mirror of
https://github.com/KeygraphHQ/shannon.git
synced 2026-10-03 23:06:51 +02:00
ezl-keygraph
1ce250d6a5
* feat(worker): record token, cache, and turn usage per agent * feat: replace model tiers with a single SHANNON_AI_MODEL across five providers * feat(cli): rebuild the setup wizard for provider and model selection * docs: document single-model selection and supported providers * feat(worker): use chat completions for OpenAI behind a custom base URL * feat: add SHANNON_AI_OPENAI_FORMAT to pick the wire API for OpenAI gateways * refactor(cli): drop endpoint path hints from the gateway format picker * feat(worker): enable pi in-session provider retry with retry-after backoff * refactor(worker): hand provider error classification to pi and drop the Anthropic ladders * refactor: remove the subscription retry preset and pipeline config section * fix(worker): validate Bedrock credentials with the same live probe as other providers * feat(worker): render the report from structured findings instead of agent-written markdown * fix(worker): dispose the credential probe session on every path * fix(worker): refuse to replace the assembled report with an empty one * refactor(worker): catch post-processing throws across the whole finalization block * revert(worker): drop the report zero-findings guard * docs(worker): correct the retry split and Bedrock credential claims * docs: regenerate llms-full.txt from current sources * feat(cli): build and run the npx flow from a clone * refactor(cli): flatten the setup summary output * feat(cli): reject runs with more than one provider configured * fix(worker): say a rejected bash call never ran * chore(cli): drop grok-4.3 and gpt-5.6-luna from the setup suggestions * feat(worker): capture structured finding locations for SARIF output * fix(worker): enumerate queue confidence so the report inherits it verbatim * feat(worker): give the reporting phase a mode-specific output schema * feat(worker): emit a SARIF 2.1.0 log for exploitative runs * fix(worker): correct SARIF locations and defer fingerprinting to the upload action * fix(worker): drop the confidence suffix from the analysis-mode summary list * feat(worker): give exploit findings a dedicated code location field * feat(worker): carry structured code locations from the vuln queue to the report * fix(worker): join code locations from the vuln queue instead of re-asking agents * fix(worker): spell out the finding_id to category mapping in the tool schema * feat: drop Google/Gemini as a supported AI provider * fix(worker): stop asking the report agent for code locations * docs: correct the provider list and drop the removed rate-limit settings * docs: add provider cyber safeguards and suggested models per provider * docs: document the SARIF output and the report rating thresholds
45 lines
1.7 KiB
TypeScript
45 lines
1.7 KiB
TypeScript
// Copyright (C) 2025 Keygraph, Inc.
|
|
//
|
|
// This program is free software: you can redistribute it and/or modify
|
|
// it under the terms of the GNU Affero General Public License version 3
|
|
// as published by the Free Software Foundation.
|
|
|
|
import { type AssistantMessage, isContextOverflow, isRetryableAssistantError } from '@earendil-works/pi-ai';
|
|
import { PentestError } from '../../services/error-handling.js';
|
|
import { ErrorCode } from '../../types/errors.js';
|
|
|
|
/**
|
|
* Wrap a failed assistant turn, taking the verdict from pi.
|
|
*
|
|
* Overflow is separated first, as pi's retry contract requires: it means the
|
|
* request was too large, not that the provider faltered, so an identical retry
|
|
* would overflow again. Everything else goes to pi's classifier, which treats
|
|
* quota, billing, and auth exhaustion as terminal and load, throttling, and
|
|
* transport faults as transient — those were already retried in-session, so
|
|
* reaching here means the attempts were exhausted.
|
|
*
|
|
* `contextWindow` is omitted where overflow cannot apply, such as a one-word
|
|
* credential probe.
|
|
*/
|
|
export function providerTurnError(message: AssistantMessage, label: string, contextWindow?: number): PentestError {
|
|
const detail = (message.errorMessage ?? 'unknown provider error').slice(0, 300);
|
|
|
|
if (contextWindow !== undefined && isContextOverflow(message, contextWindow)) {
|
|
return new PentestError(
|
|
`${label}: context window exceeded after compaction: ${detail}`,
|
|
'unknown',
|
|
false,
|
|
{ contextWindow },
|
|
ErrorCode.AGENT_EXECUTION_FAILED,
|
|
);
|
|
}
|
|
|
|
return new PentestError(
|
|
`${label}: ${detail}`,
|
|
'unknown',
|
|
isRetryableAssistantError(message),
|
|
{},
|
|
ErrorCode.AGENT_EXECUTION_FAILED,
|
|
);
|
|
}
|