Files
shannon/apps/worker/prompts/shared/login-instructions.txt
T
ezl-keygraph 5ff40f8c6f feat(worker): migrate agent runtime from Claude Agent SDK to pi harness (#389)
* feat(worker): migrate agent runtime from Claude Agent SDK to pi harness

* feat: remove Google Vertex AI provider support

* fix(worker): route Bedrock and custom-base-URL providers from env

* feat(prompts): instruct agents to call submit_exploitation_queue and submit_auth_result

* fix(worker): count sub-agent cost and surface compaction failures

* refactor(worker): rename claude-executor to pi-executor

* feat(worker): pi-event-driven output formatting

* fix(worker): gate adaptive thinking to Opus models, drop CLAUDE_THINKING_LEVEL

* fix(worker): restore minLength/minItems on vuln-collector schemas

* feat(worker): give task sub-agent write+bash, align tool descriptions

* feat(worker): add glob custom tool and route code_path globs to it

* refactor(prompts): use pi tool names (task, todo_write, read, bash, glob)

* refactor(prompts): drop stale MCP terminology for collector tools

* refactor(prompts): drop collector server names from deliverable instructions

* fix(worker): restore minLength/minItems on pre-recon and exploit collector schemas

* feat(worker): load playwright-cli skill via pi resource loader

* refactor(cli): remove CLAUDE_CODE_MAX_OUTPUT_TOKENS config

* build: drop @anthropic-ai/claude-code from worker image

* docs: remove vertex references from llms context

* docs(worker): update stale sdk comments

* refactor(worker): unify provider precedence between preflight and executor

* feat(worker): enforce bounded bash timeouts via pi extension

* ci: bump the beta release line to 2.0.0 (#356)

* fix(cli): pin npx command hints to beta tag

* fix: render agent deliverables before the success commit so resume preserves them (#377)

* 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

* 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

* style(cli): collapse usage hint now that the beta tag is gone

* 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 19:13:13 +05:30

82 lines
3.8 KiB
Plaintext

<!-- BEGIN:COMMON -->
**IF you are not already logged in when you open playwright, these are the login instructions**
**NOTE: playwright automatically saves sessions so ensure you are not already logged in before executing these steps**
<user_provided_configuration>
{{user_instructions}}
</user_provided_configuration>
<authentication_execution>
Execute the login flow based on the login_type specified in the configuration:
<!-- END:COMMON -->
<!-- BEGIN:FORM -->
**Form-based authentication:**
1. Navigate to the specified login_url using Playwright
2. Execute each step in the login_flow array sequentially:
- Replace $username with the provided username credential
- Replace $password with the provided password credential
- Replace $totp with the code generated by running `generate-totp --secret {{totp_secret}}` via the `bash` tool
- Perform the specified actions (type text, click buttons, etc.)
3. Wait for page navigation/loading to complete after each critical step
4. Handle any consent dialogs or "Continue as [user]" prompts by clicking appropriate buttons
<!-- END:FORM -->
<!-- BEGIN:SSO -->
**SSO authentication:**
1. Navigate to the specified login_url using Playwright
2. Execute each step in the login_flow array sequentially:
- Click the SSO provider button (e.g., "Sign in with Google")
- Handle account selection if prompted
- Replace $username with the provided username credential in provider login
- Replace $password with the provided password credential in provider login
- Replace $totp with the code generated by running `generate-totp --secret {{totp_secret}}` via the `bash` tool
- Handle OAuth consent screens by clicking "Allow", "Accept", or "Continue", and hitting check boxes as needed.
- Handle "Continue as [username]" dialogs by clicking "Continue"
3. Wait for OAuth callback and final redirect to complete
4. Ensure all consent and authorization steps are explicitly handled
<!-- END:SSO -->
<!-- BEGIN:VERIFICATION -->
</authentication_execution>
<success_verification>
After completing the login flow, verify successful authentication:
1. **Check Success Condition:**
- IF success_condition.type == "url_contains": Verify current URL contains the specified value
- IF success_condition.type == "url_equals_exactly": Verify current URL exactly matches the specified value
- IF success_condition.type == "element_present": Verify the specified element exists on the page
2. **Confirm Authentication State:**
- Page should NOT be on a login screen
- Page should NOT show authentication errors
- Page should display authenticated user content/interface
3. **Verification Success:**
- Login is successful - proceed with your primary task
- You now have an authenticated browser session to work with
4. **Verification Failure:**
- Retry the entire login flow ONCE with 5-second wait between attempts
- If second attempt fails, report authentication failure and stop task execution
- Do NOT proceed with authenticated actions if login verification fails
</success_verification>
<error_handling>
If login execution fails:
1. Log the specific step that failed and any error messages
2. Check for unexpected dialogs, pop-ups, or consent screens that may need handling
3. Retry the complete login flow once after a 5-second delay
4. If retry fails, report login failure and halt task execution
5. Do NOT attempt to proceed with the primary task if authentication is unsuccessful
Common issues to watch for:
- OAuth consent screens requiring explicit "Allow" or "Accept" clicks
- "Continue as [user]" or account selection prompts
- TOTP/2FA code timing issues requiring regeneration
- Page loading delays requiring explicit waits
- Redirect handling for multi-step authentication flows
</error_handling>
<!-- END:VERIFICATION -->