Commit graph

5 commits

Author SHA1 Message Date
Shannon Sands
7e1a05b475 feat: wallet approval flow, export command, improved create/import UX
Approval system:
- wallet/approval.py: PendingWalletTx stash, submit_pending(), pop_pending(),
  execute_approved() — mirrors the dangerous-command approval pattern
- tools/wallet_tool.py: wallet_send now stashes pending txs when policy
  returns require_approval (using task_id as session key)
- cli.py: Post-agent-loop check for pending wallet approvals, invokes
  wallet_approval_callback for interactive TUI prompt, executes on approve
- hermes_cli/callbacks.py: wallet_approval_callback — TUI prompt showing
  tx details with approve/deny choices (matches approval_callback pattern)
- gateway/run.py: Picks up pending wallet txs after agent response, shows
  approval hint with /approve /deny. /approve handler dispatches wallet tx
  execution via execute_approved().

Export/Import:
- wallet/manager.py: export_private_key() — CLI-only, never agent-exposed
- wallet/cli.py: 'hermes wallet export' with passphrase re-entry confirmation,
  safety warnings, import instructions. Import updated with --type flag and
  migration-focused messaging.

UX improvements:
- Create messaging emphasizes fresh wallets + funding over personal wallet import
- Import framed as migration tool, not personal wallet onboarding

Tested: approval stash/execute path confirmed on Solana mainnet
2026-03-29 08:38:29 +10:00
teknium1
163fa4a9d1 refactor(cli): implement approval locking mechanism to serialize concurrent requests
- Introduced _approval_lock to ensure that approval prompts are handled sequentially, preventing state clobbering from parallel delegation subtasks.
- Updated approval_callback and HermesCLI methods to utilize the lock for managing approval state and deadlines.
- Added tests for the config bridging logic to ensure correct environment variable mapping from config.yaml.
2026-03-13 23:59:18 -07:00
kshitijk4poor
ccfbf42844 feat: secure skill env setup on load (core #688)
When a skill declares required_environment_variables in its YAML
frontmatter, missing env vars trigger a secure TUI prompt (identical
to the sudo password widget) when the skill is loaded. Secrets flow
directly to ~/.hermes/.env, never entering LLM context.

Key changes:
- New required_environment_variables frontmatter field for skills
- Secure TUI widget (masked input, 120s timeout)
- Gateway safety: messaging platforms show local setup guidance
- Legacy prerequisites.env_vars normalized into new format
- Remote backend handling: conservative setup_needed=True
- Env var name validation, file permissions hardened to 0o600
- Redact patterns extended for secret-related JSON fields
- 12 existing skills updated with prerequisites declarations
- ~48 new tests covering skip, timeout, gateway, remote backends
- Dynamic panel widget sizing (fixes hardcoded width from original PR)

Cherry-picked from PR #723 by kshitijk4poor, rebased onto current main
with conflict resolution.

Fixes #688

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
2026-03-13 03:14:04 -07:00
Teknium
2a62514d17
feat: add 'View full command' option to dangerous command approval (#887)
When a dangerous command is detected and the user is prompted for
approval, long commands are truncated (80 chars in fallback, 70 chars
in the TUI). Users had no way to see the full command before deciding.

This adds a 'View full command' option across all approval interfaces:

- CLI fallback (tools/approval.py): [v]iew option in the prompt menu.
  Shows the full command and re-prompts for approval decision.
- CLI TUI (cli.py): 'Show full command' choice in the arrow-key
  selection panel. Expands the command display in-place and removes
  the view option after use.
- CLI callbacks (callbacks.py): 'view' choice added to the list when
  the command exceeds 70 characters.
- Gateway (gateway/run.py): 'full', 'show', 'view' responses reveal
  the complete command while keeping the approval pending.

Includes 7 new tests covering view-then-approve, view-then-deny,
short command fallthrough, and double-view behavior.

Closes community feedback about the 80-char cap on dangerous commands.
2026-03-12 06:27:21 -07:00
teknium1
b1f55e3ee5 refactor: reorganize agent and CLI structure for improved clarity
- Extracted agent internals into a dedicated `agent/` directory, including model metadata, context compression, and prompt handling.
- Enhanced CLI structure by separating banner, commands, and callbacks into distinct modules within `hermes_cli/`.
- Updated README to reflect the new directory organization and clarify the purpose of each component.
- Improved tool registration and terminal execution backends for better maintainability and usability.
2026-02-21 23:17:18 -08:00