feat(status): rich /status snapshots across CLI and gateway

[malaiwah]

Summary

Replaces the basic /status output with a comprehensive session snapshot showing model, provider, token breakdown, cost, context window, and more.

• Token breakdown: input/output/cache read/cache write/reasoning with totals
• Cost display: estimated or actual cost with human-readable labels
• Context window: live usage from context_compressor when agent is running; idle fallback via get_model_context_length when agent is idle (inspired by feat(status): show model, provider, context, and cumulative tokens #4678)
• Cache hit rate: percentage of cache reads vs total input
• Compression tracking: compaction count from live agent OR persisted compression_count for idle sessions — idle sessions now show compression history instead of omitting it
• Platform categorization: separates chat platforms from services (API, webhook)
• Queue depth: pending messages and follow-up items
• Model override awareness: shows session-level model overrides
• Transport mode: webhook vs polling for Telegram

Fixes #5960 (Tokens: 0 regression — reads from SessionDB instead of stale SessionStore).
Closes #7317 (context/compression state in gateway-visible status).
Closes #7714 (usage display like OpenClaw).
Supersedes #4678 (model + context in /status — this PR is a strict superset).
Supersedes #5989 (get_session_token_totals — included here plus much more).

Changes

File	Action
hermes_cli/status_format.py	New — 6 shared formatting helpers (no duplication between CLI and gateway)
hermes_state.py	Edit — add get_session_token_totals() and get_session_last_active()
gateway/run.py	Edit — add _build_status_snapshot(), _get_status_platform_sections(), _get_status_queue_depth(); replace _handle_status_command(); persist compression_count after each turn
gateway/session.py	Edit — add compression_count field to SessionEntry, wire through to_dict/from_dict/update_session
run_agent.py	Edit — return compression_count from run_conversation() result dict
cli.py	Edit — add _build_cli_status_snapshot(), _get_cli_status_queue_depth(); replace _show_session_status()
tests/hermes_cli/test_status_format.py	New — 27 unit tests for shared helpers
tests/gateway/test_status_command.py	Rewrite — 13 tests covering live agent, idle fallback with persisted compression, model override, platform split, queue depth
tests/cli/test_cli_status_command.py	Rewrite — 3 tests covering live agent, persisted session fallback, pending title

Example output

Gateway (Telegram/Discord) — live agent:

⚕ Hermes Agent v0.8.0
Model: `anthropic/claude-sonnet-4` · Provider: anthropic
Usage: 25,000 in · 610 out · 50,730 total · Cost: $0.1234 est.
Cache: 25,000 read · 0 write · 50% hit · 120 reasoning
Context: 28,000 / 200,000 (14%) · Compactions: 1
Session: `agent:main:telegram:dm:12345` · updated 3m ago
ID: `20260412_104559_e1760b66`
Runtime: Chat Completions · Reasoning high · Transport webhook
Queue: depth 0 · State: running
Chats: telegram, discord

Gateway — idle session (compression history persisted):

⚕ Hermes Agent v0.8.0
Model: `openai/gpt-4o` · Provider: openai
Usage: 100 in · 200 out · 3,210 total · Cost: $1.2345 est.
Cache: 10 read · 5 write · 9% hit
Context: 45,000 / 200,000 (22%) · Compactions: 3
Session: `agent:main:telegram:dm:12345` · updated 7m ago
ID: `20260412_104559_e1760b66`
Runtime: Reasoning medium
Queue: depth 0 · State: idle
Chats: telegram

Design decisions

• Shared helpers, not duplicated methods: hermes_cli/status_format.py holds all formatting logic. Both CLI and gateway import from it.
• Graceful degradation: Every data source is wrapped in try/except with safe defaults. Missing SessionDB, missing agent, missing cache — all handled.
• Idle context + compression fallback: When no live agent exists, uses get_model_context_length() + session_entry.last_prompt_tokens for context, and session_entry.compression_count for compaction history. Both are persisted via update_session() after each turn.
• Backward-compatible persistence: compression_count defaults to 0 in SessionEntry.from_dict(), so existing sessions.json files load cleanly.
• Backward-compatible attributes: Uses getattr() with defaults for optional runner attributes (_pending_hidden_turns, _agent_cache, etc.).

Test plan

• pytest tests/cli/test_cli_status_command.py tests/gateway/test_status_command.py tests/hermes_cli/test_status_format.py — 42 tests pass
• Live-tested on downstream fork with 59 regression tests passing
• Idle compression count verified via test with compression_count=3 on SessionEntry

🤖 Generated with Claude Code

[teknium1]

Thanks for the comprehensive status-snapshot work. The token regression and the gateway model/provider/context portion have since landed on main, but compression history and the broader snapshot remain useful.

Problems

• Current /status now lives in gateway/slash_commands.py:493, not gateway/run.py; it uses awaited AsyncSessionDB reads at gateway/slash_commands.py:533-537. The branch therefore needs a targeted port rather than a direct application.
• Expose context/compression state in gateway-visible status command #7317 requests a last-compression time, but this diff persists only compression_count; no timestamp is stored or rendered.
• Main localizes status fields through t(...) at gateway/slash_commands.py:608-644; the new literal English output would bypass that surface.

Suggested changes

• Salvage the remaining fields into the current handler, preserve async DB access and localization, and add current-harness coverage for live and idle compression metadata.

Automated hermes-sweeper review.

[malaiwah]

Retargeted to current main HEAD

The original branch targeted the pre-refactor gateway/run.py /status handler. The handler and surrounding code have since been refactored with async AsyncSessionDB reads and t(...) localization. I've rebased onto current main HEAD (91937a6dc):

New file — hermes_cli/status_format.py:

• Shared snapshot formatting helpers (format_api_mode_label, format_reasoning_effort_label, format_status_relative_time, safe_status_float, safe_status_int)

SessionEntry changes (gateway/session.py):

• Added compression_count: int and last_compressed_at: float fields with persistence in to_dict/from_dict/update_session

Database layer (hermes_state.py):

• Added get_session_token_totals() and get_session_last_compressed() query methods

Agent result wiring (gateway/run.py):

• Wired compression_count and last_compressed_at into both agent result dicts (lines ~5488 and ~5628)

Compression timestamp (agent/context_compressor.py):

• Added last_compressed_at = time.time() alongside the existing compression_count += 1 — this satisfies issue Expose context/compression state in gateway-visible status command #7317's request for a compression timestamp, not just a count

Localization (locales/en.yaml):

• Added strings for all new snapshot fields, preserving the t(...) localization convention

Ready for re-review.

[malaiwah]

CI fix pushed

Slice 3/8 was failing on tests/agent/test_i18n.py — the retarget added 19 new keys to locales/en.yaml under gateway.status but didn't propagate them to the other 16 locale files (ar, zh, zh-hant, ja, de, es, fr, tr, uk, af, ko, it, ga, pt, ru, hu).

Both failing tests enforce locale parity:

• test_catalog_keys_match_english — every locale must have the same keys as en.yaml
• test_catalog_placeholders_match_english — every value must use the same {placeholder} tokens

Fix: Copied the 19 English strings as fallback values into all 16 locale files (fix(i18n): add rich status snapshot keys to all 16 locale files). Standard i18n practice — untranslated keys fall back to English; translators can update at their leisure. The i18n test only verifies key presence and placeholder parity, not translation quality.

Verified locally: All 36 i18n tests pass (36 passed in 2.63s).

CI should go green on the next run.