The existing ASCII codec handler only sanitized conversation messages,
leaving tool schemas, system prompts, ephemeral prompts, prefill messages,
and HTTP headers as unhandled sources of non-ASCII content. On systems
with LANG=C or non-UTF-8 locale, Unicode symbols in tool descriptions
(e.g. arrows, em-dashes from prompt_builder) and system prompt content
would cause UnicodeEncodeError that fell through to the error path.
Changes:
- Add _sanitize_structure_non_ascii() generic recursive walker for
nested dict/list payloads
- Add _sanitize_tools_non_ascii() thin wrapper for tool schemas
- Add _force_ascii_payload flag: once ASCII locale is detected, all
subsequent API calls get proactively sanitized (prevents recurring
failures from new tool results bringing fresh Unicode each turn)
- Extend the ASCII codec error handler to sanitize: prefill_messages,
tool schemas (self.tools), system prompt, ephemeral system prompt,
and default HTTP headers
- Update stale comment that acknowledged the gap
Cherry-picked from PR #8834 (credential pool changes dropped as
separate concern).
The cherry-picked code passed the env var NAME (e.g. 'MY_API_KEY') as the
api_key value. The caller's has_usable_secret() check would reject the
var name, so the actual key was never used. Now we os.getenv() the
key_env value to get the real API key before returning it.
Two fixes for user-defined providers in config.yaml:
1. list_authenticated_providers() - now includes full models list from
providers.*.models array, not just default_model. This fixes /model
showing only one model when multiple are configured.
2. _get_named_custom_provider() - now checks providers: dict (new-style)
in addition to custom_providers: list (legacy). This fixes credential
resolution errors when switching models via /model command.
Both changes are backwards compatible with existing custom_providers list format.
Fixes: Only one model appears for custom providers in /model selection
On macOS, /etc is a symlink to /private/etc, so os.path.realpath()
resolves /etc/hosts to /private/etc/hosts. The sensitive path check
only matched /etc/ prefixes against the resolved path, allowing
writes to system files on macOS.
- Add /private/etc/ and /private/var/ to _SENSITIVE_PATH_PREFIXES
- Check both realpath-resolved and normpath-normalized paths
- Add regression tests for macOS symlink bypass
Closes#8734
Co-authored-by: ElhamDevelopmentStudio (PR #8829)
These functions were duplicated between auth.py and copilot_auth.py.
The auth.py copies had zero production callers — only copilot_auth.py's
versions are used. Redirect the test import to the live copy and update
monkeypatch targets accordingly.
When GITHUB_TOKEN is present in the environment (e.g. for gh CLI or
GitHub Actions), two issues broke Copilot authentication against
GitHub Enterprise (GHE) instances:
1. The copilot provider had no base_url_env_var, so COPILOT_API_BASE_URL
was silently ignored — requests always went to public GitHub.
2. `gh auth token` (the CLI fallback) treats GITHUB_TOKEN as an override
and echoes it back instead of reading from its credential store
(hosts.yml). This caused the same rejected token to be used even
after env var priority correctly skipped it.
Fix:
- Add base_url_env_var="COPILOT_API_BASE_URL" to copilot ProviderConfig
- Strip GITHUB_TOKEN/GH_TOKEN from the subprocess env when calling
`gh auth token` so it reads from hosts.yml
- Pass --hostname from COPILOT_GH_HOST when set so gh returns the
GHE-specific OAuth token
resolve_vision_provider_client() computed resolved_api_mode from config
but never passed it to downstream resolve_provider_client() or
_get_cached_client() calls, causing custom providers with
api_mode: anthropic_messages to crash when used for vision tasks.
Also remove the for_vision special case in _normalize_aux_provider()
that incorrectly discarded named custom provider identifiers.
Fixes#8857
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove the backward-compat code paths that read compression provider/model
settings from legacy config keys and env vars, which caused silent failures
when auto-detection resolved to incompatible backends.
What changed:
- Remove compression.summary_model, summary_provider, summary_base_url from
DEFAULT_CONFIG and cli.py defaults
- Remove backward-compat block in _resolve_task_provider_model() that read
from the legacy compression section
- Remove _get_auxiliary_provider() and _get_auxiliary_env_override() helper
functions (AUXILIARY_*/CONTEXT_* env var readers)
- Remove env var fallback chain for per-task overrides
- Update hermes config show to read from auxiliary.compression
- Add config migration (v16→17) that moves non-empty legacy values to
auxiliary.compression and strips the old keys
- Update example config and openclaw migration script
- Remove/update tests for deleted code paths
Compression model/provider is now configured exclusively via:
auxiliary.compression.provider / auxiliary.compression.model
Closes#8923
Updated the acquire_scoped_lock function to treat empty or corrupt lock files as stale. This change ensures that if a lock file exists but is invalid, it will be removed to prevent issues with stale locks. Added tests to verify recovery from both empty and corrupt lock files.
Add <thought>(.*?)</thought> to inline_patterns so Gemma 4
reasoning content is captured for /reasoning display, not just
stripped from visible output.
Closes#8891
Co-authored-by: RhushabhVaghela <rhushabhvaghela@users.noreply.github.com>
Three targeted changes to close the gaps between retry layers that
caused users to experience 'No response from provider for 580s' and
'No activity for 15 minutes' despite having 5 layers of retry:
1. Remove non-streaming fallback from streaming path
Previously, when all 3 stream retries exhausted, the code fell back
to _interruptible_api_call() which had no stale detection and no
activity tracking — a black hole that could hang for up to 1800s.
Now errors propagate to the main retry loop which has richer recovery
(credential rotation, provider fallback, backoff).
For 'stream not supported' errors, sets _disable_streaming flag so
the main retry loop automatically switches to non-streaming on the
next attempt.
2. Add _touch_activity to recovery dead zones
The gateway inactivity monitor relies on _touch_activity() to know
the agent is alive, but activity was never touched during:
- Stale stream detection/kill cycles (180-300s gaps)
- Stream retry connection rebuilds
- Main retry backoff sleeps (up to 120s)
- Error recovery classification
Now all these paths touch activity every ~30s, keeping the gateway
informed during recovery cycles.
3. Add stale-call detector to non-streaming path
_interruptible_api_call() now has the same stale detection pattern
as the streaming path: kills hung connections after 300s (default,
configurable via HERMES_API_CALL_STALE_TIMEOUT), scaled for large
contexts (450s for 50K+ tokens, 600s for 100K+ tokens), disabled
for local providers.
Also touches activity every ~30s during the wait so the gateway
monitor stays informed.
Env vars:
- HERMES_API_CALL_STALE_TIMEOUT: non-streaming stale timeout (default 300s)
- HERMES_STREAM_STALE_TIMEOUT: unchanged (default 180s)
Before: worst case ~2+ hours of sequential retries with no feedback
After: worst case bounded by gateway inactivity timeout (default 1800s)
with continuous activity reporting
Three-tier match strategy for _truncate_around_matches():
1. Full-phrase search (exact query string positions)
2. Proximity co-occurrence (all terms within 200 chars)
3. Individual terms (fallback, preserves existing behavior)
Sliding window picks the start offset covering the most matches.
Moved inline import re to module level.
Co-authored-by: Al Sayed Hoota <78100282+AlsayedHoota@users.noreply.github.com>
- Store source metadata on /voice channel join so voice input shares the
same session as the linked text channel conversation
- Treat voice-linked text channels as free-response (skip @mention and
auto-thread) while voice is active
- Scope the voice-linked exemption to the exact bound channel, not
sibling threads
- Guard signal handler registration in start_gateway() for non-main
threads (prevents RuntimeError when gateway runs in a daemon thread)
- Clean up _voice_sources on leave_voice_channel
Salvaged from PR #3475 by twilwa (Modal runtime portions excluded).
Three changes consolidated into the existing backup system:
1. Fix: hermes backup now uses sqlite3.Connection.backup() for .db files
instead of raw file copy. Raw copy of a WAL-mode database can produce
a corrupted backup — the backup() API handles this correctly.
2. hermes backup --quick: fast snapshot of just critical state files
(config.yaml, state.db, .env, auth.json, cron/jobs.json, etc.)
stored in ~/.hermes/state-snapshots/. Auto-prunes to 20 snapshots.
3. /snapshot slash command (alias /snap): in-session interface for
quick state snapshots. create/list/restore/prune subcommands.
Restore by ID or number. Powered by the same backup module.
No new modules — everything lives in hermes_cli/backup.py alongside
the existing full backup/import code.
No hooks in run_agent.py — purely on-demand, zero runtime overhead.
Closes the use case from PRs #8406 and #7813 with ~200 lines of new
logic instead of a 1090-line content-addressed storage engine.
The cron API returns schedule as {kind, expr, display} object but
CronPage.tsx rendered it directly as a React child, crashing with
'Objects are not valid as a React child'.
- Update CronJob interface in api.ts to match actual API response
- Use schedule_display (string) instead of schedule (object)
- Use state instead of status for job state
- Use last_error instead of error for error display
When HTTPS_PROXY / HTTP_PROXY / ALL_PROXY env vars are set (or macOS system proxy
is detected), pass the proxy URL explicitly via HTTPXRequest(proxy=proxy_url) instead
of relying on httpx's trust_env mechanism, which is unreliable for HTTP CONNECT
proxies (e.g. Clash / ClashMac in fake-ip mode).
Uses the shared resolve_proxy_url() from base.py (handles env vars + macOS system
proxy detection) instead of duplicating env var reading inline. Consolidates the
proxy_configured boolean into a single proxy_url = resolve_proxy_url() call that
serves as both the gate for skipping fallback-IP transport and the value passed
to HTTPXRequest.
Co-authored-by: Hermes Agent <hermes@nousresearch.com>
Salvaged from PR #8931 by MaybeRichard.
Prevents UTF-8 encoding crash when pasting text from Word or Google Docs,
which may contain lone surrogate code points (U+D800-U+DFFF).
Reuses existing _sanitize_surrogates() from run_agent module.
Remove read_json_file, read_jsonl, append_jsonl, env_str, env_lower —
all added in #7917 but never imported anywhere in the codebase. Also
remove unused List and Optional typing imports.
env_int, env_bool, and the other helpers that have real consumers are
kept.
- Move test file to tests/hermes_cli/ (consistent with test layout)
- Remove unused imports (os, pytest) from test file
- Update _sanitize_env_lines docstring: now used on read + write paths
When .env files become corrupted (e.g. concatenated KEY=VALUE pairs on
a single line due to concurrent writes or encoding issues), both
python-dotenv and load_env() would parse the entire concatenated string
as a single value. This caused bot tokens to appear duplicated up to 8×,
triggering InvalidToken errors from the Telegram API.
Root cause: _sanitize_env_lines() — which correctly splits concatenated
lines — was only called during save_env_value() writes, not during reads.
Fix:
- load_env() now calls _sanitize_env_lines() before parsing
- env_loader.load_hermes_dotenv() sanitizes the .env file on disk
before python-dotenv reads it, so os.getenv() also returns clean values
- Added tests reproducing the exact corruption pattern from #8908Closes#8908
The startup warning that Nous Research Hermes 3 & 4 models are not agentic
fired on any model whose name contained "hermes" anywhere, via a plain
substring check. That false-positived on unrelated local Modelfiles such
as `hermes-brain:qwen3-14b-ctx16k` — a tool-capable Qwen3 wrapper that
happens to live under a custom "hermes" tag namespace — making the warning
noise for legitimate setups.
Replace the substring check with a narrow regex anchored on `^`, `/`, or
`:` boundaries that only matches the real Hermes-3 / Hermes-4 chat family
(e.g. `NousResearch/Hermes-3-Llama-3.1-70B`, `hermes-4-405b`,
`openrouter/hermes3:70b`). Consolidate into a single helper
`is_nous_hermes_non_agentic()` in `hermes_cli.model_switch` so the CLI
and the canonical check don't drift, and route the duplicate inline site
in `cli.HermesCLI._print_warnings()` through the helper.
Add a parametrized test covering positive matches (real Hermes-3/-4
names) and a broad set of negatives (custom Modelfiles, Qwen/Claude/GPT,
older Nous-Hermes-2 families, bare "hermes", empty string, and the
"brain-hermes-3-impostor" boundary case).
_query_local_context_length was checking model_info.context_length
(the GGUF training max) before num_ctx (the Modelfile runtime override),
inverse to query_ollama_num_ctx. The two helpers therefore disagreed on
the same model:
hermes-brain:qwen3-14b-ctx32k # Modelfile: num_ctx 32768
underlying qwen3:14b GGUF # qwen3.context_length: 40960
query_ollama_num_ctx correctly returned 32768 (the value Ollama will
actually allocate KV cache for). _query_local_context_length returned
40960, which let ContextCompressor grow conversations past 32768 before
triggering compression — at which point Ollama silently truncated the
prefix, corrupting context.
Swap the order so num_ctx is checked first, matching query_ollama_num_ctx.
Adds a parametrized test that seeds both values and asserts num_ctx wins.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The terminal and execute_code tool schemas unconditionally mentioned
'cloud sandboxes' in their descriptions sent to the model. This caused
agents running on local backends to believe they were in a sandboxed
environment, refusing networking tasks and other operations. Worse,
agents sometimes saved this false belief to persistent memory, making
it persist across sessions.
Reported by multiple users (XLion, 林泽).
The post-loop grace call mechanism was broken: it injected a user
message and set _budget_grace_call=True, but could never re-enter the
while loop (already exited). Worse, the flag blocked the fallback
_handle_max_iterations from running, so final_response stayed None.
Users saw empty/no response when the agent hit max iterations.
Fix: remove the dead grace block and let _handle_max_iterations handle
it directly — it already injects a summary request and makes one extra
toolless API call.
When streaming fails after partial content delivery (e.g. OpenRouter
timeout kills connection mid-response), the stub response now carries
the accumulated streamed text instead of content=None.
Two fixes:
1. The partial-stream stub response includes recovered content from
_current_streamed_assistant_text — the text that was already
delivered to the user via stream callbacks before the connection
died.
2. The empty response recovery chain now checks for partial stream
content BEFORE falling back to _last_content_with_tools (prior
turn content) or wasting API calls on retries. This prevents:
- Showing wrong content from a prior turn
- Burning 3+ unnecessary retry API calls
- Falling through to '(empty)' when the user already saw content
The root cause: OpenRouter has a ~125s inactivity timeout. When
Anthropic's SSE stream goes silent during extended reasoning, the
proxy kills the connection. The model's text was already partially
streamed but the stub discarded it, triggering the empty recovery
chain which would show stale prior-turn content or waste retries.
- New docs page: user-guide/features/web-dashboard.md covering
quick start, prerequisites, all three pages (Status, Config, API Keys),
the /reload slash command, REST API endpoints, CORS config, and
development workflow
- Added 'Management' category in sidebar for web-dashboard
- Added 'hermes web' to CLI commands reference with options table
- Added '/reload' to slash commands reference (both CLI and gateway tables)
_remap_path_for_user was calling .resolve() on the Python path, which
followed venv/bin/python into the base interpreter. On uv-managed venvs
this swaps the systemd ExecStart to a bare Python that has none of the
venv's site-packages, so the service crashes on first import. Classical
python -m venv installs were unaffected by accident: the resolved target
/usr/bin/python3.x lives outside $HOME so the path-remap branch was
skipped and the system Python's packages silently worked.
Remove .resolve() calls on both current_home and the path; use
.expanduser() for lexical tilde expansion only. The function does
lexical prefix substitution, which is all it needs to do for its
actual purpose (remapping /root/.hermes -> /home/<user>/.hermes when
installing system services as root for a different user).
Repro: on a uv-managed venv install, `sudo hermes gateway install
--system` writes ExecStart=.../uv/python/cpython-3.11.15-.../bin/python3.11
instead of .../hermes-agent/venv/bin/python, and the service crashes on
ModuleNotFoundError: yaml.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The detached bash subprocess spawned by /restart gets killed by
systemd's KillMode=mixed cgroup cleanup, leaving the gateway dead.
Under systemd (detected via INVOCATION_ID env var), /restart now uses
via_service=True which exits with code 75 — RestartForceExitStatus=75
in the unit file makes systemd auto-restart the service. The detached
subprocess approach is preserved as fallback for non-systemd
environments (Docker, tmux, foreground mode).
* feat: web UI dashboard for managing Hermes Agent (salvage of #8204/#7621)
Adds an embedded web UI dashboard accessible via `hermes web`:
- Status page: agent version, active sessions, gateway status, connected platforms
- Config editor: schema-driven form with tabbed categories, import/export, reset
- API Keys page: set, clear, and view redacted values with category grouping
- Sessions, Skills, Cron, Logs, and Analytics pages
Backend:
- hermes_cli/web_server.py: FastAPI server with REST endpoints
- hermes_cli/config.py: reload_env() utility for hot-reloading .env
- hermes_cli/main.py: `hermes web` subcommand (--port, --host, --no-open)
- cli.py / commands.py: /reload slash command for .env hot-reload
- pyproject.toml: [web] optional dependency extra (fastapi + uvicorn)
- Both update paths (git + zip) auto-build web frontend when npm available
Frontend:
- Vite + React + TypeScript + Tailwind v4 SPA in web/
- shadcn/ui-style components, Nous design language
- Auto-refresh status page, toast notifications, masked password inputs
Security:
- Path traversal guard (resolve().is_relative_to()) on SPA file serving
- CORS localhost-only via allow_origin_regex
- Generic error messages (no internal leak), SessionDB handles closed properly
Tests: 47 tests covering reload_env, redact_key, API endpoints, schema
generation, path traversal, category merging, internal key stripping,
and full config round-trip.
Original work by @austinpickett (PR #1813), salvaged by @kshitijk4poor
(PR #7621 → #8204), re-salvaged onto current main with stale-branch
regressions removed.
* fix(web): clean up status page cards, always rebuild on `hermes web`
- Remove config version migration alert banner from status page
- Remove config version card (internal noise, not surfaced in TUI)
- Reorder status cards: Agent → Gateway → Active Sessions (3-col grid)
- `hermes web` now always rebuilds from source before serving,
preventing stale web_dist when editing frontend files
* feat(web): full-text search across session messages
- Add GET /api/sessions/search endpoint backed by FTS5
- Auto-append prefix wildcards so partial words match (e.g. 'nimb' → 'nimby')
- Debounced search (300ms) with spinner in the search icon slot
- Search results show FTS5 snippets with highlighted match delimiters
- Expanding a search hit auto-scrolls to the first matching message
- Matching messages get a warning ring + 'match' badge
- Inline term highlighting within Markdown (text, bold, italic, headings, lists)
- Clear button (x) on search input for quick reset
---------
Co-authored-by: emozilla <emozilla@nousresearch.com>
When a user sends /restart, the gateway now persists their routing info
(platform, chat_id, thread_id) to .restart_notify.json. After the new
gateway process starts and adapters connect, it reads the file, sends a
'Gateway restarted successfully' message to that specific chat, and
cleans up the file.
This follows the same pattern as _send_update_notification (used by
/update). Thread IDs are preserved so the notification lands in the
correct Telegram topic or Discord thread.
Previously, after /restart the user had no feedback that the gateway was
back — they had to send a message to find out. Now they get a proactive
notification and know their session continues.
PR #4654 replaced ml-paper-writing with research-paper-writing, preserving
the writing philosophy and reference files but dropping the dedicated
'Sources Behind This Guidance' attribution table from the SKILL.md body.
Re-adds:
- The researcher attribution table (Nanda, Farquhar, Gopen & Swan, Lipton,
Steinhardt, Perez, Karpathy) with affiliations and links to SKILL.md
- Orchestra Research credit as original compiler of the writing philosophy
- 'Origin & Attribution' section in sources.md documenting the full chain:
Nanda blog → Orchestra skill → teknium integration → SHL0MS expansion
OpenCode Zen was in _DOT_TO_HYPHEN_PROVIDERS, causing all dotted model
names (minimax-m2.5-free, gpt-5.4, glm-5.1) to be mangled. The fix:
Layer 1 (model_normalize.py): Remove opencode-zen from the blanket
dot-to-hyphen set. Add an explicit block that preserves dots for
non-Claude models while keeping Claude hyphenated (Zen's Claude
endpoint uses anthropic_messages mode which expects hyphens).
Layer 2 (run_agent.py _anthropic_preserve_dots): Add opencode-zen and
zai to the provider allowlist. Broaden URL check from opencode.ai/zen/go
to opencode.ai/zen/ to cover both Go and Zen endpoints. Add bigmodel.cn
for ZAI URL detection.
Also adds glm-5.1 to ZAI model lists in models.py and setup.py.
Closes#7710
Salvaged from contributions by:
- konsisumer (PR #7739, #7719)
- DomGrieco (PR #8708)
- Esashiero (PR #7296)
- sharziki (PR #7497)
- XiaoYingGee (PR #8750)
- APTX4869-maker (PR #8752)
- kagura-agent (PR #7157)
When tool_preview_length is 0 (default for platforms without a tier
default, like Session), verbose mode was truncating args JSON to 200
characters. Since the user explicitly opted into verbose mode, they
expect full tool call detail — the 200-char cap defeated the purpose.
Now: tool_preview_length=0 means no truncation in verbose mode.
Positive values still cap as before. Platform message-length limits
handle overflow naturally.
* fix(telegram): use UTF-16 code units for message length splitting
Port from nearai/ironclaw#2304: Telegram's 4096 character limit is
measured in UTF-16 code units, not Unicode codepoints. Characters
outside the Basic Multilingual Plane (emoji like 😀, CJK Extension B,
musical symbols) are surrogate pairs: 1 Python char but 2 UTF-16 units.
Previously, truncate_message() used Python's len() which counts
codepoints. This could produce chunks exceeding Telegram's actual limit
when messages contain many astral-plane characters.
Changes:
- Add utf16_len() helper and _prefix_within_utf16_limit() for
UTF-16-aware string measurement and truncation
- Add _custom_unit_to_cp() binary-search helper that maps a custom-unit
budget to the largest safe codepoint slice position
- Update truncate_message() to accept optional len_fn parameter
- Telegram adapter now passes len_fn=utf16_len when splitting messages
- Fix fallback truncation in Telegram error handler to use
_prefix_within_utf16_limit instead of codepoint slicing
- Update send_message_tool.py to use utf16_len for Telegram platform
- Add comprehensive tests: utf16_len, _prefix_within_utf16_limit,
truncate_message with len_fn (emoji splitting, content preservation,
code block handling)
- Update mock lambdas in reply_mode tests to accept **kw for len_fn
* fix: resolve npm audit vulnerabilities in browser tools and whatsapp bridge
Browser tools (agent-browser):
- Override lodash to 4.18.1 (fixes prototype pollution CVEs in transitive
dep via node-simctl → @appium/logger). Not reachable in Hermes's code
path but cleans the audit report.
- basic-ftp and brace-expansion updated via npm audit fix.
WhatsApp bridge:
- file-type updated (fixes infinite loop in ASF parser + ZIP bomb DoS)
- music-metadata updated (fixes infinite loop in ASF parser)
- path-to-regexp updated (fixes ReDoS, mitigated by localhost binding)
Both components now report 0 npm vulnerabilities.
Ref: https://gist.github.com/jacklevin74/b41b710d3e20ba78fb7e2d42e2b83819
Three changes that address the poor WhatsApp experience reported by users:
1. Reclassify WhatsApp from TIER_LOW to TIER_MEDIUM in display_config.py
— enables streaming and tool progress via the existing Baileys /edit
bridge endpoint. Users now see progressive responses instead of
minutes of silence followed by a wall of text.
2. Lower MAX_MESSAGE_LENGTH from 65536 to 4096 and add proper chunking
— send() now calls format_message() and truncate_message() before
sending, then loops through chunks with a small delay between them.
The base class truncate_message() already handles code block boundary
detection (closes/reopens fences at chunk boundaries). reply_to is
only set on the first chunk.
3. Override format_message() with WhatsApp-specific markdown conversion
— converts **bold** to *bold*, ~~strike~~ to ~strike~, headers to
bold text, and [links](url) to text (url). Code blocks and inline
code are protected from conversion via placeholder substitution.
Together these fix the two user complaints:
- 'sends the whole code all the time' → now chunked at 4K with proper
formatting
- 'terminal gets interrupted and gets cooked' → streaming + tool progress
give visual feedback so users don't accidentally interrupt with
follow-up messages
When resuming a session with --resume or -c, the last assistant response
was truncated to 200 chars / 3 lines just like older messages in the recap.
This forced users to waste tokens re-asking for the response.
Now the last assistant message in the recap is shown in full with non-dim
styling, so users can see exactly where they left off. Earlier messages
remain truncated for compact display.
Changes:
- Track un-truncated text for the last assistant entry during collection
- Replace last entry with full text after history trimming
- Render last assistant entry with bold (non-dim) styling
- Update existing truncation tests to use multi-message histories
- Add new tests for full last response display (char + multiline)
