Introduce small/medium/large model tiers so agents use the appropriate
model for their task complexity. Pre-recon uses Opus (large) for deep
source code analysis, most agents use Sonnet (medium), and report uses
Haiku (small) for summarization.
- Add src/ai/models.ts with ModelTier type and resolveModel()
- Add modelTier field to AgentDefinition
- Refactor claude-executor env var passthrough into loop
- Add Bedrock credential validation in preflight and CLI
- Pass through Bedrock and model env vars in docker-compose
- Add `pipeline` config section with `retry_preset` and `max_concurrent_pipelines` options
- Add `subscription` retry preset with extended 6h max interval for Anthropic rate limit windows
- Replace Promise.allSettled with concurrency-limited runner for vuln/exploit pipelines
- Wire pipeline config through client, shared types, and workflow activity proxy selection
ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN were not forwarded to the
SDK subprocess environment, causing router mode to fail with
"Authentication failed: Invalid API key" as the subprocess hit
Anthropic directly with the placeholder key.
Replaces validateApiKey and validateOAuthToken (direct fetch calls) with
a single SDK-based query using claude-haiku-4-5-20251001. Uses
SDKAssistantMessageError types for structured error classification and
returns human-readable error messages for each failure case.
- Remove empty section markers (// === ... ===, // --- ... ---) that duplicate JSDoc or function names
- Remove "what" comments that restate the next line of code (e.g. // Save to disk, // Check for retryable patterns)
- Remove file-level descriptions that restate the filename (e.g. // Pure functions for formatting console output)
- Fix "Added by client" comment referencing implementation history → "Used for audit correlation"
- Preserve all WHY comments: error classification groups, billing/session limit explanations, ESM interop, exactOptionalPropertyTypes, mutex reasoning
- Move error-handling, git-manager, prompt-manager, queue-validation, and reporting into src/services/
- Delete src/constants.ts — relocate AGENT_VALIDATORS and MCP_AGENT_MAPPING into session-manager.ts alongside agent definitions
- Delete src/utils/output-formatter.ts — absorb filterJsonToolCalls and getAgentPrefix into ai/output-formatters.ts
- Extract ActivityLogger interface into src/types/activity-logger.ts to break temporal/ → services circular dependency
- Consolidate VulnType, ExploitationDecision into types/agents.ts and SessionMetadata into types/audit.ts
- Remove dead timingResults/costResults globals from utils/metrics.ts and all consumers
- Add DI container (src/services/) with AgentExecutionService, ConfigLoaderService, and ExploitationCheckerService — pure domain logic with no Temporal dependencies
- Introduce Result<T, E> type and ErrorCode enum for code-based error classification in classifyErrorForTemporal, replacing scattered string matching
- Consolidate billing/spending cap detection into utils/billing-detection.ts with shared pattern lists across message-handlers, claude-executor, and error-handling
- Extract LogStream abstraction for append-only logging with backpressure, used by both AgentLogger and WorkflowLogger
- Simplify activities.ts from inline lifecycle logic to thin wrappers delegating to services, with heartbeat and error classification
- Expand config-parser with human-readable AJV errors, security validation, and rule type-specific checks
- Remove 4 duplicate file I/O functions from audit/utils.ts, re-export from utils/file-io.ts
- Consolidate AgentEndResult interface into new types/audit.ts
- Use exported AgentDefinition from types/agents.ts in session-manager.ts
- Rename AgentMetrics to AgentAuditMetrics to disambiguate from temporal/shared.ts
Query functionality is redundant with the Temporal Web UI
at http://localhost:8233. Removes query.ts, CLI handler,
npm script, and all documentation references.
- Early exit when all agents already completed instead of running empty workflow
- Descriptive error when deliverables missing from disk despite session.json success
- Quote $WORKSPACE in shannon CLI to prevent word splitting
- Prevent MSYS from converting Unix container paths on Windows
- Install @anthropic-ai/claude-code globally in the Docker image
- Add Windows platform instructions to README
- Swap commitGitSuccess/getGitCommitHash order so checkpoint in
session.json points to the success commit (which contains deliverables)
instead of the pre-agent marker commit
- Simplify restoreGitCheckpoint: git reset --hard now naturally preserves
completed agent deliverables, removing the in-memory backup/restore
- Show cumulative cost/duration in workflow.log from session.json
- Fill in per-agent metrics for skipped agents in workflow.log breakdown
- Display cumulative cost in client output for resume runs
Moves the copyDeliverablesToAudit call from runAgentActivity (called after
every agent) to logWorkflowComplete (called once at workflow end). This
prevents intermediate agent runs from copying incomplete or rogue deliverables
into the audit trail.
logWorkflowComplete wrote to workflow.log but never called
updateSessionStatus, leaving all workspaces stuck as "in-progress"
in session.json. Also derive audit path for model injection instead
of requiring explicit outputPath.
logPhaseTransition was the first activity to create session.json but
didn't pass workflowId, so originalWorkflowId was never set. This
caused terminateExistingWorkflows to look up the workspace name instead
of the actual workflow ID during resume.
Also remove path import from types/agents.ts to fix Temporal workflow
bundle determinism error.
Support WORKSPACE=<name> flag for friendly workspace names that
auto-resume if they exist or create a new named workspace otherwise.
Add ./shannon workspaces command to list all workspaces with status,
duration, and cost.
When a workflow is interrupted (VM crash, Ctrl+C, Docker restart), it can
now be resumed by passing the workspace name. The system reads session.json
to determine which agents completed, validates deliverables exist on disk,
restores the git checkpoint, and skips already-completed agents.
- Add --workspace CLI flag and auto-terminate conflicting workflows
- Add loadResumeState, restoreGitCheckpoint, recordResumeAttempt activities
- Add skip logic for all 5 pipeline phases including parallel execution
- Separate sessionId (persistent directory) from workflowId (execution ID)
- Track resume attempts in session.json for audit trail
- Derive AgentName type from ALL_AGENTS array to eliminate duplication
- Add getDeliverablePath mapping for deliverable validation
- Replace single-call "Write to deliverables/" pattern with multi-step
Write + Edit chunked writing across all 12 agent prompts
- Standardize section name to "CHUNKED WRITING (MANDATORY)" for
vuln, exploit, pre-recon, and recon agents
- Prevents agents from hitting 32K output token limit when generating
large analysis reports and exploitation evidence
* fix: add file_path parameter to save_deliverable for large reports
Large deliverable reports can exceed output token limits when passed as
inline content. This change allows agents to write reports to disk first
and pass a file_path instead.
Changes:
- Add file_path parameter to save_deliverable MCP tool with path
traversal protection
- Pass CLAUDE_CODE_MAX_OUTPUT_TOKENS env var to SDK subprocesses
- Fix false positive error detection by extracting only text content
(not tool_use JSON) when checking for API errors
- Update all prompts to instruct agents to use file_path for large
reports and stop immediately after completion
* docs: simplify and condense CLAUDE.md
Reduce verbosity while preserving all essential information for AI
assistance. Makes the documentation more scannable and focused.
* feat: add issue number detection to pr command
The /pr command now automatically detects issue numbers from:
1. Explicit arguments (e.g., /pr 123 or /pr 123,456)
2. Branch name patterns (e.g., fix/123-bug, issue-456-feature)
Adds "Closes #X" lines to PR body to auto-close issues on merge.
* chore: remove CLAUDE_CODE_MAX_OUTPUT_TOKENS env var handling
No longer needed with the new Claude Agent SDK version.
* fix: restore max_output_tokens error handling
Podman doesn't support the `host-gateway` special value in extra_hosts,
which causes container startup failures on macOS with Podman Desktop.
Changes:
- Add docker-compose.docker.yml with extra_hosts override for Docker
- Update shannon script to detect Podman via `command -v podman`
- Skip extra_hosts override when Podman is detected
This ensures:
- Docker users (Linux): Get host.docker.internal working automatically
- Podman users (macOS): Base config works without modification
Co-authored-by: ajmallesh <ajmallesh@gmail.com>
