCH\_RESULT(...) are now registered functions, field-format design, and no longer land here.)

**Fix.** Use a supported form. Regex: x.matches("re") or x MATCHES "re". Field presence on a map or list element: "field" in x\[0], or has(x.field) on a plain member path. The message names the call the evaluator could not resolve.

## CEL\_EXPRESSION\_LIMIT

Severity: warning

**Meaning.** An expression exceeds the supported CEL budget after preparation. Ordinary boolean conditions allow up to 65536 UTF-16 units, 4096 syntax nodes and 64 nesting levels, with each indivisible expression at most 4096 units. Scalar expressions remain limited to 4096 units. Unsupported expressions retain their existing fallback or refusal policy, and routing may evaluate alternatives separately. This warning does not block compilation or import.

**Fix.** Simplify the named expression or split it into shorter rules. Keep individual comparisons, function calls and scalar SET expressions within 4096 prepared source units. Do not rely on legacy fallback to make an unsupported condition agree across escalation, flow and routing surfaces.

## CEL\_MATCH\_PATTERN\_REJECTED

Severity: warning

**Meaning.** A condition or guardrail check passes a literal pattern to abl.matches\_pattern or abl.not\_matches\_pattern (or uses x MATCHES "pattern", which runs as abl.matches\_pattern) that the runtime regex engine cannot run: it is longer than 500 characters, uses a construct RE2 does not support (backreferences, lookahead or lookbehind), or is not a valid regex. At runtime the call does not fail: abl.matches\_pattern returns false and abl.not\_matches\_pattern returns true for every input, so a guardrail built on it never fires (or always fires) and the trace shows an ordinary result. It is a warning, not an error, and evaluation is unchanged.

**Fix.** Keep each pattern to 500 characters or fewer and to RE2 syntax. Split a long alternation into several calls of at most 500 characters each, joined with || for abl.matches\_pattern or with && for abl.not\_matches\_pattern. Replace lookarounds and backreferences with plain alternatives or an additional condition.

## CONFIGURATION\_INVALID\_VALUE

Severity: warning

**Meaning.** A configuration value is not one the setting supports. The parser keeps its existing behavior, and the message says what applies instead. Strict validation does not promote this warning to an error. It is raised for these settings: the `EXECUTION` `conversation_history_window` (a whole number from 0 to 10; an invalid value is not applied and the runtime keeps its default of `2`), `EXECUTION` `compaction_threshold` (a number from 0 to 1), a block-form value for an `EXECUTION` scalar key, and the `HANDOFF` `CONTEXT` `history` value and its `last_n` count.

**Fix.** Use a supported value for the named setting. The message names the setting and the behavior that applies instead. If the setting is missing, check the inherited project configuration.

## CONFIGURATION\_UNKNOWN\_KEY

Severity: warning

**Meaning.** A key is not recognized in the block that holds it. Names are scoped to their block, so a key that works in one block can be unknown in another. The key has no effect, and the defaults or inherited settings stay in effect. The warning does not make a misspelled or wrongly cased key work. Strict validation does not promote it to an error. The parser raises it for unknown keys in the agent `EXECUTION` block (ABL text and YAML) and in a `HANDOFF` `CONTEXT` block. In ABL text, `EXECUTION` keys match without regard to case or underscores. In YAML, only the documented spellings (snake\_case or camelCase) are accepted, so a key with other casing warns.

**Fix.** Check the spelling, the case, and the block. See [Configuration properties](https://koreai.mintlify.site/agent-platform/abl/reference/agent-declaration.md#configuration-properties) for the supported `EXECUTION` keys.

## CONSTRAINT\_ON\_FAIL\_VOICE\_ILLEGAL\_PLACEMENT

Severity: warning

**Meaning.** A constraint refusal is spoken with the delivery policy of the step or turn it interrupts. A VOICE, BARGE\_IN, STREAMING or LISTENING line there has no effect, so it is reported with a warning instead of being dropped silently.

**Fix.** Remove the line, or set the policy on the FLOW step or the agent CONVERSATION.listening.

## CONVERSATION\_BACKCHANNEL\_DURATION\_CAP\_IGNORED

Severity: warning

**Meaning.** on\_caller\_backchannel.max\_duration\_ms has no effect. The voice gateway cannot enforce a duration cap and reports no utterance duration, so the value is ignored and back-channels are matched on the phrase list alone.

**Fix.** Remove max\_duration\_ms from on\_caller\_backchannel.

## CONVERSATION\_BACKGROUND\_DISALLOW\_DEFAULT

Severity: warning

**Meaning.** listening.mode is background but listening.barge\_in (else listening.on\_overlap) resolves to disallow. A background call with barge-in off behaves as a slower turn-taking call.

**Fix.** Set listening.mode to turn\_taking, or set listening.barge\_in to allow so the caller can interrupt in the background mode.

## CONVERSATION\_BACKGROUND\_ONLY\_WITH\_TURN\_TAKING

Severity: warning

**Meaning.** on\_caller\_backchannel or barge\_in\_continuation is authored together with listening.mode turn\_taking. Both only work in background listening mode, so they stay inactive on every turn that listens in turn\_taking.

**Fix.** Remove the background-only key, or set listening.mode to background (the mode is fixed per call).

## DELEGATE\_CHILD\_GATHER\_INPUT\_UNMAPPED

Severity: error

**Meaning.** A DELEGATE target requires GATHER fields (required, no default) that the delegate INPUT mapping does not supply. Delegation is a one-shot internal call with no customer turn, so the child would block asking for input nobody can give.

**Fix.** Map every required child gather field in DELEGATE INPUT, give those fields defaults or mark them optional on the child, or model a genuinely interactive child as a HANDOFF with RETURN true so it can converse with the customer before control comes back.

## DEPRECATED\_INLINE\_FEEDBACK

Severity: warning

**Meaning.** An inline FEEDBACK block declares its question and control directly on the agent, with no survey template behind it. It compiles and renders as authored and the customer is still asked. Feedback Insights groups responses by template ID and selects a compatible scoring method at read time; an inline response has no template ID and does not appear in template-scoped score, trend, distribution or segment views. Inline declarations remain supported for compatibility. A project survey template gives agents one reusable, exact-name definition of the question and control without configuring a scoring method on the template.

**Fix.** Create a survey in the project Feedback Templates area and attach it here with FEEDBACK\_TEMPLATE, moving the inline prompt, type and labels onto it. The referencing block then keeps only per-string overrides and its render guard, and the responses start appearing in Feedback Insights.

## ENABLED\_WHEN\_ALL\_DISABLED\_RISK

Severity: warning

**Meaning.** This agent routes with HANDOFF, and every one of its HANDOFF and DELEGATE entries has an ENABLED\_WHEN condition, so when all of those conditions are false at once the agent has no route left and must answer every request itself. It is a warning, not an error, so the agent still compiles.

**Fix.** Keep at least one entry without ENABLED\_WHEN as an always-available route, or make sure the agent itself can serve the requests that the switched-off routes would have taken.

## ENABLED\_WHEN\_AUTHORED\_ROUTE\_NO\_FALLBACK

Severity: warning

**Meaning.** An authored HANDOFF (in a FLOW step, an action handler, a digression, a tool result or error hook, or an error handler) goes to a target whose every HANDOFF entry has ENABLED\_WHEN, and none of those entries has ON\_FAILURE. When the condition is false the handoff is refused, and without ON\_FAILURE nothing says what the agent does next. It is a warning, not an error, so the agent still compiles.

**Fix.** Add ON\_FAILURE (continue, respond or escalate) to the HANDOFF entry for the target, or declare an entry for the target without ENABLED\_WHEN if the authored route must always be able to run.

## ENABLED\_WHEN\_EMPTY

Severity: error

**Meaning.** ENABLED\_WHEN decides whether a HANDOFF or DELEGATE target is available at all. An empty availability condition is ambiguous: it could mean always available or never available, so the platform refuses to guess and the target is left without one.

**Fix.** Write a deterministic condition such as \_metadata.country != "SGP", or remove ENABLED\_WHEN to keep the target always available.

## ENABLED\_WHEN\_LINE\_COMMENT

Severity: error

**Meaning.** CEL treats // as a comment to the end of the line. A folded YAML block joins its lines before the condition is read, so a // comment there hides every clause after it and the target could be available when the author meant it not to be.

**Fix.** Use a YAML # comment, or write the condition as a literal block (|) with the comment on its own line.

## ENABLED\_WHEN\_ON\_START\_UNSTABLE\_DATA

Severity: warning

**Meaning.** ON\_START delegates to a target whose every DELEGATE entry has ENABLED\_WHEN, and a condition reads data that may not exist yet when the session starts, such as conversation memory or tool results. Evaluated at start, such a condition sees empty values, so the delegate may be switched off for reasons the author did not intend. It is a warning, not an error, so the agent still compiles.

**Fix.** Write the ENABLED\_WHEN condition over data that is known when the session starts: \_metadata, env, caller, session or user. Otherwise, run the delegate later in the conversation instead of in ON\_START.

## ENABLED\_WHEN\_SAFETY\_ROUTE\_CONDITIONAL

Severity: error

**Meaning.** A constraint ON\_FAIL hands off to a target whose every HANDOFF entry has ENABLED\_WHEN. A constraint handoff is a safety route that must always be able to run, but ENABLED\_WHEN can switch the target off, which would leave the failed constraint with nowhere to go.

**Fix.** Declare a HANDOFF entry for the target without ENABLED\_WHEN, or send the constraint ON\_FAIL to a target that is always available, such as ESCALATE or another unconditional HANDOFF target.

## ENABLED\_WHEN\_SEMANTIC\_REFERENCE

Severity: error

**Meaning.** An ENABLED\_WHEN condition reads what the current turn means: the intent classification (intent or a field under it), the routing decision (routing.\*, routing\_intent, source\_route\_intent), the current user input, or previous\_system\_message\_was\_offer, or is natural language that only a model can judge. ENABLED\_WHEN decides whether a HANDOFF or DELEGATE target is available at all, before any turn is understood, so it must depend only on data that is known up front. Turn meaning is already expressed by WHEN.

**Fix.** Move the turn-dependent part of the condition into WHEN, and keep ENABLED\_WHEN for deterministic availability facts such as \_metadata.country != "SGP", env, caller, session or user data.

## ENABLED\_WHEN\_SHADOWED\_BY\_UNCONDITIONAL\_ENTRY

Severity: warning

**Meaning.** The same target is declared more than once in one HANDOFF or DELEGATE section, and only some of those entries have ENABLED\_WHEN. The entry without ENABLED\_WHEN keeps the target available whatever the condition says, so the condition does not switch the target off. It is a warning, not an error, so the agent still compiles.

**Fix.** Give every entry for the target the same ENABLED\_WHEN condition if the target should be switched off, or remove ENABLED\_WHEN from the entry that has it if the target should stay available.

## FLOW\_ON\_INPUT\_GATE\_AFTER\_CONSUMED\_INPUT

Severity: warning

**Meaning.** A route already used the customer message (an ON\_INPUT branch, or the THEN or ON\_RESULT branch of a GATHER step). It reaches a FLOW step that routes only with ON\_INPUT and shows no prompt, with nothing shown on the way. Each customer message is routed by one step, so that step does not evaluate the same message. The turn ends with no reply, and the next message is routed there. `turn_input` does not change this, because the ON\_INPUT branches are not evaluated in that turn.

**Fix.** To route on the same message, change the step to ON\_RESULT and read the message with `turn_input`. To wait for a new answer, add a RESPOND with the question on the branch or on a step before it.

## FLOW\_PROMPTLESS\_ON\_INPUT\_UNMATCHED\_TRAP

Severity: warning

**Meaning.** A promptless ON\_INPUT-only FLOW step has conditional branches but no ELSE/default branch. Input that matches no condition leaves the session waiting on the same step without an authored prompt.

**Fix.** Add an ELSE branch for unmatched input, add a RESPOND prompt that explains the accepted choices, or keep the gate only when silent waiting is explicitly intended.

## FLOW\_STEP\_WHEN\_IGNORED

Severity: warning

**Meaning.** A FLOW step declares a step-level WHEN. The condition is not compiled and has no effect: the step, including its CALL, runs whenever the flow reaches it.

**Fix.** Guard the step from the step before it with ON\_RESULT branches, or use CHECK with ON\_FAIL to skip it, and remove the WHEN.

## GATHER\_ASR\_REASONING\_UNSUPPORTED

Severity: warning

**Meaning.** Listening settings (ASR:) are on a top-level GATHER field of a reasoning agent that is not marked armable: true. The reasoning agent applies a field's settings only to an armable field, so these are kept for round trips but have no effect on calls. In an agent with a FLOW, a field that sets asr\_timeout\_ms does not warn: a FLOW tool call missing that input asks for it through this field and applies its settings.

**Fix.** Add armable: true to the field so the agent can apply its listening settings when it asks for it, or remove the ASR: block.

## GATHER\_ASR\_SHARED\_STEP

Severity: warning

**Meaning.** A GATHER field with listening settings is asked together with other required fields in the same step. Listening settings apply only when a field is asked on its own, so they never take effect here.

**Fix.** Move the field with ASR: to its own FLOW step.

## GATHER\_ASR\_TERMS\_BINDING\_FORBIDDEN

Severity: error

**Meaning.** A GATHER field ASR: block takes its special words from a session value the platform never sends to a speech engine: session identity or runtime-internal roots, conversation history, protected email aliases, prototype or secret path parts, or a user.\* value without restore\_pii: true.

**Fix.** Bind to a value your flow or tools set (for example a list a tool returned). For user.\* values, add restore\_pii: true only if sending the caller personal data to the speech engine is intended.

## GATHER\_ASR\_TERMS\_BINDING\_INVALID

Severity: error

**Meaning.** A GATHER field ASR: block takes its special words from a session value, but the value is not exactly one quoted \{\{path}} reference (surrounding text, several references, filters, an unquoted reference, a reference inside a list, or a path longer than 8 parts or 128 characters).

**Fix.** Write the whole list, or one language list, as a single quoted reference such as terms: "\{\{caller.streets}}", where the path is plain dotted names with optional \[n] indexes.

## GATHER\_ASR\_UNKNOWN\_KEY

Severity: error

**Meaning.** A GATHER field ASR: block names a listening setting the platform does not know. Credential-like keys (service instance ids, API keys, labels) are rejected this way, because listening settings never carry credentials.

**Fix.** Use only provider, model, language, vocabulary (mode, terms) and no\_input\_timeout\_ms, and pick the speech engine by provider name; credentials stay on the voice channel.

## GATHER\_DTMF\_FINISH\_KEY\_ALONE\_INPUT\_UNUSED

Severity: warning

**Meaning.** The agent or a behavior profile sets `finishKeyAlone` to `input`. A FLOW question it reaches has no `finishKeyAlone` of its own, and its step has no ON\_INPUT branch. A caller who presses only the finish key there hears the question again.

**Fix.** Set `finishKeyAlone: value` on the question, add an ON\_INPUT branch for the key, or set `finishKeyAlone: no_input` on the question.

## GATHER\_DTMF\_FINISH\_KEY\_ALONE\_INVALID

Severity: error

**Meaning.** `finishKeyAlone` in keypad settings has a value its level does not allow. It sets what happens when the caller presses only the finish key: `no_input` (wait and ask again, the default), `input` (send the key to the agent), or, on a FLOW question only, `value` (store the key as the answer).

**Fix.** Use `no_input` or `input` on a behavior profile, an agent, or the project. Use `no_input`, `input`, or `value` on a FLOW GATHER field.

## GATHER\_DTMF\_FINISH\_KEY\_ALONE\_NEVER\_ACCEPTED

Severity: warning

**Meaning.** `finishKeyAlone` is `value` on a FLOW question whose allowed values or regular-expression validation reject the finish key. Storing the key always fails validation, and the question is asked again.

**Fix.** Add the finish key to the allowed values or the pattern. Or use `input` and handle the key in an ON\_INPUT branch.

## GATHER\_DTMF\_FINISH\_KEY\_ALONE\_NO\_FINISH\_KEY

Severity: warning

**Meaning.** `finishKeyAlone` is `input` or `value` in keypad settings whose `finishOnKey` is `none`. With no finish key, the caller cannot press it alone, so the setting never applies.

**Fix.** Set `finishOnKey` to `"#"` or `"*"` in the same keypad settings, or remove `finishKeyAlone`.

## GATHER\_DTMF\_FINISH\_KEY\_ALONE\_VALUE\_REASONING

Severity: error

**Meaning.** `finishKeyAlone` is `value` on a top-level GATHER field. The reasoning agent collects those fields as a whole, so there is no single question to store the finish key in.

**Fix.** Use `input` on this field so the agent receives the key. Or set `value` on the field in the FLOW step that asks for it.

## GATHER\_DTMF\_FINISH\_KEY\_ALONE\_VALUE\_TYPE

Severity: error

**Meaning.** `finishKeyAlone` is `value` on a FLOW question whose type can never hold a single `#` or `*`. These types are number, date, phone number, email address, yes or no answer, list, and range.

**Fix.** Use `input` and handle the key in an ON\_INPUT branch. Or ask for the key in a text or menu question.

## GATHER\_DTMF\_FINISH\_KEY\_INVALID

Severity: error

**Meaning.** `finishOnKey` in a FLOW GATHER field `DTMF:` block is not `"#"`, `"*"`, or `"none"`. It cannot finish the typed answer.

**Fix.** Use `"#"`, `"*"`, or `"none"`.

## GENESYS\_SIP\_HEADER\_KEY\_COLLISION

Severity: error

**Meaning.** Two or more of the Genesys SIP transfer headers, reason, queue, metadata, resolve to the same header key once a trigger-level GENESYS\_SIP\_HEADERS override is merged over the ESCALATE routing defaults (the comparison is case-insensitive, as SIP header names are). The runtime payload builder rejects a transfer whose header keys collide, so the escalation would fail during a live call; the compiler reports the collision at authoring time instead.

**Fix.** Give each emitted header a distinct key via reason\_header\_key, queue\_header\_key and metadata\_header\_key. Remember the defaults count as taken, the reason header defaults to X-Transfer-Reason and the metadata header (sent only when a metadata value exists) to X-Transfer-Metadata, and check both the routing block and every trigger override, since the effective set is their merge.

## GUARDRAIL\_BUILTIN\_NOT\_BOUND

Severity: warning

**Meaning.** A guardrail check reads one of the identifiers content, session\_state or tool\_results, or a BEFORE tool-call constraint (REQUIRE or WHEN) reads tool\_args, but the agent does not set EXECUTION guardrail\_builtins: true and declares no session variable of that name. The name is then not bound, so the check errors when it runs: a guardrail check lets every message through, while a BEFORE tool-call constraint that cannot be evaluated fails closed and blocks the call. It is a warning, not an error, and evaluation is unchanged.

**Fix.** Set guardrail\_builtins: true under EXECUTION to bind content (the checked text), session\_state, tool\_results and tool\_args, or write text instead of content. Setting the key changes behaviour: a check that failed open starts to apply and can block.

## GUARDRAIL\_CONTENT\_SHADOWS\_SESSION\_VAR

Severity: warning

**Meaning.** The agent sets EXECUTION guardrail\_builtins: true and also declares a session variable named content, and a guardrail check reads the identifier content. With the alias on, content is the text being checked (an alias of text), so the check tests that text and never the session variable, whatever the author intended. It is a warning, not an error, and evaluation is unchanged.

**Fix.** Rename the session variable so the two no longer share a name, or, if the checked text was meant, write text instead of content to make that explicit.

## GUARDRAIL\_UNKNOWN\_PROPERTY

Severity: warning

**Meaning.** The parser discards a guardrail property it does not recognize. The guardrail then runs with the default for what the property was meant to set. A misspelled action leaves the guardrail on its default action (warn in ABL, block in YAML). A misspelled check leaves it with no check.

**Fix.** Correct the property name. Use the suggestion in the message when there is one. Delete the line if you do not need it. Property names are case-insensitive in ABL and exact in YAML.

## HOOK\_LANGUAGE\_ACTIONS\_REQUIRE\_SETTING

Severity: warning

**Meaning.** HOOKS before\_turn interaction-language actions are authored. They take effect only when the project's language detection setting is on, on chat and on pipeline voice calls; runtime skips them on realtime speech-to-speech calls. The compiler cannot see project settings, so it reports this on every compile of such an agent.

**Fix.** Turn on language detection in the project settings, or remove the actions if the agent should keep one language.

## HOOK\_LANGUAGE\_ACTION\_NOT\_BEFORE\_TURN

Severity: error

**Meaning.** Runtime evaluates hook interaction-language actions once per turn, before the filler and the model call, so the reply, the filler and the voice all use the language the hook chose. Only before\_turn runs at that point; in any other hook the action would have nothing to steer, so it is rejected instead of being silently ignored.

**Fix.** Move the SET\_INTERACTION\_LANGUAGE or CLEAR\_INTERACTION\_LANGUAGE action, with its WHEN:, under HOOKS before\_turn.

## HOOK\_LANGUAGE\_ACTION\_UNSUPPORTED\_HOOK

Severity: error

**Meaning.** The IR carries interaction\_language\_actions on a hook other than before\_turn. Runtime runs these actions only in the before\_turn early pass, so on any other hook they would be silently ignored.

**Fix.** Move the interaction-language actions to HOOKS before\_turn.

## HOOK\_LANGUAGE\_CATCH\_ALL\_NOT\_LAST

Severity: warning

**Meaning.** before\_turn interaction-language actions are tried in order and the first whose WHEN: holds wins. An action with no WHEN: always matches, so every action written after it is unreachable.

**Fix.** Move the action without WHEN: to the end of the before\_turn language actions, or give it a WHEN: condition.

## HOOK\_LANGUAGE\_ENTRY\_INVALID

Severity: error

**Meaning.** Each interaction\_language\_actions entry is one guarded action: it either sets the session language (from a tag or an expression) or clears it. An entry with none of the keys does nothing, and an entry with several is ambiguous, so the entry is dropped and the agent does not compile.

**Fix.** Keep exactly one of set\_interaction\_language, set\_interaction\_language\_expression or clear\_interaction\_language in the entry, next to its optional when.

## HOOK\_LANGUAGE\_WHEN\_INVALID\_CEL

Severity: warning

**Meaning.** A WHEN: that guards a HOOKS before\_turn SET\_INTERACTION\_LANGUAGE or CLEAR\_INTERACTION\_LANGUAGE is not a valid CEL expression. The action is dropped rather than run unconditionally, because an always-on language switch would change the language of every reply, filler and voice prompt.

**Fix.** Rewrite the WHEN: as one valid CEL expression, for example session.languageDetection.status == "detected", or delete the action.

## HOOK\_VOICE\_NOT\_UNDER\_RESPOND

Severity: warning

**Meaning.** A hook VOICE block styles the reply of the RESPOND it is indented under, including a RESPOND inside a WHEN: branch. Written beside a one-line RESPOND, or in a hook with no RESPOND, nothing reads it, so its BARGE\_IN, STREAMING and acoustic settings do not apply and the hook reply keeps the step and turn defaults. After a | block RESPOND in a WHEN: branch the block would swallow a nested VOICE as reply text, so VOICE goes level with that RESPOND instead.

**Fix.** Indent VOICE: one level under the one-line RESPOND: it belongs to (level with the RESPOND: after a | block in a WHEN: branch), or remove it.

## HOOK\_WHEN\_BODY\_MULTIPLE\_ACTIONS

Severity: error

**Meaning.** A hook WHEN: branch is either a reply branch (RESPOND) or a language branch (SET\_INTERACTION\_LANGUAGE or CLEAR\_INTERACTION\_LANGUAGE). The two run at different points of the turn, so one body cannot hold both, and two language actions under one WHEN: would leave it unclear which one applies. The whole branch is dropped.

**Fix.** Split the body into separate WHEN: branches with the same condition: one with the RESPOND and one with the language action.

## HOOK\_WHEN\_BRANCH\_INVALID\_CEL

Severity: warning

**Meaning.** A hook WHEN: line that precedes an indented RESPOND: is not a valid CEL expression. The branch is not compiled as a conditional branch: the WHEN: is ignored and the RESPOND: runs unconditionally on every run of the hook, exactly as it did before hook branches existed. It is a warning, not an error, so the agent still compiles.

**Fix.** Rewrite the WHEN: as one valid CEL expression so the RESPOND: applies only when it is true, or delete the WHEN: line if the RESPOND: is meant to run every time.

## HTTP\_TOOL\_INVALID\_IDEMPOTENCY\_HEADER

Severity: warning

**Meaning.** An HTTP tool declares idempotency\_header with an empty, malformed, overlong, or reserved header name (a credential, cookie, transport, SOAP or request-signing header). The runtime therefore does not send its idempotency key to the provider for that tool.

**Fix.** Set idempotency\_header to the header your provider documents for idempotency keys, for example Idempotency-Key, or remove it if the provider does not support idempotency keys.

## IMMUTABLE\_SYSTEM\_IDENTIFIER

Severity: error

**Meaning.** A SET, CLEAR, or return mapping writes to a system-owned identifier, user\_id, session\_id, tenant\_id, or project\_id, including any nested path under one of them. Those values carry the identity and isolation context the platform itself owns, so authored writes to them are refused rather than allowed to corrupt who or where the session is.

**Fix.** Write the value under a domain-specific name instead, customer\_user\_id, order\_session\_ref, and map it explicitly wherever it is consumed. Identity itself only moves through the supported channels: handoff pass-through, memory grants, or runtime bootstrap; remove the SET, CLEAR, or map entry that targets the reserved name.

## INVALID\_APPROVED\_SIP\_AUTHORITY

Severity: error

**Meaning.** A call\_transfer tool declares an approved\_authorities allow-list entry that is not a valid literal SIP authority, malformed scheme, missing/non-literal host or port, a query/header section, or another structural defect the shared compileApprovedAuthority parser rejects.

**Fix.** Author the entry as a literal 'sip:' or 'sips:' URI with an explicit VDN (userinfo), host, and port and no query/header section, for example, 'sip:421001\@172.0.41.7:5060'.

## INVALID\_CEL\_SYNTAX

Severity: error

**Meaning.** A condition that reads as a CEL expression fails to parse, even after legacy-operator migration and presence-check normalization. The runtime evaluator never throws, an unparseable condition silently evaluates false, so the branch, constraint, trigger, or completion it guards would simply never fire, with no error at runtime to say why.

**Fix.** Rewrite the condition as a valid CEL expression: use == and != for equality (never the JavaScript triple forms), && / || / ! or AND / OR / NOT for logic, and keep every parenthesis, bracket, and quote balanced. String values go in double quotes. Test membership with in, strings with contains, matches, startsWith, or endsWith, and presence with has() on a member path or the IS SET / IS NOT SET sugar. Platform helpers live under the abl namespace, for example abl.upper(name) or abl.round(price, 2). For a condition that should always hold, write true. The message carries the parser description of exactly what it could not read.

## INVALID\_HANDOFF\_TARGET

Severity: error

**Meaning.** A handoff target does not resolve: the named agent does not exist in this compilation, or the reference, from ON\_ACTION, a digression or an error handler, names an agent this agent holds no handoff authority for. The transfer would have nowhere to go at runtime.

**Fix.** Correct the target to the exact name of an agent in the project, and declare it in this agent HANDOFF configuration (for error handlers, ROUTING or a constraint handoff also grants authority). Names match exactly; a target outside this project needs a declared remote handoff entry.

## INVALID\_SIP\_TRANSFER\_DESTINATION

Severity: error

**Meaning.** A call\_transfer tool declares a static sipTransferId default that is empty, templated, or not a valid sip: or sips: URI, so the transfer destination cannot be used reliably.

**Fix.** Set default\_source to config or system and provide a literal sip: or sips: URI such as 'sip:[desk@sbc.example.com](mailto:desk@sbc.example.com)'. Remove the default to use the project-configured transfer target, or configure a dynamic target in Agent Transfer settings instead of templating the value.

## INVALID\_SURVEY\_CONDITION

Severity: error

**Meaning.** A survey template's follow-up or comment-box condition cannot be evaluated as written: it does not parse, it references a name the platform does not supply, or a matching condition would select a question that does not exist. An invalid condition never matches, so left unresolved the survey ships looking configured and behaves as though it had no conditions at all, a follow-up nobody is ever asked, or a comment box nobody is ever offered.

**Fix.** Fix the condition on the survey template in the project Surveys area, the message names the editor (comment box or follow-up) and the position of the condition at fault. A condition may reference only rating, max, language, channel and session, with session values addressed as session.name. If the condition was meant to select a per-condition question, give it one, or give the follow-up a default question for it to fall back to.

## LISTENING\_FINISH\_KEY\_ALONE\_VALUE\_LEVEL

Severity: error

**Meaning.** `finishKeyAlone` is `value` on a behavior profile, an agent, or the project. Storing the finish key as an answer needs a single question to hold it, so `value` works only on a FLOW GATHER field.

**Fix.** Use `input` here so the agent receives the key. Or set `value` on the field in the FLOW step that asks for it.

## LISTENING\_KEY\_NEEDS\_NEWER\_RUNTIME

Severity: warning

**Meaning.** A listening setting this runtime knows but does not apply yet (for example asr\_timeout\_ms) was written. It is checked for range and then ignored, so the agent keeps working on older and newer runtimes.

**Fix.** Keep it if the agent will run on a runtime that supports it; otherwise remove it. Nothing changes on this runtime either way.

## MATCHES\_FUNCTION\_REGEX\_LITERAL

Severity: warning

**Meaning.** MATCHES(subject, "pattern") is the fuzzy spoken-answer function that compares what a caller said with a stored value, but its second argument is a string literal that looks like a regex (an anchor, character class or quantifier). The function does not run a regex, so the comparison cannot behave the way the pattern suggests and the condition is almost certainly wrong. It is a warning, not an error, and evaluation is unchanged.

**Fix.** If a regex was meant, write the infix form subject MATCHES "pattern" or the method form subject.matches("pattern"). If a fuzzy comparison was meant, pass the stored value as the second argument, MATCHES(said, stored, "kind"), or use a literal without regex syntax.

## MATCHES\_INFIX\_LITERAL\_AMBIGUOUS

Severity: warning

**Meaning.** A condition uses the regex infix form x MATCHES "literal" with a pattern that has no regex metacharacter, so it reads like the fuzzy spoken-answer function MATCHES(a, b). The infix form is the one that applies: it is true when that exact, case-sensitive text appears anywhere in x. It is a warning, not an error, and evaluation is unchanged.

**Fix.** If a fuzzy comparison of what the caller said was meant, write the function form MATCHES(x, "literal") (or compare two fields: MATCHES(supplied, stored)). If a regex was meant, keep the infix form; anchoring it (^literal\$) or using x == "literal" for an exact comparison also clears the warning.

## MEMORY\_INVALID\_ACCESS

Severity: warning

**Meaning.** ACCESS sets whether the agent may read, write, or both read and write a persistent memory value. A value outside `read`, `write`, and `readwrite` restricts nothing. In ABL the value is ignored and the default `readwrite` applies. In YAML, where values are case-sensitive, the value is kept but acts as `readwrite`. A value meant to be read-only can be overwritten.

**Fix.** Set ACCESS to `read`, `write`, or `readwrite` (lowercase in YAML). Or remove the line to keep the default.

## MEMORY\_INVALID\_SCOPE

Severity: warning

**Meaning.** SCOPE sets who shares a persistent memory value. `user` keeps one value per end user. `project` shares one value across the project. `execution_tree` shares it among the agents of one handoff tree. A value outside these never selects the scope you meant. In ABL the value is ignored and the path falls back to `user`, so a value meant to be shared is stored separately for each user. In YAML, where values are case-sensitive, the value matches no scope. The agent then does not load or save the path with its other persistent memory, and tool reads and writes treat it as `user`.

**Fix.** Set SCOPE to `user`, `project`, or `execution_tree` (lowercase in YAML). Or remove the line to keep the default.

## MEMORY\_MODEL\_VISIBLE\_PATH\_UNSUPPORTED

Severity: error

**Meaning.** Automatic memory projection must be able to remove the exact declared path. Unsupported selectors cannot safely enforce an authored opt-out.

**Fix.** Use numeric dot segments for array positions, or opt out the supported parent path instead. Existing entries without a false opt-out are unaffected.

## MEMORY\_MODEL\_WRITERS\_INVALID

Severity: error

**Meaning.** Explicit model ownership must be a consistent list of agent names. Silently dropping malformed ownership could reopen a protected model write.

**Fix.** Use MODEL\_WRITERS: \[agent\_name, ...], or MODEL\_WRITERS: \[] to deny all model writers. Repeated declarations must agree.

## MODEL\_CONTEXT\_INVALID

Severity: error

**Meaning.** Tool result MODEL\_CONTEXT selects either FIELDS or TEMPLATE. Response MODEL\_CONTEXT must be a text scalar beside RESPOND. Invalid input cannot safely define a model view.

**Fix.** Use exactly one non-empty FIELDS: \[path, ...] or TEMPLATE: "text" for tools; use a text scalar beside FLOW, COMPLETE, or tool-hook RESPOND.

## NO\_INPUT\_HOOK\_RESPOND\_UNSUPPORTED

Severity: error

**Meaning.** An on\_no\_input\_exhausted hook has a RESPOND. The call can end straight after the hook, which could cut the reply off.

**Fix.** Remove RESPOND and put the final words in exhausted\_message.

## NO\_INPUT\_TARGET\_NO\_HOOK

Severity: error

**Meaning.** on\_exhausted is hook, but the agent has no on\_no\_input\_exhausted hook, so nothing would run when silence is exhausted.

**Fix.** Add HOOKS on\_no\_input\_exhausted to this agent, or set on\_exhausted to hangup or custom.

## ON\_ERROR\_HANDLER\_TYPE\_DRIFT

Severity: warning

**Meaning.** The ON\_ERROR handler type is not one of the canonical runtime error types (default, llm\_error, tool\_error, routing\_error, validation\_error, timeout\_error, unknown\_error). Runtime dispatches on the canonical names, so a handler declared under any other name may never match. Names with a known replacement get a targeted hint; the rest get a generic one.

**Fix.** Rename the handler to a canonical error type, and express the narrower distinction with SUBTYPE, for example tool\_error with SUBTYPE: tool\_timeout.

## ON\_START\_BRANCH\_DO\_ACTIVATED

Severity: warning

**Meaning.** Notice: this ON\_START branch runs its DO: list (SET, CALL and HANDOFF) at session start when it matches. Before ON\_START DO: lists were supported, a branch DO: was silently ignored, so a project that already contained one now runs it.

**Fix.** No action is needed if the actions are intended. Otherwise remove the DO: list from the branch.

## ON\_START\_DELEGATE\_WITH\_HANDOFF

Severity: warning

**Meaning.** ON\_START both delegates and hands off. When a handoff runs at session start, the child owns the session and the ON\_START DELEGATE is not returned.

**Fix.** Choose one start-time route: keep the handoff and remove DELEGATE, or remove the handoff and keep the delegation.

## ON\_START\_HANDOFF\_ACTIVATED

Severity: warning

**Meaning.** Notice: this agent hands off at session start when no ON\_START branch matches. Before ON\_START handoffs were supported, this HANDOFF line was silently dropped, so a project that already contained it now behaves differently.

**Fix.** No action is needed if the start-time handoff is intended. Otherwise remove the HANDOFF line from ON\_START.

## ON\_START\_HANDOFF\_TARGET\_INVALID

Severity: warning

**Meaning.** An ON\_START handoff names a target this agent cannot start at session start: the agent itself, an agent not in this compilation, an agent with no top-level HANDOFF entry, or a remote (A2A) entry. The entry stays in the compiled agent; at runtime the existing route authority refuses it, the entry agent keeps the session and the refusal is traced.

**Fix.** Name a local agent of this project that is declared in this agent top-level HANDOFF section, and set RETURN, CONTEXT and WHEN on that HANDOFF entry.

## ON\_START\_HANDOFF\_UNREACHABLE

Severity: warning

**Meaning.** The top-level ON\_START HANDOFF runs only when no ON\_START branch matches, and an ELSE branch always matches, so the top-level handoff can never run.

**Fix.** Move the HANDOFF into the DO: list of the branches that should hand off (including ELSE), or remove the ELSE branch.

## PARALLEL\_CROSS\_CALL\_READ

Severity: error

**Meaning.** An expression in a PARALLEL call reads another call's result without AFTER. It can also read a value that the block writes only after all calls finish (SET targets, ERROR\_AS, STATUS\_AS). Calls run at the same time, so the value is not there yet.

**Fix.** Add `AFTER: <name>` to wait for the other call, or read the value in a later step.

## PARALLEL\_DEPENDENCY\_INVALID

Severity: error

**Meaning.** An AFTER entry names no call in the block, names its own call, forms a cycle, chains deeper than 3, or is used with a WAIT other than `all`.

**Fix.** Point AFTER at the AS of another call in the block. Remove the cycle. Keep `WAIT: all`.

## PARALLEL\_EXPRESSION\_INVALID

Severity: error

**Meaning.** A WHEN, FILTER, KEY\_BY, or SET expression in a PARALLEL call does not parse.

**Fix.** Fix the expression syntax.

## PARALLEL\_LIMIT\_EXCEEDED

Severity: error

**Meaning.** A PARALLEL block exceeds a platform limit: 10 calls, 20 requests per batch (each FOR\_EACH counts its MAX\_ITEMS), MAX\_ITEMS 20, MAX\_CONCURRENCY 1 to 10, RETRY 3, or TIMEOUT 120 seconds.

**Fix.** Lower the value named in the message, or split the work across steps.

## PARALLEL\_MAPPING\_TARGET\_OVERLAP

Severity: warning

**Meaning.** Two tools in one PARALLEL block write the same variable in their `on_result.set` mappings. Results bind in the order the calls are written, so the later call's value wins.

**Fix.** Give the mappings different targets, or accept that the later call wins.

## PARALLEL\_NAME\_CONFLICT

Severity: error

**Meaning.** Two names in a PARALLEL block collide (AS, ERROR\_AS, STATUS\_AS, SET targets, item names). The name `result` is also reserved for the call result.

**Fix.** Give each value its own name.

## PARALLEL\_OPTION\_CONFLICT

Severity: error

**Meaning.** PARALLEL options contradict each other. Examples: REQUIRED or FAIL\_FAST with a WAIT other than `all`, WAIT n larger than the number of calls, a FALLBACK that is the call's own tool, or a FALLBACK that does not accept the call's WITH inputs.

**Fix.** Adjust the options as the message describes.

## PARALLEL\_REQUIRED\_WITH\_ON\_RESULT

Severity: warning

**Meaning.** A PARALLEL step has a REQUIRED call and ON\_RESULT branches. A matching ON\_RESULT branch runs before ON\_FAILURE, so it can route the step even when a required call failed.

**Fix.** Check the status view in the ON\_RESULT branch, or route only through ON\_SUCCESS, ON\_PARTIAL, and ON\_FAILURE.

## PARALLEL\_SOURCE\_INVALID

Severity: error

**Meaning.** The PARALLEL block has a parse error. Examples: an unknown key, a value in the wrong form, a FOR\_EACH-only key without FOR\_EACH, or no calls. The block does not run, because running it without the bad part would do something other than what you wrote.

**Fix.** Fix the key or value that the message names. Durations are `1500ms`, `2s`, or a whole number of milliseconds. WAIT is `all`, `first`, `first_success`, or a number.

## PARALLEL\_STEP\_SHAPE

Severity: error

**Meaning.** A FLOW step combines PARALLEL with CALL, GATHER, SECURE\_INPUT, HUMAN\_APPROVAL, or `REASONING: true`. Or it uses ON\_PARTIAL without PARALLEL. A PARALLEL step only runs its calls and routes on their outcome.

**Fix.** Move the other construct to its own step before or after the PARALLEL step. Or add a PARALLEL block for ON\_PARTIAL.

## PARALLEL\_TOOL\_NOT\_ALLOWED

Severity: error

**Meaning.** A PARALLEL call or FALLBACK uses a tool that needs user confirmation, publishes SearchAI citations, captures or consumes vault secrets, or has lifecycle hooks that do more than SET, CLEAR, or LOG. Such tools change conversation state while they run. A parallel batch cannot keep that state in order.

**Fix.** Call the tool in its own CALL step, or limit its hooks to SET, CLEAR, and LOG.

## PARALLEL\_TOOL\_NOT\_READ\_ONLY

Severity: error

**Meaning.** A PARALLEL call or FALLBACK uses a tool that may change data. Only read-only tools run in parallel, because several writes at once could commit in part or in the wrong order. A tool with no declared effect counts as a write, unless it is an HTTP GET, HEAD, or OPTIONS tool.

**Fix.** Declare `effect: read_only` on the tool if it only reads data. Or call the tool in its own CALL step.

## PARALLEL\_TOOL\_UNKNOWN

Severity: error

**Meaning.** A PARALLEL call or FALLBACK names a tool the agent does not have.

**Fix.** Check the tool name, or add the tool to the agent.

## PLAINTEXT\_HTTP\_HEADER\_SECRET

Severity: warning

**Meaning.** An HTTP tool header contains a high-confidence credential-like literal. The compiler preserves the authored request for compatibility, but the value can cross export, logging or runtime boundaries without secret-management controls.

**Fix.** Replace the literal with a secret-backed config reference such as \{\{config.API\_TOKEN}}, or attach the tool to an auth profile. Keep credentials out of authored HTTP header values.

## PLAIN\_ENGLISH\_COMPLETE\_WHEN

Severity: error

**Meaning.** The WHEN of a COMPLETE condition is prose, multi-word text with none of the structured comparison, logic, or function forms, but COMPLETE WHEN is evaluated deterministically, not read by the model. The sentence would never be true, so the agent could never complete through this condition.

**Fix.** Restate the condition as a boolean expression over session state, for example task\_done == true or refund\_status == "issued". If the judgment the sentence describes genuinely belongs to the model, have a reasoning step or instruction set a variable recording the outcome, then complete on that variable, or classify into intent state first and complete on the classified value.

## PROFILE\_INVALID\_APPLIES\_TO

Severity: error

**Meaning.** The behavior profile has an `APPLIES_TO` line with a value other than `all_agents`. `APPLIES_TO` only widens a profile to every agent in the project, so no other value is supported. Compile fails for that profile.

**Fix.** Write `APPLIES_TO: all_agents` to attach the profile to every agent. Or delete the line and reference the profile from each agent with `USE BEHAVIOR_PROFILE:`.

## REALTIME\_TOOL\_EFFECT\_REQUIRED

Severity: error

**Meaning.** Strict realtime effect metadata mode found a business tool without an explicit effect, so the compiler cannot safely select its guarded scheduler lane.

**Fix.** Add effect: read\_only, state\_write, or side\_effect. Keep compatibility mode only while migrating legacy tools; missing metadata there retains the legacy queue/idempotency path.

## RESERVED\_VARIABLE\_NAME

Severity: warning

**Meaning.** A SET assignment writes to a system-reserved variable name. The runtime uses those names for its own values, regex capture groups among them, and may overwrite the assignment mid-turn.

**Fix.** Rename the variable to one outside the reserved set; a short agent-specific prefix is enough to keep it clear of runtime names.

## ROUTE\_WHEN\_MULTILINE\_JOINED

Severity: warning

**Meaning.** A HANDOFF or DELEGATE condition written on indented lines below an empty WHEN: or ENABLED\_WHEN:, or continued below an inline ENABLED\_WHEN: value, is joined with single spaces into one condition. A line that looks like a key or starts a new entry ends the condition, and # lines are skipped. A condition opened with an explicit block indicator (| or >) is joined the same way without this warning.

**Fix.** Check that the joined condition is the one you meant. Write it on one line, or open it with a block indicator (ENABLED\_WHEN: |), to silence this warning.

## SECRET\_REF\_UNSUPPORTED\_CONSUMER\_TYPE

Severity: error

**Meaning.** A tool declares SECRET\_ACCESS read of a key, but its type cannot consume secrets. Only http tools resolve \{\{\_secret.`<key>`}}; every other type routes to an executor with no secret-substitution step, and a tool with no type at all falls through to the contract-only fallback. The declaration is not merely inert: the runtime takes the value from the single-use vault on the way in, so the entry is spent without ever being delivered, and the next legitimately authorized consumer fails with "already used", a failure that points at the wrong tool. RESULT\_SECRETS capture is unaffected and still works on any tool type.

**Fix.** Move the call that needs the secret into an http tool, or remove the SECRET\_ACCESS block from this one. If a workflow was chosen because a fixed body template could not build a variable-length batch payload, an http tool can now build one directly with \{\{#each input.`<parameter>`}}, keeping the secret inside the only sink that resolves it.

## SECURE\_EMBEDDED\_PLACEHOLDER

Severity: error

**Meaning.** A SECURE\_INPUT deliver.args value embeds a \{\{secure.`<field>`}} placeholder inside a larger string (for example, "pan-\{\{secure.card\_number}}") instead of using it as the whole argument value. Secure field values never pass through the LLM or session state, concatenating them into other text would force the runtime to materialize the raw PCI-scoped value outside the secure delivery path.

**Fix.** Deliver each secure field as its own whole-value placeholder, for example, \{ pan: "\{\{secure.card\_number}}" }, never interpolated into a longer string. Non-secure context can still use \{\{ctx.\*}} placeholders freely.

## SECURE\_INPUT\_EMPTY\_OUTCOME\_ROUTE

Severity: error

**Meaning.** A SECURE\_INPUT outcome route (ON\_SUCCESS, ON\_TIMEOUT, ON\_CANCEL or ON\_FAIL) is written but names no step. These routes take a FLOW step name only; a RESPOND or other block indented under one is not part of SECURE\_INPUT and is ignored. With the route empty, the flow has nowhere to go after that outcome, so after a real payment the caller hears the empty-response fallback instead of a confirmation.

**Fix.** Name a FLOW step in the route, for example, ON\_SUCCESS: payment\_done, and write the RESPOND (and any other work) in that step.

## SECURE\_INPUT\_FIELD\_VOICE\_ON\_SECRET

Severity: error

**Meaning.** A SECURE\_INPUT field sets MODE, RECORD, or SPEECH\_AS but is not marked NOT\_SECRET. These settings let a field be spoken, recorded, and shown in the transcript. They are allowed only on a value you declared readable. A secret field (card number, expiry, security code) always uses the step MODE, is never recorded, and never shows its value.

**Fix.** Remove MODE, RECORD, and SPEECH\_AS from the secret field. For a value such as a postal code or a consent answer, add `NOT_SECRET: true` and SAVE\_AS instead.

## SECURE\_INPUT\_INVALID\_FIELD\_MODE

Severity: error

**Meaning.** A NOT\_SECRET field of a SECURE\_INPUT step sets a MODE that is empty or names a channel other than `dtmf` or `speech`. A mistyped word such as `spech` would be ignored, and the field would have fewer ways to be answered than you wrote, or none.

**Fix.** Set the field MODE to a non-empty list of `dtmf` and `speech`, for example `MODE: [dtmf, speech]`.

## SECURE\_INPUT\_INVALID\_MODE

Severity: error

**Meaning.** A SECURE\_INPUT step declares a MODE that is empty or includes a collection channel other than dtmf or speech. The DSL parser silently drops any unrecognized mode token, so an author who mistypes a mode ends up with an empty array and a gate the runtime cannot open.

**Fix.** Set MODE to a non-empty list drawn only from dtmf and speech, for example, MODE: \[dtmf] or MODE: \[dtmf, speech].

## SECURE\_INPUT\_INVALID\_NOT\_SECRET

Severity: error

**Meaning.** A SECURE\_INPUT field marked NOT\_SECRET breaks a rule that keeps card data secret. NOT\_SECRET takes an allow-listed kind (postal\_code) together with SAVE\_AS, never READ\_ONCE, a luhn or date\_mmYY check, or a field named like card data or a PIN, and 5 to 10 digits. Once accepted the value is a session variable, so later CALLs read that variable, not \{\{secure.`<field>`}}. The step must keep at least one secret field, and the delivery must send one.

**Fix.** Write NOT\_SECRET: postal\_code with SAVE\_AS: billing\_zip and COLLECT: \{ digits: 5..5 }, and pass "\{\{billing\_zip}}" to the CALL. Leave card numbers, expiry dates, security codes and PINs secret.

## SECURE\_INPUT\_INVALID\_PROGRESS\_PROMPT

Severity: error

**Meaning.** A SECURE\_INPUT PROGRESS\_PROMPT has no TEXT, or its timing is out of range. The hold line needs words to speak; AFTER may be at most 60 seconds and REPEAT\_EVERY must be 5 to 60 seconds, so a repeat does not cut off the line before it or leave the caller waiting too long.

**Fix.** Write TEXT: "\{\{locale.PAYMENT\_PROCESSING}}" (or a language map), AFTER: 0s to 60s and REPEAT\_EVERY: 5s to 60s.

## SECURE\_INPUT\_INVALID\_RESULT\_CONTRACT

Severity: error

**Meaning.** The SECURE\_INPUT delivery CALL result contract cannot be honoured exactly: AS is not a variable name or has no RESULT\_FIELDS allowlist, RESULT\_FIELDS has no AS to bind to or lists an invalid path, a duplicate or a top-level path named failure (reserved: on ON\_FAIL the step writes failure.reason and failure.http\_status under AS), or SUCCESS\_WHEN is empty, names an invalid path, or lists no accepted value. A path is a response field name or a dotted path of at most five names (result.status). Nothing from a secure response leaves the secure boundary except the scalar fields RESULT\_FIELDS names, and SUCCESS\_WHEN is exact equality on the named fields.

**Fix.** Write the contract as AS: `<variable>`, RESULT\_FIELDS: \[Field, result.status, ...] with response field names or dotted paths of at most five names, and optionally SUCCESS\_WHEN: \{ Field: "value" } or \{ result.status: \[value1, value2] }.

## SECURE\_INPUT\_INVALID\_SAVE\_AS

Severity: error

**Meaning.** A SECURE\_INPUT field SAVE\_AS is not a variable name, or the step already writes that name as the delivery AS, SAFE\_DETAILS\_AS or another field's SAVE\_AS. Each would replace the other.

**Fix.** Give SAVE\_AS its own variable name of letters, digits and underscores, for example, `SAVE_AS: billing_zip`.

## SECURE\_INPUT\_INVALID\_SPEECH\_AS

Severity: error

**Meaning.** A NOT\_SECRET field of a SECURE\_INPUT step sets SPEECH\_AS to a value other than `digits` or `text`. `digits` reads a spoken answer as a number (`one one one twenty five` is 11125). `text` keeps the caller's words.

**Fix.** Write `SPEECH_AS: digits` for a spoken number, or `SPEECH_AS: text` for words such as a yes or no answer.

## SECURE\_INPUT\_MISSING\_DELIVER\_TOOL

Severity: error

**Meaning.** A SECURE\_INPUT step has no deliver tool. The parser defaults deliver to an empty tool name when the step has no CALL line, which leaves the collected secure fields with nowhere to go, the gate would collect PCI-scoped values and then have no tool invocation to deliver them to.

**Fix.** Add a CALL `<tool>` WITH: \{ ... } line inside the SECURE\_INPUT block naming the tool that should receive the collected fields.

## SECURE\_INPUT\_MISSING\_PROMPT

Severity: error

**Meaning.** A SECURE\_INPUT step either declares no FIELDS at all, or declares a field with no usable PROMPT, neither a language map with at least one entry nor a template reference. A field the runtime cannot prompt for can never be collected.

**Fix.** Declare at least one field under FIELDS, and give each field a PROMPT, either a language-keyed map such as \{ en: "Enter card number" } or a \{ template: `<name>` } reference to a resolved survey template.

## SECURE\_INPUT\_NOT\_SECRET\_CARD\_DATA

Severity: warning

**Meaning.** A NOT\_SECRET field is checked with `luhn` or `date_mmYY`. The card number or expiry is then saved where later steps, tools, and reports can read it. The compiler still accepts it.

**Fix.** Remove NOT\_SECRET so the field stays secret, or check a value that is safe to read.

## SECURE\_INPUT\_PROGRESS\_PROMPT\_UNUSED

Severity: warning

**Meaning.** A SECURE\_INPUT field sets PROGRESS\_PROMPT, but the field has no VALIDATE CALL. A field hold line is spoken only while that field's VALIDATE CALL runs; built-in checks such as luhn or regex finish at once and never speak it.

**Fix.** Remove the field PROGRESS\_PROMPT, or move it to the SECURE\_INPUT block to speak it during the delivery CALL.

## SECURE\_INPUT\_PROMPT\_SECURE\_REFERENCE

Severity: error

**Meaning.** A SECURE\_INPUT field RETRY\_PROMPT or NO\_INPUT\_PROMPT contains a \{\{secure.`<field>`}} reference. Prompts are spoken to the caller and go through session state and traces, so a collected card value may never appear in one.

**Fix.** Remove the \{\{secure.\*}} reference from the prompt. Session variables such as \{\{amount}} and locale entries such as \{\{locale.CARD\_RETRY}} are allowed; for the card, use the safe details from SAFE\_DETAILS\_AS (for example, \{\{card.card\_number.last4}}) in a later step.

## SECURE\_INPUT\_SPEECH\_AS\_UNUSED

Severity: warning

**Meaning.** A NOT\_SECRET field of a SECURE\_INPUT step sets SPEECH\_AS, but neither the field MODE nor the step MODE allows speech. The field is answered only on the keypad, so SPEECH\_AS has no effect.

**Fix.** Add `speech` to the field MODE (`MODE: [dtmf, speech]`), or remove SPEECH\_AS.

## SECURE\_UNKNOWN\_FIELD

Severity: error

**Meaning.** A SECURE\_INPUT deliver.args value references \{\{secure.`<name>`}} for a field name that is not declared under this step's FIELDS. The runtime has no collected value to substitute, so delivery cannot succeed.

**Fix.** Either add a field with that name under FIELDS, or fix the \{\{secure.\*}} reference in deliver.args to name a field that is actually declared.

## SESSION\_MODEL\_WRITERS\_INVALID

Severity: error

**Meaning.** A session MODEL\_WRITERS declaration is not a list of non-empty agent names.

**Fix.** Use MODEL\_WRITERS: \[agent\_name, ...], or \[] to deny all model writers. Omit the declaration to preserve inferred ownership.

## SESSION\_MODEL\_WRITER\_UNKNOWN

Severity: error

**Meaning.** A session MODEL\_WRITERS declaration names an agent outside the compiled project.

**Fix.** Name a project agent exactly as declared, including case, or remove it from the writer list.

## SESSION\_READONLY\_DECLARATION\_MISMATCH

Severity: warning

**Meaning.** Agents disagree on READONLY for the same shared session field. READONLY applies to every agent of the project, so the model of an agent that declares the field writable is refused too.

**Fix.** Declare the field READONLY in every agent that declares it, or remove READONLY where another agent's model must write it. Authored writes such as SET, on\_result, hooks and CONTEXT.pass are not affected.

## SET\_PLACEHOLDER\_IN\_EXPRESSION

Severity: warning

**Meaning.** A SET value is a formula (a function call, a comparison, or arithmetic) that also holds a `{{name}}` placeholder. The runtime never evaluates a SET value that has a placeholder. It fills in the placeholder and stores the whole formula as text. A condition then reads that text as a non-empty value, so a gate such as `LOWER("{{flag}}") == "true"` is always on.

**Fix.** To compute the value, name the variable without braces: `LOWER(flag) == "true"`. To store text, put the whole value in quotes.

## SET\_QUOTED\_VALUE\_READ\_AS\_PATH

Severity: warning

**Meaning.** In `ON_INPUT`, `ON_RESULT`, `ON_SUCCESS` and `ON_FAILURE` branches, digression `DO` blocks, and handoff return handlers, a `SET` value written in quotes is stored without its quotes. A quoted bare name or dotted path, such as `"USER_REQUESTED_FOR_AGENT_TRANSFER"`, is then read as the variable or path of that name when one exists. It is stored as text only when none exists. A step-level `SET` keeps the quotes and always stores the text. The warning applies to an agent compiled in legacy `SET` value mode. A project created with literal `SET` value mode stores a complete quoted value as written and is not warned. A project created before the mode existed stays in legacy mode.

**Fix.** Move the assignment to a step-level `SET` when the value must always be text. Or use text that cannot match a variable name, for example text with a space or punctuation. Quoted text with spaces or punctuation is stored as written and does not warn.

## STEP\_PROFILE\_ALREADY\_AGENT\_LEVEL

Severity: warning

**Meaning.** A FLOW step references a profile that is already attached to the agent. The profile applies at agent scope only, and the step reference changes nothing.

**Fix.** Remove the step reference if the profile should apply across the agent. Remove the agent attachment if it should apply only to this step.

## STEP\_PROFILE\_CALL\_SCOPED\_FIELD

Severity: warning

**Meaning.** A step-attached profile sets `CONVERSATION.listening.mode`. The mode is fixed for the whole call, so a step ignores it.

**Fix.** Set `CONVERSATION.listening.mode` on the agent or in the channel configuration.

## STEP\_PROFILE\_NOT\_FOUND

Severity: warning

**Meaning.** A FLOW step references a behavior profile that is not in the compile set. The compiler leaves that step reference out. CI/CD release builds do not load profile documents, so step references on those paths report this code.

**Fix.** Add the profile to the project, or correct the step reference to match the profile name exactly.

## STEP\_PROFILE\_PRIORITY\_CONFLICT

Severity: warning

**Meaning.** Two different behavior profiles attached to the same FLOW step declare the same PRIORITY. Their merge order then depends on declaration order.

**Fix.** Give the step-attached profiles different PRIORITY values. Repeated references to the same profile are removed automatically.

## STEP\_PROFILE\_UNKNOWN\_TOOL

Severity: warning

**Meaning.** A step-attached profile hides a tool that the agent does not declare, so the hide has no effect.

**Fix.** Correct the `TOOLS.HIDE` name to a tool the agent declares, declare the tool, or remove the entry.

## STEP\_PROFILE\_UNSUPPORTED\_FIELD

Severity: warning

**Meaning.** A step-attached profile contains RESPONSE\_RULES, GATHER\_OVERRIDES, FLOW modifications, or FLOW\_REPLACE. These are not applied at step scope.

**Fix.** Move the field to an agent-attached profile if it should affect the agent, or remove it from the step profile.

## STEP\_SET\_DUPLICATE\_TARGET

Severity: warning

**Meaning.** A FLOW step SET block writes the same variable on more than one line. Once you publish the agent again, the lines run one by one in written order. Each line reads the value the line before it wrote: `x = 1` then `x = x + 1` gives 2. A version published before keeps only the last line for that variable, run where the first line is, so the earlier lines never run there.

**Fix.** Check that the result in written order is the one you want. Then publish the agent so live sessions use it. To keep the old result, delete the earlier lines for that variable.

## SYSTEM\_PROMPT\_LIMITATIONS\_APPENDED

Severity: warning

**Meaning.** The agent declares LIMITATIONS and its own SYSTEM\_PROMPT, but the prompt has no \{\{limitations}} placeholder. The runtime adds the limitations after the prompt text under a "Limitations:" heading, so the model still receives every rule; this warning tells you where they end up.

**Fix.** Put \{\{limitations}} in SYSTEM\_PROMPT where the rules should appear (it renders as one "- rule" line per limitation), or keep the default placement after the prompt and ignore this warning.

## TOOL\_CACHE\_INELIGIBLE

Severity: warning

**Meaning.** The runtime reuses a tool result within one conversation only for read-only tools. An HTTP tool is read-only when its method is GET or HEAD, or when it declares `effect: read_only`. MCP, lambda, and synchronous workflow tools must declare `effect: read_only`. Connector, platform, and async webhook tools, async workflows, and system tools are never cached. The hint stays, and the tool runs on every call.

**Fix.** Remove `cacheable: true`, or declare `effect: read_only` if the tool never changes data. Strict validation reports this as an error for a tool that declares a write effect.

## TOOL\_CACHE\_INVALID

Severity: warning

**Meaning.** `cache_ttl_ms` must be a whole number of milliseconds from 1000 to 3600000. The runtime clamps a value outside the range and replaces any other value with the default of 60000. `cache_invalidated_by` must list other tools of the project that can change data. A tool cannot list itself. Both properties take effect only with `cacheable: true`.

**Fix.** Set `cache_ttl_ms` to a whole number from 1000 to 3600000. List only write tools of this project in `cache_invalidated_by`. Add `cacheable: true`.

## TOOL\_CONFIRMATION\_PHRASE\_NOT\_ACTION

Severity: warning

**Meaning.** The tool requires confirmation and has no consent\_action, so the confirmation question is built from the first sentence of its description ("Shall I `<description>` …?"). That sentence is a noun phrase or opens with a third-person verb, so the customer reads a broken question such as "Shall I synthetic transfer service for 25, Alex?".

**Fix.** Start the description with the action as a verb, for example "Transfer the amount to the beneficiary.", or set consent\_action on the confirmation.

## TOOL\_CONTEXT\_ACCESS\_READ\_BEFORE\_WRITE

Severity: warning

**Meaning.** A tool's CONTEXT\_ACCESS.read names a key that only that same tool's own ON\_RESULT or ON\_ERROR SET ever writes. That key cannot exist yet on the tool's first call in a session, so the runtime's context-injection guard fails the call closed every time (by design, an authorized-but-missing declared read never runs silently degraded). The declaration compiles clean today with no signal that the tool can never succeed on its first invocation.

**Fix.** Either drop the key from CONTEXT\_ACCESS.read if the tool does not actually need it as an input, or arrange for another tool or step earlier in the flow to populate it before this tool first runs. If the value truly can only come from this tool itself, read it from the tool result directly instead of declaring it as a CONTEXT\_ACCESS dependency.

## TOOL\_OUTPUT\_SCHEMA\_INVALID

Severity: error

**Meaning.** An MCP tool OUTPUT\_SCHEMA is the JSON Schema of the tool result. A value that is not valid JSON cannot describe the result, so it is dropped.

**Fix.** Write OUTPUT\_SCHEMA as a single JSON object, for example \{"type": "object", "properties": \{...}}.

## TOOL\_VOICE\_UNKNOWN\_KEY

Severity: warning

**Meaning.** A tool-level VOICE block sets the delivery policy of the reply generated after the tool returns. Acoustic voice settings belong to the reply, template or channel.

**Fix.** Keep only BARGE\_IN and STREAMING in the tool VOICE block. The listening mode is fixed per call: set CONVERSATION.listening.mode on the agent instead.

## UNKNOWN\_SURVEY\_TEMPLATE

Severity: error

**Meaning.** A FEEDBACK block names a survey template that does not exist in the project being compiled. A contextual project build reports this as an error and cannot publish the unresolved reference. The template supplies the question and rating control; Feedback Insights selects a compatible scoring method when results are read.

**Fix.** Correct the FEEDBACK\_TEMPLATE name to one the project defines, the message lists every available template, or create the template in the project Surveys area. Names are compared exactly. If the survey was meant to be authored inline, remove FEEDBACK\_TEMPLATE and give the block its own prompt and type instead.

## UNSAFE\_SIP\_AUTHORITY\_PATTERN

Severity: error

**Meaning.** A call\_transfer tool declares an approved\_authorities entry whose VDN (userinfo) uses a pattern outside the constrained digit-class DSL, a general regex metacharacter, group, alternation, anchor, or an unbounded length, that compileApprovedAuthority rejects as unsafe rather than silently narrowing it.

**Fix.** Express the VDN as an exact digit string or the digit-class DSL only ('\[0-9]' single-digit ranges, for example, 'sip:5210\[0-9]\[0-9]@172.0.41.7:5060'). Regex syntax such as '.\*', '+', '|', '(...)', or anchors is not supported.

## UNTRUSTED\_SIP\_TRANSFER\_DESTINATION

Severity: warning

**Meaning.** A call\_transfer tool declares a sipTransferId default without default\_source: config or system, so the value is treated as model-supplied and ignored at transfer time.

**Fix.** Add default\_source: config and use a literal SIP URI when the agent should own the transfer destination. Otherwise remove the default and configure the target at the project level.

## VOICE\_BARGE\_IN\_ILLEGAL\_PLACEMENT

Severity: error

**Meaning.** Scoped barge-in changes a single playback lifecycle and is not a behavior-profile, channel-override, free-standing ON\_START or YAML execution.voice setting. ABL EXECUTION.voice and MESSAGES never applied it, so they ignore it with the warning VOICE\_DELIVERY\_KEY\_IGNORED\_PLACEMENT instead.

**Fix.** Move BARGE\_IN to a template, FLOW step, GATHER field, tool VOICE block, or the VOICE block under RESPOND.

## VOICE\_DELIVERY\_KEY\_IGNORED\_PLACEMENT

Severity: warning

**Meaning.** BARGE\_IN and STREAMING choose how one spoken output is delivered, so they take effect on a template, FLOW step, GATHER field, tool VOICE block or the VOICE block under RESPOND. Under ABL EXECUTION.voice and MESSAGES they have never had an effect: the line is ignored, is not stored, is never read as message text, and the agent keeps compiling.

**Fix.** Remove the line, or move it to a template, FLOW step, GATHER field, tool VOICE block, or the VOICE block under RESPOND. For a call-wide default use CONVERSATION.listening.barge\_in.

## VOICE\_INVALID\_BARGE\_IN

Severity: error

**Meaning.** Per-output barge-in controls are a closed policy enum. An invalid value must not silently inherit or change playback behaviour.

**Fix.** Set VOICE.BARGE\_IN to allow or disallow, in lowercase.

## VOICE\_INVALID\_STREAMING

Severity: warning

**Meaning.** Per-output streaming is a boolean. A non-boolean value is ignored, so the next layer's setting stands.

**Fix.** Set VOICE.STREAMING to true or false.

## VOICE\_INVALID\_TURN\_DETECTION

Severity: error

**Meaning.** turn\_detection takes `enabled` (true or false) and an optional `eou_threshold` of 0.3, 0.4, 0.5, 0.6, 0.7, 0.8 or 0.9. An invalid value is dropped so the call keeps the next level's setting.

**Fix.** Write turn\_detection with enabled: true or false, and eou\_threshold set to 0.3, 0.4, 0.5, 0.6, 0.7, 0.8 or 0.9 (0.3 answers fastest, 0.9 Slow dictation waits longest).

## VOICE\_LISTENING\_CALL\_LEVEL\_ONLY

Severity: error

**Meaning.** The listening mode (background or turn\_taking) is resolved once at call start and never changes during the call, so it cannot be authored per turn, step, template, field or tool.

**Fix.** Remove LISTENING from this VOICE block and set CONVERSATION.listening.mode (agent or behavior profile) or the channel listeningMode instead.

## VOICE\_NO\_INPUT\_ILLEGAL\_PLACEMENT

Severity: error

**Meaning.** A caller-silence policy belongs to the step that waits for the caller. Under a GATHER field, RESPOND, branch, handler or response format it would never be applied, so it is rejected instead of being dropped.

**Fix.** Move ON\_NO\_INPUT to the VOICE block directly under the FLOW step, or to CONVERSATION.listening.on\_no\_input for the whole agent.

## VOICE\_SIP\_HEADERS\_ILLEGAL\_PLACEMENT

Severity: warning

**Meaning.** SIP headers authored under VOICE are sent on the SIP BYE that ends the voice call, and only a COMPLETE condition ends the call that way. Under a RESPOND, FLOW step, GATHER field, branch, handler or response format there is no BYE to carry them, so the block is ignored.

**Fix.** Move SIP\_HEADERS to the VOICE block of the COMPLETE condition that ends the call. Headers for a transfer belong in the ESCALATE routing (routing.voice.sip\_headers).

## VOICE\_STREAMING\_LEGACY\_PLACEMENT

Severity: warning

**Meaning.** Per-output streaming belongs on a template, FLOW step, GATHER field, tool or concrete RESPOND output. Behavior-profile, channel-override and free-standing ON\_START VOICE blocks, and YAML execution.voice, still accept it so existing agents keep compiling. ABL EXECUTION.voice and MESSAGES ignore it instead (see VOICE\_DELIVERY\_KEY\_IGNORED\_PLACEMENT).

**Fix.** Move STREAMING to a template, FLOW step, GATHER field, tool VOICE block, or the VOICE block under RESPOND.

## VOICE\_TURN\_DETECTION\_WITH\_END\_OF\_SPEECH

Severity: warning

**Meaning.** While gateway turn detection is on, the gateway decides when the caller has finished, so the end-of-speech hint in the same block has no effect on that turn.

**Fix.** Remove end\_of\_speech\_turn\_type / end\_of\_speech\_timeout\_ms from this block, or turn turn detection off here.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.