* Agents: add subagent orchestration controls
* Agents: add subagent orchestration controls (WIP uncommitted changes)
* feat(subagents): add depth-based spawn gating for sub-sub-agents
* feat(subagents): tool policy, registry, and announce chain for nested agents
* feat(subagents): system prompt, docs, changelog for nested sub-agents
* fix(subagents): prevent model fallback override, show model during active runs, and block context overflow fallback
Bug 1: When a session has an explicit model override (e.g., gpt/openai-codex),
the fallback candidate logic in resolveFallbackCandidates silently appended the
global primary model (opus) as a backstop. On reinjection/steer with a transient
error, the session could fall back to opus which has a smaller context window
and crash. Fix: when storedModelOverride is set, pass fallbacksOverride ?? []
instead of undefined, preventing the implicit primary backstop.
Bug 2: Active subagents showed 'model n/a' in /subagents list because
resolveModelDisplay only read entry.model/modelProvider (populated after run
completes). Fix: fall back to modelOverride/providerOverride fields which are
populated at spawn time via sessions.patch.
Bug 3: Context overflow errors (prompt too long, context_length_exceeded) could
theoretically escape runEmbeddedPiAgent and be treated as failover candidates
in runWithModelFallback, causing a switch to a model with a smaller context
window. Fix: in runWithModelFallback, detect context overflow errors via
isLikelyContextOverflowError and rethrow them immediately instead of trying the
next model candidate.
* fix(subagents): track spawn depth in session store and fix announce routing for nested agents
* Fix compaction status tracking and dedupe overflow compaction triggers
* fix(subagents): enforce depth block via session store and implement cascade kill
* fix: inject group chat context into system prompt
* fix(subagents): always write model to session store at spawn time
* Preserve spawnDepth when agent handler rewrites session entry
* fix(subagents): suppress announce on steer-restart
* fix(subagents): fallback spawned session model to runtime default
* fix(subagents): enforce spawn depth when caller key resolves by sessionId
* feat(subagents): implement active-first ordering for numeric targets and enhance task display
- Added a test to verify that subagents with numeric targets follow an active-first list ordering.
- Updated `resolveSubagentTarget` to sort subagent runs based on active status and recent activity.
- Enhanced task display in command responses to prevent truncation of long task descriptions.
- Introduced new utility functions for compacting task text and managing subagent run states.
* fix(subagents): show model for active runs via run record fallback
When the spawned model matches the agent's default model, the session
store's override fields are intentionally cleared (isDefault: true).
The model/modelProvider fields are only populated after the run
completes. This left active subagents showing 'model n/a'.
Fix: store the resolved model on SubagentRunRecord at registration
time, and use it as a fallback in both display paths (subagents tool
and /subagents command) when the session store entry has no model info.
Changes:
- SubagentRunRecord: add optional model field
- registerSubagentRun: accept and persist model param
- sessions-spawn-tool: pass resolvedModel to registerSubagentRun
- subagents-tool: pass run record model as fallback to resolveModelDisplay
- commands-subagents: pass run record model as fallback to resolveModelDisplay
* feat(chat): implement session key resolution and reset on sidebar navigation
- Added functions to resolve the main session key and reset chat state when switching sessions from the sidebar.
- Updated the `renderTab` function to handle session key changes when navigating to the chat tab.
- Introduced a test to verify that the session resets to "main" when opening chat from the sidebar navigation.
* fix: subagent timeout=0 passthrough and fallback prompt duplication
Bug 1: runTimeoutSeconds=0 now means 'no timeout' instead of applying 600s default
- sessions-spawn-tool: default to undefined (not 0) when neither timeout param
is provided; use != null check so explicit 0 passes through to gateway
- agent.ts: accept 0 as valid timeout (resolveAgentTimeoutMs already handles
0 → MAX_SAFE_TIMEOUT_MS)
Bug 2: model fallback no longer re-injects the original prompt as a duplicate
- agent.ts: track fallback attempt index; on retries use a short continuation
message instead of the full original prompt since the session file already
contains it from the first attempt
- Also skip re-sending images on fallback retries (already in session)
* feat(subagents): truncate long task descriptions in subagents command output
- Introduced a new utility function to format task previews, limiting their length to improve readability.
- Updated the command handler to use the new formatting function, ensuring task descriptions are truncated appropriately.
- Adjusted related tests to verify that long task descriptions are now truncated in the output.
* refactor(subagents): update subagent registry path resolution and improve command output formatting
- Replaced direct import of STATE_DIR with a utility function to resolve the state directory dynamically.
- Enhanced the formatting of command output for active and recent subagents, adding separators for better readability.
- Updated related tests to reflect changes in command output structure.
* fix(subagent): default sessions_spawn to no timeout when runTimeoutSeconds omitted
The previous fix (75a791106) correctly handled the case where
runTimeoutSeconds was explicitly set to 0 ("no timeout"). However,
when models omit the parameter entirely (which is common since the
schema marks it as optional), runTimeoutSeconds resolved to undefined.
undefined flowed through the chain as:
sessions_spawn → timeout: undefined (since undefined != null is false)
→ gateway agent handler → agentCommand opts.timeout: undefined
→ resolveAgentTimeoutMs({ overrideSeconds: undefined })
→ DEFAULT_AGENT_TIMEOUT_SECONDS (600s = 10 minutes)
This caused subagents to be killed at exactly 10 minutes even though
the user's intent (via TOOLS.md) was for subagents to run without a
timeout.
Fix: default runTimeoutSeconds to 0 (no timeout) when neither
runTimeoutSeconds nor timeoutSeconds is provided by the caller.
Subagent spawns are long-running by design and should not inherit the
600s agent-command default timeout.
* fix(subagent): accept timeout=0 in agent-via-gateway path (second 600s default)
* fix: thread timeout override through getReplyFromConfig dispatch path
getReplyFromConfig called resolveAgentTimeoutMs({ cfg }) with no override,
always falling back to the config default (600s). Add timeoutOverrideSeconds
to GetReplyOptions and pass it through as overrideSeconds so callers of the
dispatch chain can specify a custom timeout (0 = no timeout).
This complements the existing timeout threading in agentCommand and the
cron isolated-agent runner, which already pass overrideSeconds correctly.
* feat(model-fallback): normalize OpenAI Codex model references and enhance fallback handling
- Added normalization for OpenAI Codex model references, specifically converting "gpt-5.3-codex" to "openai-codex" before execution.
- Updated the `resolveFallbackCandidates` function to utilize the new normalization logic.
- Enhanced tests to verify the correct behavior of model normalization and fallback mechanisms.
- Introduced a new test case to ensure that the normalization process works as expected for various input formats.
* feat(tests): add unit tests for steer failure behavior in openclaw-tools
- Introduced a new test file to validate the behavior of subagents when steer replacement dispatch fails.
- Implemented tests to ensure that the announce behavior is restored correctly and that the suppression reason is cleared as expected.
- Enhanced the subagent registry with a new function to clear steer restart suppression.
- Updated related components to support the new test scenarios.
* fix(subagents): replace stop command with kill in slash commands and documentation
- Updated the `/subagents` command to replace `stop` with `kill` for consistency in controlling sub-agent runs.
- Modified related documentation to reflect the change in command usage.
- Removed legacy timeoutSeconds references from the sessions-spawn-tool schema and tests to streamline timeout handling.
- Enhanced tests to ensure correct behavior of the updated commands and their interactions.
* feat(tests): add unit tests for readLatestAssistantReply function
- Introduced a new test file for the `readLatestAssistantReply` function to validate its behavior with various message scenarios.
- Implemented tests to ensure the function correctly retrieves the latest assistant message and handles cases where the latest message has no text.
- Mocked the gateway call to simulate different message histories for comprehensive testing.
* feat(tests): enhance subagent kill-all cascade tests and announce formatting
- Added a new test to verify that the `kill-all` command cascades through ended parents to active descendants in subagents.
- Updated the subagent announce formatting tests to reflect changes in message structure, including the replacement of "Findings:" with "Result:" and the addition of new expectations for message content.
- Improved the handling of long findings and stats in the announce formatting logic to ensure concise output.
- Refactored related functions to enhance clarity and maintainability in the subagent registry and tools.
* refactor(subagent): update announce formatting and remove unused constants
- Modified the subagent announce formatting to replace "Findings:" with "Result:" and adjusted related expectations in tests.
- Removed constants for maximum announce findings characters and summary words, simplifying the announcement logic.
- Updated the handling of findings to retain full content instead of truncating, ensuring more informative outputs.
- Cleaned up unused imports in the commands-subagents file to enhance code clarity.
* feat(tests): enhance billing error handling in user-facing text
- Added tests to ensure that normal text mentioning billing plans is not rewritten, preserving user context.
- Updated the `isBillingErrorMessage` and `sanitizeUserFacingText` functions to improve handling of billing-related messages.
- Introduced new test cases for various scenarios involving billing messages to ensure accurate processing and output.
- Enhanced the subagent announce flow to correctly manage active descendant runs, preventing premature announcements.
* feat(subagent): enhance workflow guidance and auto-announcement clarity
- Added a new guideline in the subagent system prompt to emphasize trust in push-based completion, discouraging busy polling for status updates.
- Updated documentation to clarify that sub-agents will automatically announce their results, improving user understanding of the workflow.
- Enhanced tests to verify the new guidance on avoiding polling loops and to ensure the accuracy of the updated prompts.
* fix(cron): avoid announcing interim subagent spawn acks
* chore: clean post-rebase imports
* fix(cron): fall back to child replies when parent stays interim
* fix(subagents): make active-run guidance advisory
* fix(subagents): update announce flow to handle active descendants and enhance test coverage
- Modified the announce flow to defer announcements when active descendant runs are present, ensuring accurate status reporting.
- Updated tests to verify the new behavior, including scenarios where no fallback requester is available and ensuring proper handling of finished subagents.
- Enhanced the announce formatting to include an `expectFinal` flag for better clarity in the announcement process.
* fix(subagents): enhance announce flow and formatting for user updates
- Updated the announce flow to provide clearer instructions for user updates based on active subagent runs and requester context.
- Refactored the announcement logic to improve clarity and ensure internal context remains private.
- Enhanced tests to verify the new message expectations and formatting, including updated prompts for user-facing updates.
- Introduced a new function to build reply instructions based on session context, improving the overall announcement process.
* fix: resolve prep blockers and changelog placement (#14447) (thanks @tyler6204)
* fix: restore cron delivery-plan import after rebase (#14447) (thanks @tyler6204)
* fix: resolve test failures from rebase conflicts (#14447) (thanks @tyler6204)
* fix: apply formatting after rebase (#14447) (thanks @tyler6204)
620 lines
16 KiB
TypeScript
620 lines
16 KiB
TypeScript
import type { AssistantMessage } from "@mariozechner/pi-ai";
|
|
import { describe, expect, it } from "vitest";
|
|
import {
|
|
extractAssistantText,
|
|
formatReasoningMessage,
|
|
stripDowngradedToolCallText,
|
|
} from "./pi-embedded-utils.js";
|
|
|
|
describe("extractAssistantText", () => {
|
|
it("strips Minimax tool invocation XML from text", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `<invoke name="Bash">
|
|
<parameter name="command">netstat -tlnp | grep 18789</parameter>
|
|
</invoke>
|
|
</minimax:tool_call>`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("");
|
|
});
|
|
|
|
it("strips multiple tool invocations", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `Let me check that.<invoke name="Read">
|
|
<parameter name="path">/home/admin/test.txt</parameter>
|
|
</invoke>
|
|
</minimax:tool_call>`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Let me check that.");
|
|
});
|
|
|
|
it("keeps invoke snippets without Minimax markers", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `Example:\n<invoke name="Bash">\n<parameter name="command">ls</parameter>\n</invoke>`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe(
|
|
`Example:\n<invoke name="Bash">\n<parameter name="command">ls</parameter>\n</invoke>`,
|
|
);
|
|
});
|
|
|
|
it("preserves normal text without tool invocations", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "This is a normal response without any tool calls.",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("This is a normal response without any tool calls.");
|
|
});
|
|
|
|
it("sanitizes HTTP-ish error text only when stopReason is error", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
stopReason: "error",
|
|
errorMessage: "500 Internal Server Error",
|
|
content: [{ type: "text", text: "500 Internal Server Error" }],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("HTTP 500: Internal Server Error");
|
|
});
|
|
|
|
it("does not rewrite normal text that references billing plans", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "Firebase downgraded Chore Champ to the Spark plan; confirm whether billing should be re-enabled.",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe(
|
|
"Firebase downgraded Chore Champ to the Spark plan; confirm whether billing should be re-enabled.",
|
|
);
|
|
});
|
|
|
|
it("strips Minimax tool invocations with extra attributes", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `Before<invoke name='Bash' data-foo="bar">\n<parameter name="command">ls</parameter>\n</invoke>\n</minimax:tool_call>After`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Before\nAfter");
|
|
});
|
|
|
|
it("strips minimax tool_call open and close tags", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "Start<minimax:tool_call>Inner</minimax:tool_call>End",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("StartInnerEnd");
|
|
});
|
|
|
|
it("ignores invoke blocks without minimax markers", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "Before<invoke>Keep</invoke>After",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Before<invoke>Keep</invoke>After");
|
|
});
|
|
|
|
it("strips invoke blocks when minimax markers are present elsewhere", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "Before<invoke>Drop</invoke><minimax:tool_call>After",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("BeforeAfter");
|
|
});
|
|
|
|
it("strips invoke blocks with nested tags", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `A<invoke name="Bash"><param><deep>1</deep></param></invoke></minimax:tool_call>B`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("AB");
|
|
});
|
|
|
|
it("strips tool XML mixed with regular content", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `I'll help you with that.<invoke name="Bash">
|
|
<parameter name="command">ls -la</parameter>
|
|
</invoke>
|
|
</minimax:tool_call>Here are the results.`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("I'll help you with that.\nHere are the results.");
|
|
});
|
|
|
|
it("handles multiple invoke blocks in one message", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `First check.<invoke name="Read">
|
|
<parameter name="path">file1.txt</parameter>
|
|
</invoke>
|
|
</minimax:tool_call>Second check.<invoke name="Bash">
|
|
<parameter name="command">pwd</parameter>
|
|
</invoke>
|
|
</minimax:tool_call>Done.`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("First check.\nSecond check.\nDone.");
|
|
});
|
|
|
|
it("handles stray closing tags without opening tags", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "Some text here.</minimax:tool_call>More text.",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Some text here.More text.");
|
|
});
|
|
|
|
it("returns empty string when message is only tool invocations", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `<invoke name="Bash">
|
|
<parameter name="command">test</parameter>
|
|
</invoke>
|
|
</minimax:tool_call>`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("");
|
|
});
|
|
|
|
it("handles multiple text blocks", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "First block.",
|
|
},
|
|
{
|
|
type: "text",
|
|
text: `<invoke name="Bash">
|
|
<parameter name="command">ls</parameter>
|
|
</invoke>
|
|
</minimax:tool_call>`,
|
|
},
|
|
{
|
|
type: "text",
|
|
text: "Third block.",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("First block.\nThird block.");
|
|
});
|
|
|
|
it("strips downgraded Gemini tool call text representations", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `[Tool Call: exec (ID: toolu_vrtx_014w1P6B6w4V92v4VzG7Qk12)]
|
|
Arguments: { "command": "git status", "timeout": 120000 }`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("");
|
|
});
|
|
|
|
it("strips multiple downgraded tool calls", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `[Tool Call: read (ID: toolu_1)]
|
|
Arguments: { "path": "/some/file.txt" }
|
|
[Tool Call: exec (ID: toolu_2)]
|
|
Arguments: { "command": "ls -la" }`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("");
|
|
});
|
|
|
|
it("strips tool results for downgraded calls", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `[Tool Result for ID toolu_123]
|
|
{"status": "ok", "data": "some result"}`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("");
|
|
});
|
|
|
|
it("preserves text around downgraded tool calls", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `Let me check that for you.
|
|
[Tool Call: browser (ID: toolu_abc)]
|
|
Arguments: { "action": "act", "request": "click button" }`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Let me check that for you.");
|
|
});
|
|
|
|
it("preserves trailing text after downgraded tool call blocks", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `Intro text.
|
|
[Tool Call: read (ID: toolu_1)]
|
|
Arguments: {
|
|
"path": "/tmp/file.txt"
|
|
}
|
|
Back to the user.`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Intro text.\nBack to the user.");
|
|
});
|
|
|
|
it("handles multiple text blocks with tool calls and results", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "Here's what I found:",
|
|
},
|
|
{
|
|
type: "text",
|
|
text: `[Tool Call: read (ID: toolu_1)]
|
|
Arguments: { "path": "/test.txt" }`,
|
|
},
|
|
{
|
|
type: "text",
|
|
text: `[Tool Result for ID toolu_1]
|
|
File contents here`,
|
|
},
|
|
{
|
|
type: "text",
|
|
text: "Done checking.",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Here's what I found:\nDone checking.");
|
|
});
|
|
|
|
it("strips thinking tags from text content", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "<think>El usuario quiere retomar una tarea...</think>Aquí está tu respuesta.",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Aquí está tu respuesta.");
|
|
});
|
|
|
|
it("strips thinking tags with attributes", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `<think reason="deliberate">Hidden</think>Visible`,
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Visible");
|
|
});
|
|
|
|
it("strips thinking tags without closing tag", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "<think>Pensando sobre el problema...",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("");
|
|
});
|
|
|
|
it("strips thinking tags with various formats", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "Before<thinking>internal reasoning</thinking>After",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("BeforeAfter");
|
|
});
|
|
|
|
it("strips antthinking tags", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "<antthinking>Some reasoning</antthinking>The actual answer.",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("The actual answer.");
|
|
});
|
|
|
|
it("strips final tags while keeping content", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "<final>\nAnswer\n</final>",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Answer");
|
|
});
|
|
|
|
it("strips thought tags", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "<thought>Internal deliberation</thought>Final response.",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("Final response.");
|
|
});
|
|
|
|
it("handles nested or multiple thinking blocks", () => {
|
|
const msg: AssistantMessage = {
|
|
role: "assistant",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: "Start<think>first thought</think>Middle<think>second thought</think>End",
|
|
},
|
|
],
|
|
timestamp: Date.now(),
|
|
};
|
|
|
|
const result = extractAssistantText(msg);
|
|
expect(result).toBe("StartMiddleEnd");
|
|
});
|
|
});
|
|
|
|
describe("formatReasoningMessage", () => {
|
|
it("returns empty string for empty input", () => {
|
|
expect(formatReasoningMessage("")).toBe("");
|
|
});
|
|
|
|
it("returns empty string for whitespace-only input", () => {
|
|
expect(formatReasoningMessage(" \n \t ")).toBe("");
|
|
});
|
|
|
|
it("wraps single line in italics", () => {
|
|
expect(formatReasoningMessage("Single line of reasoning")).toBe(
|
|
"Reasoning:\n_Single line of reasoning_",
|
|
);
|
|
});
|
|
|
|
it("wraps each line separately for multiline text (Telegram fix)", () => {
|
|
expect(formatReasoningMessage("Line one\nLine two\nLine three")).toBe(
|
|
"Reasoning:\n_Line one_\n_Line two_\n_Line three_",
|
|
);
|
|
});
|
|
|
|
it("preserves empty lines between reasoning text", () => {
|
|
expect(formatReasoningMessage("First block\n\nSecond block")).toBe(
|
|
"Reasoning:\n_First block_\n\n_Second block_",
|
|
);
|
|
});
|
|
|
|
it("handles mixed empty and non-empty lines", () => {
|
|
expect(formatReasoningMessage("A\n\nB\nC")).toBe("Reasoning:\n_A_\n\n_B_\n_C_");
|
|
});
|
|
|
|
it("trims leading/trailing whitespace", () => {
|
|
expect(formatReasoningMessage(" \n Reasoning here \n ")).toBe(
|
|
"Reasoning:\n_Reasoning here_",
|
|
);
|
|
});
|
|
});
|
|
|
|
describe("stripDowngradedToolCallText", () => {
|
|
it("strips [Historical context: ...] blocks", () => {
|
|
const text = `[Historical context: a different model called tool "exec" with arguments {"command":"git status"}]`;
|
|
expect(stripDowngradedToolCallText(text)).toBe("");
|
|
});
|
|
|
|
it("preserves text before [Historical context: ...] blocks", () => {
|
|
const text = `Here is the answer.\n[Historical context: a different model called tool "read"]`;
|
|
expect(stripDowngradedToolCallText(text)).toBe("Here is the answer.");
|
|
});
|
|
|
|
it("preserves text around [Historical context: ...] blocks", () => {
|
|
const text = `Before.\n[Historical context: tool call info]\nAfter.`;
|
|
expect(stripDowngradedToolCallText(text)).toBe("Before.\nAfter.");
|
|
});
|
|
|
|
it("strips multiple [Historical context: ...] blocks", () => {
|
|
const text = `[Historical context: first tool call]\n[Historical context: second tool call]`;
|
|
expect(stripDowngradedToolCallText(text)).toBe("");
|
|
});
|
|
|
|
it("strips mixed [Tool Call: ...] and [Historical context: ...] blocks", () => {
|
|
const text = `Intro.\n[Tool Call: exec (ID: toolu_1)]\nArguments: { "command": "ls" }\n[Historical context: a different model called tool "read"]`;
|
|
expect(stripDowngradedToolCallText(text)).toBe("Intro.");
|
|
});
|
|
|
|
it("returns text unchanged when no markers are present", () => {
|
|
const text = "Just a normal response with no markers.";
|
|
expect(stripDowngradedToolCallText(text)).toBe("Just a normal response with no markers.");
|
|
});
|
|
|
|
it("returns empty string for empty input", () => {
|
|
expect(stripDowngradedToolCallText("")).toBe("");
|
|
});
|
|
});
|