feat(tts): add Piper setup support and fix Telegram voice note metadata - #7815
Closed
szafranski wants to merge 5321 commits into
Closed
feat(tts): add Piper setup support and fix Telegram voice note metadata#7815szafranski wants to merge 5321 commits into
szafranski wants to merge 5321 commits into
Conversation
szafranski
changed the title
szafranski
force-pushed
the
feat/piper-tts
branch
2 times, most recently
from
April 15, 2026 22:00
bea4a29 to
8229c08
Compare
Contributor
Author
|
Updated the branch after rebasing onto current I also re-ran the targeted Piper/Telegram tests and manually verified the end-to-end flow on a Debian 13 test host:
Full |
…d-lastmsg-8541 feat(tui): turn elapsed in FaceTicker + done-in sys line on turn end (NousResearch#8541)
This reverts commit 675e9fb.
…ousResearch#13148) * feat(security): URL query param + userinfo + form body redaction Port from nearai/ironclaw#2529. Hermes already has broad value-shape coverage in agent/redact.py (30+ vendor prefixes, JWTs, DB connstrs, etc.) but missed three key-name-based patterns that catch opaque tokens without recognizable prefixes: 1. URL query params - OAuth callback codes (?code=...), access_token, refresh_token, signature, etc. These are opaque and won't match any prefix regex. Now redacted by parameter NAME. 2. URL userinfo (https://user:pass@host) - for non-DB schemes. DB schemes were already handled by _DB_CONNSTR_RE. 3. Form-urlencoded body (k=v pairs joined by ampersands) - conservative, only triggers on clean pure-form inputs with no other text. Sensitive key allowlist matches ironclaw's (exact case-insensitive, NOT substring - so token_count and session_id pass through). Tests: +20 new test cases across 3 test classes. All 75 redact tests pass; gateway/test_pii_redaction and tools/test_browser_secret_exfil also green. Known pre-existing limitation: _ENV_ASSIGN_RE greedy match swallows whole all-caps ENV-style names + trailing text when followed by another assignment. Left untouched here (out of scope); URL query redaction handles the lowercase case. * feat: replace kimi-k2.5 with kimi-k2.6 on OpenRouter and Nous Portal Update model catalogs for OpenRouter (fallback snapshot), Nous Portal, and NVIDIA NIM to reference moonshotai/kimi-k2.6. Add kimi-k2.6 to the fixed-temperature frozenset in auxiliary_client.py so the 0.6 contract is enforced on aggregator routings. Native Moonshot provider lists (kimi-coding, kimi-coding-cn, moonshot, opencode-zen, opencode-go) are unchanged — those use Moonshot's own model IDs which are unaffected.
…NousResearch#13021) Replaces the serial for-loop in tick() with ThreadPoolExecutor so all jobs due in a single tick run concurrently. A slow job no longer blocks others from executing, fixing silent job skipping (issue NousResearch#9086). Thread safety: - Session/delivery env vars migrated from os.environ to ContextVars (gateway/session_context.py) so parallel jobs can't clobber each other's delivery targets. Each thread gets its own copied context. - jobs.json read-modify-write cycles (advance_next_run, mark_job_run) protected by threading.Lock to prevent concurrent save clobber. - send_message_tool reads delivery vars via get_session_env() for ContextVar-aware resolution with os.environ fallback. Configuration: - cron.max_parallel_jobs in config.yaml (null = unbounded, 1 = serial) - HERMES_CRON_MAX_PARALLEL env var override Based on PR NousResearch#9169 by @VenomMoth1. Fixes NousResearch#9086
Extract 12 Codex Responses API format-conversion and normalization functions from run_agent.py into agent/codex_responses_adapter.py, following the existing pattern of anthropic_adapter.py and bedrock_adapter.py. run_agent.py: 12,550 → 11,865 lines (-685 lines) Functions moved: - _chat_content_to_responses_parts (multimodal content conversion) - _summarize_user_message_for_log (multimodal message logging) - _deterministic_call_id (cache-safe fallback IDs) - _split_responses_tool_id (composite ID splitting) - _derive_responses_function_call_id (fc_ prefix conversion) - _responses_tools (schema format conversion) - _chat_messages_to_responses_input (message format conversion) - _preflight_codex_input_items (input validation) - _preflight_codex_api_kwargs (API kwargs validation) - _extract_responses_message_text (response text extraction) - _extract_responses_reasoning_text (reasoning extraction) - _normalize_codex_response (full response normalization) All functions are stateless module-level functions. AIAgent methods remain as thin one-line wrappers. Both module-level helpers are re-exported from run_agent.py for backward compatibility with existing test imports. Includes multimodal inline image support (PR NousResearch#12969) that the original PR was missing. Based on PR NousResearch#12975 by @kshitijk4poor.
…in/QQ adapters Add dm_policy and group_policy to the WhatsApp adapter, bringing parity with WeCom/Weixin/QQ. Allows independent control of DM and group access: disable DMs entirely, allowlist specific senders/groups, or keep open. - dm_policy: open (default) | allowlist | disabled - group_policy: open (default) | allowlist | disabled - Config bridging for YAML → env vars - 22 tests covering all policy combinations Backward compatible — defaults preserve existing behavior. Cherry-picked from PR NousResearch#11597 by @MassiveMassimo. Dropped the run.py group auth bypass (would have skipped user auth for ALL platforms, not just WhatsApp).
…iders (NousResearch#13152) Add kimi-k2.6 as the top model in kimi-coding, kimi-coding-cn, and moonshot static provider lists (models.py, setup.py, main.py). kimi-k2.5 retained alongside it.
…providers Section 3 (user-defined endpoints) added the plain ep_name to seen_slugs but not the custom:-prefixed slug. Section 4 generates custom:<name> via custom_provider_slug() and checks seen_slugs — since the prefixed slug was missing, the same provider appeared twice in /model. Register custom_provider_slug(display_name).lower() in seen_slugs after Section 3 emits a provider, so Section 4's dedup correctly suppresses the duplicate. Closes NousResearch#12293. Co-authored-by: bennytimz <bennytimz@users.noreply.github.com>
…search#13157) Kimi's gateway selects the correct temperature server-side based on the active mode (thinking -> 1.0, non-thinking -> 0.6). Sending any temperature value — even the previously "correct" one — conflicts with gateway-managed defaults. Replaces the old approach of forcing specific temperature values (0.6 for non-thinking, 1.0 for thinking) with an OMIT_TEMPERATURE sentinel that tells all call sites to strip the temperature key from API kwargs entirely. Changes: - agent/auxiliary_client.py: OMIT_TEMPERATURE sentinel, _is_kimi_model() prefix check (covers all kimi-* models), _fixed_temperature_for_model() returns sentinel for kimi models. _build_call_kwargs() strips temp. - run_agent.py: _build_api_kwargs, flush_memories, and summary generation paths all handle the sentinel by popping/omitting temperature. - trajectory_compressor.py: _effective_temperature_for_model returns None for kimi (sentinel mapped), direct client calls use kwargs dict to conditionally include temperature. - mini_swe_runner.py: same sentinel handling via wrapper function. - 6 test files updated: all 'forces temperature X' assertions replaced with 'temperature not in kwargs' assertions. Net: -76 lines (171 added, 247 removed). Inspired by PR NousResearch#13137 (@kshitijk4poor).
…abled (NousResearch#13162) When createForumTopic fails with 'not a forum' in a private chat, the error now tells the user exactly what to do: enable Topics in the DM chat settings from the Telegram app. Also adds a Prerequisites callout to the docs explaining this client-side requirement before the config section.
…tree isolation Adds a _resolve_path() helper that reads TERMINAL_CWD and uses it as the base for relative path resolution. Applied to _check_sensitive_path, read_file_tool, _update_read_timestamp, and _check_file_staleness. Absolute paths and non-worktree sessions (no TERMINAL_CWD) are unaffected — falls back to os.getcwd(). Fixes NousResearch#12689.
…search#13136) * ci(nix): automatic lockfile fixing to keep main building This reverts commit ef34b34. * update lockfiles
Cherry-picked from PR NousResearch#13159 by @cdanis. Adds native media attachment delivery to Signal via signal-cli JSON-RPC attachments param. Signal messages with media now follow the same early-return pattern as Telegram/Discord/Matrix — attachments are sent only with the last chunk to avoid duplicates. Follow-up fixes on top of the original PR: - Moved Signal into its own early-return block above the restriction check (matches Telegram/Discord/Matrix pattern) - Fixed media_files being sent on every chunk in the generic loop - Restored restriction/warning guards to simple form (Signal exits early) - Fixed non-hermetic test writing to /tmp instead of tmp_path
The Activity accordion in ToolTrail tints red (via metaTone) when an error item is present, but stays collapsed — the error is invisible until the user clicks. Track the latest error id and force-open openMeta whenever it advances. Users can still manually collapse; a new error re-opens.
…ity-autoexpand-on-error fix(tui): auto-expand Activity section on error
…ersion The link regex in format_message used [^)]+ for the URL portion, which stopped at the first ) character. URLs with nested parentheses (e.g. Wikipedia links like Python_(programming_language)) were improperly parsed. Use a better regex, which is the same the Slack adapter uses.
… gibberish The colored ✓/✗ marks in /tools list, /tools enable, and /tools disable were showing up as "?[32m✓ enabled?[0m" instead of green and red. The colors come out as ANSI escape codes, but the tui eats the ESC byte and replaces it with "?" when those codes are printed straight to stdout. They need to go through prompt_toolkit's renderer. Fix: capture the command's output and re-print each line through _cprint(), the same workaround used elsewhere for NousResearch#2262. The capture buffer fakes isatty()=True so the color helper still emits escapes (StringIO.isatty() is False, which would otherwise strip colors). The capture path only runs inside the TUI; standalone CLI and tests go straight through to real stdout where colors already work.
alt-glitch
added
tool/tts
szafranski
force-pushed
the
feat/piper-tts
branch
from
April 22, 2026 13:28
28b844e to
0598137
Compare
Contributor
Author
|
I noticed #17092 was closed in favor of this PR before #17885 landed, and now #17885 covers the main native Piper provider path. Given that, I do not want to keep a large overlapping PR open unnecessarily. What would maintainers prefer here? I can either:
Potential follow-up areas I see:
Happy to trim this down aggressively if any of those are wanted. |
This was referenced May 31, 2026
szafranski
force-pushed
the
feat/piper-tts
branch
from
June 10, 2026 19:42
0598137 to
da88fcc
Compare
Contributor
Author
|
Closing this PR to reduce review noise. The useful pieces are now covered by smaller, cleaner threads:
This PR also has stale branch history and a very noisy diff, so keeping it open would make review harder rather than easier. Thanks. |
szafranski
added a commit
to szafranski/hermes-agent
that referenced
this pull request
Jul 11, 2026
…t show 0:00 Telegram only auto-derives a voice/audio clip's duration from container metadata for short recordings; clips longer than ~4:50 are delivered with duration 0 and render as 0:00 in the player. Probe the length locally (stdlib wave -> mutagen -> ffprobe) and pass duration explicitly to sendVoice/sendAudio. Best-effort: when nothing can read the file we omit duration and fall back to Telegram's prior behavior. Extracts and hardens the Telegram-only part of the stale, Piper-bundled PR NousResearch#7815 (ffprobe-only, predates the send_voice retry/anchor refactor); relates to NousResearch#8508.
teknium1
pushed a commit
that referenced
this pull request
Jul 16, 2026
…t show 0:00 Telegram only auto-derives a voice/audio clip's duration from container metadata for short recordings; clips longer than ~4:50 are delivered with duration 0 and render as 0:00 in the player. Probe the length locally (stdlib wave -> mutagen -> ffprobe) and pass duration explicitly to sendVoice/sendAudio. Best-effort: when nothing can read the file we omit duration and fall back to Telegram's prior behavior. Extracts and hardens the Telegram-only part of the stale, Piper-bundled PR #7815 (ffprobe-only, predates the send_voice retry/anchor refactor); relates to #8508.
Gravezzz
pushed a commit
to Gravezzz/hermes-agent
that referenced
this pull request
Jul 21, 2026
…t show 0:00 Telegram only auto-derives a voice/audio clip's duration from container metadata for short recordings; clips longer than ~4:50 are delivered with duration 0 and render as 0:00 in the player. Probe the length locally (stdlib wave -> mutagen -> ffprobe) and pass duration explicitly to sendVoice/sendAudio. Best-effort: when nothing can read the file we omit duration and fall back to Telegram's prior behavior. Extracts and hardens the Telegram-only part of the stale, Piper-bundled PR NousResearch#7815 (ffprobe-only, predates the send_voice retry/anchor refactor); relates to NousResearch#8508.
This was referenced Jul 30, 2026
randlee
pushed a commit
to randlee/hermes-agent
that referenced
this pull request
Aug 11, 2026
…t show 0:00 Telegram only auto-derives a voice/audio clip's duration from container metadata for short recordings; clips longer than ~4:50 are delivered with duration 0 and render as 0:00 in the player. Probe the length locally (stdlib wave -> mutagen -> ffprobe) and pass duration explicitly to sendVoice/sendAudio. Best-effort: when nothing can read the file we omit duration and fall back to Telegram's prior behavior. Extracts and hardens the Telegram-only part of the stale, Piper-bundled PR NousResearch#7815 (ffprobe-only, predates the send_voice retry/anchor refactor); relates to NousResearch#8508.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Adds first-class local Piper TTS support to Hermes setup and runtime, and fixes Telegram voice-note handling so generated audio is delivered with the correct metadata and file path.
This PR stays intentionally narrow and does five things:
hermes setup tts.7a6c333ec560f0e688371adc2fbb7bbe105028c6.model_path, and Unicode-safe voice download URLs.filenameanddurationmetadata and using the correct voice-note path.This keeps the PR aligned with the existing setup/runtime flow instead of introducing a parallel path, and limits the Telegram fix to the existing media handoff points already used by the current implementation.
Related Issue
Fixes #8508
Type of Change
Changes Made
piper_catalog.pyand packaged it inpyproject.tomlhermes_cli/setup.pyto expose Piper as a built-in TTS optionmodel_pathPiper (local on-device, free, 40+ languages, 150+ voice models)tools/tts_tool.pyto support:model_pathgateway/platforms/telegram.pytools/send_message_tool.pytests/tools/test_tts_tool_piper.pytests/hermes_cli/test_setup.pytests/hermes_cli/test_setup_model_provider.pytests/gateway/test_telegram_documents.pytests/tools/test_send_message_tool.pytests/tools/test_tts_mistral.pyHow to Test
Run the setup tests:
python -m pytest tests/hermes_cli/test_setup.py tests/hermes_cli/test_setup_model_provider.py -qRun the focused TTS / Telegram validation:
python -m pytest tests/tools/test_tts_tool_piper.py tests/tools/test_send_message_tool.py::TestSendTelegramMediaDelivery tests/gateway/test_telegram_documents.py tests/tools/test_tts_mistral.py -qManually verify in a real environment:
Checklist
Code
fix(scope):,feat(scope):, etc.)pytest tests/ -qand all tests passDocumentation & Housekeeping
docs/, docstrings) — or N/Acli-config.yaml.exampleif I added/changed config keys — or N/ACONTRIBUTING.mdorAGENTS.mdif I changed architecture or workflows — or N/AValidation
47 passed72 passedManual verification on the Debian 13 test host confirmed:
Notes
This branch was refreshed onto current
upstream/mainand conflicts were resolved without expanding PR scope.pytest tests/ -qwas attempted again, but the full suite is still not green in this environment, so that checklist item remains unchecked. The failures are not limited to this PR's Piper / Telegram scope.