Compare commits

..
Author SHA1 Message Date
ezl-keygraph 24862ddc9b chore: mark the pi harness migration as a breaking change
BREAKING CHANGE: Google Vertex AI is no longer a supported provider. The
CLAUDE_CODE_USE_VERTEX, ANTHROPIC_VERTEX_PROJECT, CLOUD_ML_REGION, and
GOOGLE_APPLICATION_CREDENTIALS environment variables, along with the
use_vertex, vertex_project, and cloud_ml_region config.toml keys, are
removed. Vertex users must switch to Anthropic, AWS Bedrock, or a custom
Anthropic-compatible base URL.

The CLAUDE_CODE_MAX_OUTPUT_TOKENS environment variable and the
max_output_tokens config.toml key are also removed.
2026-07-16 19:07:21 +05:30
ezl-keygraph b24caf8ae2 style(cli): collapse usage hint now that the beta tag is gone 2026-07-16 18:58:27 +05:30
ezl-keygraph 934a0ddd79 Merge remote-tracking branch 'origin/main' into feat/pi-harness-migration
# Conflicts:
#	CLAUDE.md
#	README.md
#	apps/cli/src/commands/start.ts
#	apps/cli/src/commands/uninstall.ts
#	apps/worker/src/services/agent-execution.ts
#	apps/worker/src/services/preflight.ts
#	apps/worker/src/session-manager.ts
#	apps/worker/src/temporal/activities.ts
#	apps/worker/src/temporal/shared.ts
#	apps/worker/src/temporal/workflows.ts
#	docs/ai-providers.md
#	llms-full.txt
2026-07-16 18:58:18 +05:30
ezl-keygraph d0b0ec3378 refactor(worker): converge shared core with shannon-oss (#388)
* fix(worker): port keygraph shared-core correctness fixes

* refactor(worker): adopt collectors/ and ai/pi/ layout; add task budget cap and cancellation

* refactor(worker): drop inconsistent Collector "Server" suffix

* refactor(worker): drop unused providerConfig/apiKey seams, resolve credentials from env only

* refactor(worker): port oss code_path pattern expansion + external_directory allow

* fix(worker): preserve dotfile paths in code_path avoid patterns (.env no longer stripped to env)

* feat(worker): render Unprocessed Vulnerabilities section in exploit deliverable (align with oss)

* feat(worker): request set_blind_spots for all vuln classes (align auth/ssrf with production prompts)

* refactor(worker): adopt unified permissionSystem* naming and helper layout

* refactor(worker): inline blind_spots into vuln deliverable section array

* chore(worker): drop unused zod dependency (tree is typebox-native)

* fix(worker): normalize base32 TOTP secret to accept padding and whitespace

* refactor(worker): adopt shared toolResult helper and flatSchema naming in collectors

* refactor(worker): use undefined over null in queue-schema builders

* docs(worker): converge renderer/collector doc comments to current pi terminology

* refactor(worker): adopt schema.ts cleanInput/stringEnum helpers in collectors

* feat(worker): converge exploit-collector/renderer with vendored; capture and render overview for blocked findings

* refactor(worker): converge session-tools/pipeline/exploitation-checker with vendored

* refactor(worker): converge task-tool usage reporting with vendored onUsage callback

* refactor(worker): converge structured output onto a submitTool executor channel

* docs(worker): expand exploit-renderer docstring to match shannon-oss

* docs(worker): adopt richer vuln-renderer docstring from shannon-oss

* docs(worker): neutralize billing-detection wording for shannon-oss parity

* fix(worker): verify checkpoint hash in the deliverables clone being reset

* fix(worker): fail fast on malformed exploitation queue JSON

* fix(worker): honor retryable flag when classifying exploitation-queue check failures

* fix(worker): fail fast on corrupted session.json in run-scope validation

* feat(worker): propagate Temporal cancellation signal into agent and auth pi sessions

* fix(worker): mark exploit agent complete when exploitation is skipped so resume skips it

* prompts: drop scan description from executive report prompt

* refactor(worker): add createGenericSubmitTool for raw JSON-schema submit tools

* refactor(worker): gate playwright-cli skill to browser agents via skillsOverride (adopt shannon-oss mechanism)

* docs(worker): correct formatLogTime comment to UTC to match toISOString

* refactor(worker): converge queue-schemas with shannon-oss (guarded count, decl order)

* refactor(worker): converge task-tool with shannon-oss (byte-identical; modelRegistry optional)

* fix(worker): use replaceLiteral for all prompt value insertions to prevent $-mangling

* fix(worker): classify agent execution failures by error type instead of hardcoding validation

* fix(worker): cap auth-failure detail at 250 chars to match shannon-oss

* style(worker): apply biome formatting

* refactor(worker): remove per-session task delegation cap from task tool
2026-07-16 14:09:02 +05:30
ezl-keygraph b845936aa5 feat(cli): restructure run folder and improve terminal UX (#383)
* feat: surface report at run root and nest run internals under .shannon

* feat: use plain-language wording in user-facing terminal messages

* feat(cli): guide users to watch scan progress and surface report path on start

* docs: sync run-folder layout and CLI wording across docs and comments

* feat(cli): add version command reporting package version or git SHA

* feat(cli): detect TTY for interactive prompts, color, and progress output

* docs: document --yes flag, version command, and tty module

* fix(cli): FORCE_COLOR precedence and plain uninstall --yes output

* fix(cli): respect empty NO_COLOR

* fix(cli): let NO_COLOR take precedence over FORCE_COLOR

* docs: mark claude-code-router integration as removed
2026-07-04 21:14:00 +05:30
ezl-keygraph 5596411bd3 fix: render agent deliverables before the success commit so resume preserves them (#377) 2026-06-23 14:25:17 +05:30
ezl-keygraph 6a86b6c4c3 fix(cli): pin npx command hints to beta tag 2026-06-17 18:30:02 +05:30
ezl-keygraph fb14a0170a ci: bump the beta release line to 2.0.0 (#356) 2026-06-17 18:09:27 +05:30
ezl-keygraph cf396fb9c7 feat(worker): enforce bounded bash timeouts via pi extension 2026-06-16 12:48:32 +05:30
ezl-keygraph f97afb482e refactor(worker): unify provider precedence between preflight and executor 2026-06-15 23:06:48 +05:30
ezl-keygraph c2bceba95c docs(worker): update stale sdk comments 2026-06-15 22:50:44 +05:30
ezl-keygraph 7c20384991 docs: remove vertex references from llms context 2026-06-15 22:48:59 +05:30
ezl-keygraph 0bc004a583 build: drop @anthropic-ai/claude-code from worker image 2026-06-15 22:42:12 +05:30
ezl-keygraph d3beea504a refactor(cli): remove CLAUDE_CODE_MAX_OUTPUT_TOKENS config 2026-06-15 22:40:50 +05:30
ezl-keygraph f46243a35a feat(worker): load playwright-cli skill via pi resource loader 2026-06-15 22:37:36 +05:30
ezl-keygraph 09e11b3ad9 fix(worker): restore minLength/minItems on pre-recon and exploit collector schemas 2026-06-15 21:06:29 +05:30
ezl-keygraph e16dcba13f refactor(prompts): drop collector server names from deliverable instructions 2026-06-15 20:21:22 +05:30
ezl-keygraph 5547afa73f refactor(prompts): drop stale MCP terminology for collector tools 2026-06-15 20:18:53 +05:30
ezl-keygraph 667e6ac4b0 refactor(prompts): use pi tool names (task, todo_write, read, bash, glob) 2026-06-15 20:03:26 +05:30
ezl-keygraph d18e928a6a feat(worker): add glob custom tool and route code_path globs to it 2026-06-15 20:03:26 +05:30
ezl-keygraph 58d0defea7 feat(worker): give task sub-agent write+bash, align tool descriptions 2026-06-15 19:54:20 +05:30
ezl-keygraph 9e845159b3 fix(worker): restore minLength/minItems on vuln-collector schemas 2026-06-15 18:42:53 +05:30
ezl-keygraph 0fd2f6bbe4 fix(worker): gate adaptive thinking to Opus models, drop CLAUDE_THINKING_LEVEL 2026-06-15 18:11:46 +05:30
ezl-keygraph 575465a741 feat(worker): pi-event-driven output formatting 2026-06-15 16:16:46 +05:30
ezl-keygraph 263b18e98a refactor(worker): rename claude-executor to pi-executor 2026-06-15 16:05:31 +05:30
ezl-keygraph 56241625a4 fix(worker): count sub-agent cost and surface compaction failures 2026-06-15 15:59:55 +05:30
ezl-keygraph 79fb49c159 feat(prompts): instruct agents to call submit_exploitation_queue and submit_auth_result 2026-06-15 15:49:02 +05:30
ezl-keygraph c275b27a6c fix(worker): route Bedrock and custom-base-URL providers from env 2026-06-15 15:36:14 +05:30
ezl-keygraph a9e966026c feat: remove Google Vertex AI provider support 2026-06-15 12:49:40 +05:30
ezl-keygraph 1908156525 feat(worker): migrate agent runtime from Claude Agent SDK to pi harness 2026-06-15 12:05:32 +05:30
2 changed files with 5 additions and 5 deletions

No files matched your search

+1 -1
View File
@@ -18,7 +18,7 @@ ANTHROPIC_API_KEY=your-api-key-here
# =============================================================================
# OPTION 2: Custom Base URL (compatible proxies, gateways, etc.)
# =============================================================================
# Point the agent at an alternative Anthropic-compatible endpoint.
# Point the SDK at an alternative Anthropic-compatible endpoint.
# ANTHROPIC_BASE_URL=https://your-proxy.example.com
# ANTHROPIC_AUTH_TOKEN=your-auth-token # Auth token for the custom endpoint
+4 -4
View File
@@ -127,7 +127,7 @@ Infra (Temporal) runs via `docker-compose.yml`. Workers are ephemeral `docker ru
- `apps/worker/src/paths.ts` — Centralized path constants (`PROMPTS_DIR`, `CONFIGS_DIR`, `WORKSPACES_DIR`)
- `apps/worker/src/session-manager.ts` — Agent definitions (`AGENTS` record). Agent types in `apps/worker/src/types/agents.ts`
- `apps/worker/src/config-parser.ts` — YAML config parsing with JSON Schema validation
- `apps/worker/src/ai/pi/pi-executor.ts` — pi harness integration (retry disabled; Temporal owns retry)
- `apps/worker/src/ai/pi-executor.ts` — pi harness integration (retry disabled; Temporal owns retry)
- `apps/worker/src/services/` — Business logic layer (Temporal-agnostic). Activities delegate here. Key: `agent-execution.ts`, `error-handling.ts`, `container.ts`
- `apps/worker/src/types/` — Consolidated types: `Result<T,E>`, `ErrorCode`, `AgentName`, `ActivityLogger`, etc.
- `apps/worker/src/utils/` — Shared utilities (file I/O, formatting, concurrency)
@@ -150,9 +150,9 @@ Durable workflow orchestration with crash recovery, queryable progress, intellig
5. **Reporting** (`report`) — Executive-level security report
### Supporting Systems
- **Configuration** — YAML configs in `apps/worker/configs/` with JSON Schema validation (`config-schema.json`). Supports auth settings (MFA/TOTP), URL/code rule scoping (`rules.avoid`/`rules.focus`), run-scope steering (`vuln_classes`, `exploit`), free-form `rules_of_engagement`, and post-hoc `report` filters (`min_severity`, `min_confidence`, `guidance`). `code_path` avoid rules are enforced via the `@gotgenes/pi-permission-system` extension: `apps/worker/src/temporal/activities.ts:syncCodePathDenyRules` writes a global `path` deny config once per workflow (`apps/worker/src/ai/pi/permission-system.ts:syncPermissionSystemConfig`), and the executor loads the extension when that config is present (`apps/worker/src/ai/pi/pi-executor.ts`), so denies fire across every tool and child `task` session. `vuln_classes`/`exploit` scope is locked into `session.json` on first run; resumes with a different scope fail fast (`persistOrValidateRunScope`). Credential resolution — local mode: env vars → `./.env`; npx mode: env vars → `~/.shannon/config.toml` (via `npx @keygraph/shannon setup`)
- **Configuration** — YAML configs in `apps/worker/configs/` with JSON Schema validation (`config-schema.json`). Supports auth settings (MFA/TOTP), URL/code rule scoping (`rules.avoid`/`rules.focus`), run-scope steering (`vuln_classes`, `exploit`), free-form `rules_of_engagement`, and post-hoc `report` filters (`min_severity`, `min_confidence`, `guidance`). `code_path` avoid rules are enforced via the `@gotgenes/pi-permission-system` extension: `apps/worker/src/temporal/activities.ts:syncCodePathDenyRules` writes a global `path` deny config once per workflow (`apps/worker/src/ai/settings-writer.ts:writeCodePathPermissionConfig`), and the executor loads the extension when that config is present (`apps/worker/src/ai/pi-executor.ts`), so denies fire across every tool and child `task` session. `vuln_classes`/`exploit` scope is locked into `session.json` on first run; resumes with a different scope fail fast (`persistOrValidateRunScope`). Credential resolution — local mode: env vars → `./.env`; npx mode: env vars → `~/.shannon/config.toml` (via `npx @keygraph/shannon setup`)
- **Prompts** — Per-phase templates in `apps/worker/prompts/` with variable substitution (`{{TARGET_URL}}`, `{{CONFIG_CONTEXT}}`). Shared partials in `apps/worker/prompts/shared/` via `apps/worker/src/services/prompt-manager.ts`, including `_code-path-rules.txt` (focus/avoid `[FILE]`/`[GLOB]` routing) and `_rules-of-engagement.txt` (free-text engagement rules). When `exploit: false`, `apps/worker/src/services/findings-renderer.ts` deterministically converts each `*_exploitation_queue.json` into a `*_findings.md` for report assembly — no LLM in the loop
- **Agent Harness (pi)** — Uses the **pi harness** (`@earendil-works/pi-coding-agent`, requires Node ≥ 22.19) via `apps/worker/src/ai/pi/pi-executor.ts` (`runPiPrompt` → `createAgentSession`, retry disabled so Temporal owns retry). Models resolve through pi-ai in `apps/worker/src/ai/models.ts` (Anthropic / Bedrock / custom base URL via `ModelRegistry`+`AuthStorage`). pi ships no JSON-schema output or `Task`/`TodoWrite` built-ins, so structured queues are captured via a `submit_exploitation_queue` custom tool (`apps/worker/src/ai/queue-schemas.ts`), and `task` (child sessions scoped to `read`, `grep`, `find`, `ls`, `write`, and `bash` — no nested `task` or collector tools; `CHILD_TOOLS` in `apps/worker/src/ai/pi/task-tool.ts`) + `todo_write` (`apps/worker/src/ai/pi/session-tools.ts`) are provided as custom tools; the per-phase collectors are pi custom tools (TypeBox `defineTool` in `apps/worker/src/collectors/`). Adaptive thinking (pi's `medium` level) is enabled only on Opus 4.6/4.7/4.8 (`supportsAdaptiveThinking`); every other model runs with thinking `off`. Disable per-scan via `CLAUDE_ADAPTIVE_THINKING=false` (→ `off`) / `core.adaptive_thinking = false` (npx TOML). Browser automation via `playwright-cli` with session isolation (`-s=<session>`). TOTP generation via `generate-totp` CLI tool. Login flow template at `apps/worker/prompts/shared/login-instructions.txt` supports form, SSO, API, and basic auth. On authenticated whitebox scans, the `validate-authentication` preflight performs the single real login and saves the browser session to `auth-state.json` in the per-session audit directory (path from `authStateFile()` in `apps/worker/src/audit/utils.ts`, derived from `generateAuditPath()`). The validation activity (`apps/worker/src/services/validate-authentication.ts`) removes any stale file from a prior run before the agent runs and verifies the file parses and contains cookies or storage before the preflight is marked complete; `logWorkflowComplete` deletes it when the workflow ends so authenticated cookies don't sit on disk between scans. Agent prompts opt in to session reuse by `@include(shared/_shared-session.txt)` before their `<login_instructions>` block — the partial restores the session and falls through to the full login flow if verification fails. `vuln-auth`/`exploit-auth` omit the include and own their own login
- **Agent Harness (pi)** — Uses the **pi harness** (`@earendil-works/pi-coding-agent`, requires Node ≥ 22.19) via `apps/worker/src/ai/pi-executor.ts` (`runPiPrompt` → `createAgentSession`, retry disabled so Temporal owns retry). Models resolve through pi-ai in `apps/worker/src/ai/models.ts` (Anthropic / Bedrock / custom base URL via `ModelRegistry`+`AuthStorage`). pi ships no JSON-schema output or `Task`/`TodoWrite` built-ins, so structured queues are captured via a `submit_exploitation_queue` custom tool (`apps/worker/src/ai/queue-schemas.ts`), and `task` (read-only child sessions) + `todo_write` are provided as custom tools (`apps/worker/src/ai/tools.ts`); the per-phase MCP collectors are pi custom tools (TypeBox `defineTool` in `apps/worker/src/mcp-server/`). Adaptive thinking (pi's `medium` level) is enabled only on Opus 4.6/4.7/4.8 (`supportsAdaptiveThinking`); every other model runs with thinking `off`. Disable per-scan via `CLAUDE_ADAPTIVE_THINKING=false` (→ `off`) / `core.adaptive_thinking = false` (npx TOML). Browser automation via `playwright-cli` with session isolation (`-s=<session>`). TOTP generation via `generate-totp` CLI tool. Login flow template at `apps/worker/prompts/shared/login-instructions.txt` supports form, SSO, API, and basic auth. On authenticated whitebox scans, the `validate-authentication` preflight performs the single real login and saves the browser session to `auth-state.json` in the per-session audit directory (path from `authStateFile()` in `apps/worker/src/audit/utils.ts`, derived from `generateAuditPath()`). The validation activity (`apps/worker/src/services/validate-authentication.ts`) removes any stale file from a prior run before the agent runs and verifies the file parses and contains cookies or storage before the preflight is marked complete; `logWorkflowComplete` deletes it when the workflow ends so authenticated cookies don't sit on disk between scans. Agent prompts opt in to session reuse by `@include(shared/_shared-session.txt)` before their `<login_instructions>` block — the partial restores the session and falls through to the full login flow if verification fails. `vuln-auth`/`exploit-auth` omit the include and own their own login
- **Audit System** — Crash-safe append-only logging in `workspaces/{hostname}_{sessionId}/`. The run directory's top level holds only the human-facing report (`Security-Assessment-Report.md`, `FINAL_REPORT_FILENAME` in `apps/worker/src/paths.ts`); everything else — deliverables, per-agent logs, prompts, `session.json`, `workflow.log`, and browser artifacts — is nested under a hidden `.shannon/` internals dir (`INTERNAL_DIR`) so a customer sees only the report. Audit path helpers route through `generateInternalPath` (`apps/worker/src/audit/utils.ts`); the CLI nests the overlay backing dirs under the same `.shannon/` (`apps/cli/src/docker.ts`, `start.ts`). `session.json`/`workflow.log` reads use dual-read resolvers (`resolveSessionJsonPath`, `resolveRunFile`) that prefer `.shannon/` and fall back to the legacy run-root layout, so pre-restructure workspaces stay listable (`workspaces`/`logs`) without migration. Resuming a pre-restructure workspace upgrades it in place first: `migrateLegacyWorkspaceLayout` (`apps/cli/src/commands/start.ts`) renames the flat deliverables/logs/session entries into `.shannon/` (carrying the deliverables `.git` along) before the overlay dirs are mounted, so resume finds the old checkpoints instead of re-running every agent. The report is surfaced by copying the assembled `comprehensive_security_assessment_report.md` from the deliverables dir to the run root (`copyReportToRunRoot` in `apps/worker/src/services/reporting.ts`). WorkflowLogger (`apps/worker/src/audit/workflow-logger.ts`) provides unified human-readable per-workflow logs, backed by LogStream (`apps/worker/src/audit/log-stream.ts`) shared stream primitive
- **Deliverables** — Saved to `.shannon/deliverables/` in the target repo via the `save-deliverable` CLI script (`apps/worker/src/scripts/save-deliverable.ts`)
- **Workspaces & Resume** — Named workspaces via `-w <name>` or auto-named from URL+timestamp. Resume detects completed agents via `session.json`. `loadResumeState()` in `apps/worker/src/temporal/activities.ts` validates deliverable existence, restores git checkpoints, and cleans up incomplete deliverables. Workspace listing via `apps/worker/src/temporal/workspaces.ts`
@@ -233,7 +233,7 @@ Comments must be **timeless** — no references to this conversation, refactorin
**Entry Points:** `apps/worker/src/temporal/workflows.ts`, `apps/worker/src/temporal/activities.ts`, `apps/worker/src/temporal/worker.ts`
**Core Logic:** `apps/worker/src/session-manager.ts`, `apps/worker/src/ai/pi/pi-executor.ts`, `apps/worker/src/ai/pi/permission-system.ts` (writes `code_path` deny rules to the `@gotgenes/pi-permission-system` global config), `apps/worker/src/config-parser.ts`, `apps/worker/src/services/` (incl. `preflight.ts`, `findings-renderer.ts`, `reporting.ts`), `apps/worker/src/audit/`
**Core Logic:** `apps/worker/src/session-manager.ts`, `apps/worker/src/ai/pi-executor.ts`, `apps/worker/src/ai/settings-writer.ts` (writes `code_path` deny rules to the `@gotgenes/pi-permission-system` global config), `apps/worker/src/config-parser.ts`, `apps/worker/src/services/` (incl. `preflight.ts`, `findings-renderer.ts`, `reporting.ts`), `apps/worker/src/audit/`
**Config:** `docker-compose.yml`, `apps/cli/infra/compose.yml`, `apps/worker/configs/`, `apps/worker/prompts/`, `tsconfig.base.json` (shared compiler options), `turbo.json`, `biome.json`