CalvinBackup/shannon
1
0
Fork 0
mirror of https://github.com/KeygraphHQ/shannon.git synced 2026-09-28 04:22:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat: multi-provider model support, SARIF output, and exploit-mode fixes (#402)

Browse Source 
* 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
This commit is contained in:
ezl-keygraph
2026-07-30 19:31:52 +05:30
committed by GitHub
parent 30a12114ae
commit 1ce250d6a5
69 changed files with 3225 additions and 1471 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/worker/src/audit/metrics-tracker.ts
+23 -1
View File
@@ -23,6 +23,11 @@ interface AttemptData {
attempt_number: number;
duration_ms: number;
cost_usd: number;
input_tokens?: number | undefined;
output_tokens?: number | undefined;
cache_read_tokens?: number | undefined;
cache_write_tokens?: number | undefined;
turns?: number | undefined;
success: boolean;
timestamp: string;
model?: string | undefined;
@@ -34,6 +39,10 @@ interface AgentAuditMetrics {
attempts: AttemptData[];
final_duration_ms: number;
total_cost_usd: number;
total_input_tokens: number;
total_output_tokens: number;
total_cache_read_tokens: number;
total_cache_write_tokens: number;
model?: string | undefined;
checkpoint?: string | undefined;
}
@@ -174,6 +183,10 @@ export class MetricsTracker {
attempts: [],
final_duration_ms: 0,
total_cost_usd: 0,
total_input_tokens: 0,
total_output_tokens: 0,
total_cache_read_tokens: 0,
total_cache_write_tokens: 0,
};
this.data.metrics.agents[agentName] = agent;
@@ -184,6 +197,11 @@ export class MetricsTracker {
cost_usd: result.cost_usd,
success: result.success,
timestamp: formatTimestamp(),
...(result.input_tokens !== undefined && { input_tokens: result.input_tokens }),
...(result.output_tokens !== undefined && { output_tokens: result.output_tokens }),
...(result.cache_read_tokens !== undefined && { cache_read_tokens: result.cache_read_tokens }),
...(result.cache_write_tokens !== undefined && { cache_write_tokens: result.cache_write_tokens }),
...(result.turns !== undefined && { turns: result.turns }),
};
if (result.model) {
@@ -197,8 +215,12 @@ export class MetricsTracker {
// 3. Append attempt to history
agent.attempts.push(attempt);
// 4. Recalculate total cost across all attempts (includes failures)
// 4. Recalculate totals across all attempts (includes failures)
agent.total_cost_usd = agent.attempts.reduce((sum, a) => sum + a.cost_usd, 0);
agent.total_input_tokens = agent.attempts.reduce((sum, a) => sum + (a.input_tokens ?? 0), 0);
agent.total_output_tokens = agent.attempts.reduce((sum, a) => sum + (a.output_tokens ?? 0), 0);
agent.total_cache_read_tokens = agent.attempts.reduce((sum, a) => sum + (a.cache_read_tokens ?? 0), 0);
agent.total_cache_write_tokens = agent.attempts.reduce((sum, a) => sum + (a.cache_write_tokens ?? 0), 0);
// 5. Update agent status based on outcome
if (result.success) {
apps/worker/src/audit/workflow-logger.ts
-14
View File
@@ -12,7 +12,6 @@
*/
import fs from 'node:fs/promises';
import { isFableModel, resolveModelId } from '../ai/models.js';
import { formatDuration, formatTimestamp } from '../utils/formatting.js';
import { LogStream } from './log-stream.js';
import { generateWorkflowLogPath, type SessionMetadata } from './utils.js';
@@ -87,19 +86,6 @@ export class WorkflowLogger {
`Started: ${formatTimestamp()}`,
];
// Surface Fable usage: its safety classifiers route cybersecurity tasks to
// Opus 4.8, so those phases run on Opus 4.8 regardless of the tier setting.
const fableTiers = (['small', 'medium', 'large'] as const)
.map((tier) => ({ tier, model: resolveModelId(tier) }))
.filter(({ model }) => isFableModel(model));
if (fableTiers.length > 0) {
const tierList = fableTiers.map(({ tier, model }) => `${tier} (${model})`).join(', ');
lines.push(
`Note: ${tierList} set to a Fable model. Fable's safety classifiers`,
` route cybersecurity tasks to Opus 4.8, so those phases run on Opus 4.8.`,
);
}
lines.push(`================================================================================`, ``);
return this.logStream.write(lines.join('\n'));