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

* 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

apps/cli/src/model-spec.ts

@@ -0,0 +1,86 @@
+/**
+ * Parsing for the single model setting, `SHANNON_AI_MODEL=<provider>:<model-id>`.
+ *
+ * Mirrors apps/worker/src/ai/models.ts. The CLI cannot import from the worker
+ * package (it ships as a standalone bundle), so the provider list and the parse
+ * rule are duplicated here deliberately and must stay in sync.
+ */
+
+/** Providers Shannon can currently reach. Each is a pi-ai provider id. */
+export const SUPPORTED_PROVIDERS = ['anthropic', 'openai', 'xai', 'amazon-bedrock'] as const;
+
+export type ProviderId = (typeof SUPPORTED_PROVIDERS)[number];
+
+/**
+ * Env vars carrying each provider's API key, in precedence order. Any one of them
+ * satisfies the provider. Mirrors PROVIDER_API_KEY_ENV in apps/worker/src/ai/models.ts.
+ */
+export const PROVIDER_API_KEY_ENV: Readonly<Record<ProviderId, readonly string[]>> = {
+  anthropic: ['ANTHROPIC_API_KEY', 'CLAUDE_CODE_OAUTH_TOKEN'],
+  openai: ['OPENAI_API_KEY'],
+  xai: ['XAI_API_KEY'],
+  'amazon-bedrock': ['AWS_BEARER_TOKEN_BEDROCK'],
+};
+
+/** Additional env vars a provider requires beyond its API key. All must be set. */
+export const PROVIDER_EXTRA_ENV: Readonly<Record<ProviderId, readonly string[]>> = {
+  anthropic: [],
+  openai: [],
+  xai: [],
+  'amazon-bedrock': ['AWS_REGION'],
+};
+
+/** Human-readable credential requirement, used in "nothing configured" errors. */
+export const PROVIDER_CREDENTIAL_HINT: Readonly<Record<ProviderId, string>> = {
+  anthropic: 'ANTHROPIC_API_KEY (or CLAUDE_CODE_OAUTH_TOKEN)',
+  openai: 'OPENAI_API_KEY',
+  xai: 'XAI_API_KEY',
+  'amazon-bedrock': 'AWS_REGION and AWS_BEARER_TOKEN_BEDROCK',
+};
+
+/** Model used when SHANNON_AI_MODEL is unset. */
+export const DEFAULT_MODEL_SPEC = 'anthropic:claude-sonnet-4-6';
+
+/**
+ * Values SHANNON_AI_OPENAI_FORMAT accepts, selecting the wire format an
+ * OpenAI-compatible gateway serves. Mirrors OPENAI_FORMATS in
+ * apps/worker/src/ai/models.ts; the worker validates and applies it.
+ */
+export const OPENAI_FORMATS = ['chat-completions', 'responses'] as const;
+
+export type OpenAiFormat = (typeof OPENAI_FORMATS)[number];
+
+export interface ModelSpec {
+  providerId: ProviderId;
+  modelId: string;
+}
+
+function isSupportedProvider(value: string): value is ProviderId {
+  return (SUPPORTED_PROVIDERS as readonly string[]).includes(value);
+}
+
+/**
+ * Parse a `<provider>:<model-id>` spec. Splits on the first colon only, so colons
+ * inside a model ID survive (`amazon-bedrock:us.anthropic.claude-opus-4-5-20251101-v1:0`).
+ * Returns an error string rather than throwing, for the CLI's validation flow.
+ */
+export function parseModelSpec(spec: string): ModelSpec | string {
+  const trimmed = spec.trim();
+  const separator = trimmed.indexOf(':');
+  const malformed = `SHANNON_AI_MODEL must be "<provider>:<model-id>", got "${trimmed}". Example: ${DEFAULT_MODEL_SPEC}`;
+  if (separator === -1) return malformed;
+
+  const providerId = trimmed.slice(0, separator).trim();
+  const modelId = trimmed.slice(separator + 1).trim();
+  if (!providerId || !modelId) return malformed;
+
+  if (!isSupportedProvider(providerId)) {
+    return `Unsupported provider "${providerId}" in SHANNON_AI_MODEL. Supported providers: ${SUPPORTED_PROVIDERS.join(', ')}`;
+  }
+  return { providerId, modelId };
+}
+
+/** Resolve the run's model spec from the environment, or an error string. */
+export function resolveModelSpec(): ModelSpec | string {
+  return parseModelSpec(process.env.SHANNON_AI_MODEL || DEFAULT_MODEL_SPEC);
+}