feat(tts): add register_tts_provider() plugin hook (salvage of #30420)#31745
Merged
Conversation
Adds a `TTSProvider(ABC)` + `register_tts_provider()` extension point to the plugin context API, **alongside** the existing config-driven `tts.providers.<name>: type: command` registry from PR #17843. This is additive — the command-provider surface stays as the primary way to add a TTS backend. The hook covers cases the shell-template grammar can't reasonably express: - Native Python SDKs without a CLI (Cartesia, Fish Audio, etc.) - Streaming synthesis (chunked Opus → voice-bubble delivery) - Voice metadata API for the `hermes tools` picker - OAuth-refreshing auth flows None of the 10 inline built-in providers (`edge`, `openai`, `elevenlabs`, `minimax`, `gemini`, `mistral`, `xai`, `piper`, `kittentts`, `neutts`) are migrated to plugins. They stay inline. The hook is for *new* engines that aren't built-in. ## Resolution order The dispatcher's resolution order is the load-bearing invariant: 1. `tts.provider` is a built-in name → built-in dispatch. **Always wins.** 2. `tts.provider` matches `tts.providers.<name>` with `command:` set → command-provider dispatch (PR #17843). 3. `tts.provider` matches a plugin-registered `TTSProvider` → plugin dispatch (new). 4. No match → falls through to Edge TTS default (legacy behavior). Built-ins-always-win is enforced at THREE layers: - Registry: `register_provider()` rejects shadowing names with a warning. - Dispatcher: `_dispatch_to_plugin_provider()` short-circuits built-in names defensively before consulting the registry. - Picker: `_plugin_tts_providers()` filters built-in shadows out of the `hermes tools` row list defensively. Command-providers-win-over-plugins is enforced at TWO layers: - The caller in `text_to_speech_tool` checks `_resolve_command_provider_config` first. - `_dispatch_to_plugin_provider` re-checks for a same-name command config defensively so a refactor of the caller can't silently break the invariant. ## New files - `agent/tts_provider.py` — `TTSProvider(ABC)` with `synthesize()` (required), `list_voices()`, `list_models()`, `get_setup_schema()`, `stream()`, `voice_compatible` (all optional with sane defaults). Mirrors `agent/image_gen_provider.py` shape. - `agent/tts_registry.py` — `register_provider`/`get_provider`/`list_providers` with `_BUILTIN_NAMES` reject-shadowing invariant. Mirrors `agent/image_gen_registry.py` shape. - `plugins/tts/...` directory ready for community plugins (none shipped). ## Modified files - `hermes_cli/plugins.py` — `register_tts_provider()` method on `PluginContext`. Matches the gating shape of `register_image_gen_provider()` / `register_browser_provider()`. - `tools/tts_tool.py` — `_dispatch_to_plugin_provider()` + `_plugin_provider_is_voice_compatible()` + walrus-elif wiring into the main dispatcher. Built-in elif chain untouched. - `hermes_cli/tools_config.py` — `_plugin_tts_providers()` injects plugin rows into the Text-to-Speech picker category alongside the 10 hardcoded built-in rows. ## Tests - `tests/agent/test_tts_registry.py` — 47 tests covering registration, lookup, ABC contract, helpers, AND a `TestBuiltinSync` regression test that fails if `agent.tts_registry._BUILTIN_NAMES` drifts from `tools.tts_tool.BUILTIN_TTS_PROVIDERS` (kept duplicated due to circular import constraints). - `tests/tools/test_tts_plugin_dispatch.py` — 35 tests covering built-in-always-wins, command-wins-over-plugin, plugin dispatch, exception passthrough, voice_compatible helper. - `tests/hermes_cli/test_tts_picker.py` — 10 tests covering the picker surface, builtin shadowing defense, integration with `_visible_providers`. - `tests/hermes_cli/test_plugins_tts_registration.py` — 3 end-to-end tests via `PluginManager.discover_and_load()`. - `tests/plugins/tts/check_parity_vs_main.py` — 9-scenario subprocess parity harness vs `origin/main`. The only intentional diff is `fallback_edge → plugin` for the `plugin-installed` scenario. ## Verification - 95/95 new tests pass. - 170/170 pre-existing TTS tests (test_tts_command_providers, test_tts_max_text_length, test_tts_speed, etc.) pass unchanged. - Parity harness against `origin/main`: 8 OK + 1 expected DIFF. - E2E smoke: a registered plugin's `synthesize()` is called via `text_to_speech_tool` with the standard JSON envelope returned. - Ruff clean on all touched files. ## Docs - `website/docs/user-guide/features/tts.md` — new "Python plugin providers" section with a decision table (command-provider vs plugin), minimal plugin example, and the optional-hook reference. - `website/docs/user-guide/features/plugins.md` — TTS row updated to mention both surfaces (command-provider primary, plugin for SDK/streaming). Closes #30398
Contributor
🔎 Lint report:
|
| Rule | Count |
|---|---|
invalid-argument-type |
5 |
unresolved-import |
3 |
invalid-assignment |
1 |
not-subscriptable |
1 |
First entries
tests/agent/test_tts_registry.py:21: [unresolved-import] unresolved-import: Cannot resolve imported module `pytest`
tests/hermes_cli/test_tts_picker.py:11: [unresolved-import] unresolved-import: Cannot resolve imported module `pytest`
tests/agent/test_tts_registry.py:147: [invalid-argument-type] invalid-argument-type: Argument to function `get_provider` is incorrect: Expected `str`, found `Literal[123]`
tests/agent/test_tts_registry.py:282: [invalid-argument-type] invalid-argument-type: Argument to function `resolve_output_format` is incorrect: Expected `str | None`, found `Literal[123]`
tests/hermes_cli/test_tts_picker.py:105: [invalid-assignment] invalid-assignment: Invalid subscript assignment with key of type `Literal["bogus"]` and value of type `_NoName` on object of type `dict[str, TTSProvider]`
tests/tools/test_tts_plugin_dispatch.py:213: [not-subscriptable] not-subscriptable: Cannot subscript object of type `None` with no `__getitem__` method
tests/agent/test_tts_registry.py:283: [invalid-argument-type] invalid-argument-type: Argument to function `resolve_output_format` is incorrect: Expected `str | None`, found `list[Unknown]`
tests/agent/test_tts_registry.py:84: [invalid-argument-type] invalid-argument-type: Argument to function `register_provider` is incorrect: Expected `TTSProvider`, found `Literal["not a provider"]`
tests/agent/test_tts_registry.py:146: [invalid-argument-type] invalid-argument-type: Argument to function `get_provider` is incorrect: Expected `str`, found `None`
tests/tools/test_tts_plugin_dispatch.py:33: [unresolved-import] unresolved-import: Cannot resolve imported module `pytest`
✅ Fixed issues: none
Unchanged: 4850 pre-existing issues carried over.
Diagnostics are surfaced as warnings — this check never fails the build.
7 tasks
teknium1
added a commit
that referenced
this pull request
May 27, 2026
) Background processes whose command contains `gh pr view --json statusCheckRollup` or `gh pr checks | jq` now get a runtime hint in the result pointing at the canonical green-ci-policy snippets. The homebrew shape has caused at least seven silent CI-watcher failures in the past two weeks (#31329, #31448, #31695, #31709, #31745, #32264, #33131) — each one a different jq/awk/grep variation of the same fundamental problem (stdout buffering, jq null-key edge cases, conclusion-vs-status confusion, TTY-only banner grepping). The skill that documents this anti-pattern is excellent, but a skill only fires if the agent loads it. The tool surface fires on every misuse. This is the embed-footguns-in-tool-surface pattern from PR #31289 applied to a recurring failure mode that's outgrown skill-only enforcement. Detector is deliberately narrow — flags two specific shapes: 1. Any command containing `statusCheckRollup` (the JSON-API path — conclusion vs status field semantics keep burning us). 2. `gh pr view` / `gh pr checks` combined with `jq` (gh pr checks doesn't emit JSON, so any `| jq` here is confused intent; the canonical column-2 poller uses awk-on-tabs, not jq). Does NOT flag the blessed column-2 awk-on-tabs poller (which uses `awk -F"\t" "\==\"pending\""`) or the exit-code-driven `gh pr checks $PR >/dev/null` snippet. Hint composes with the existing background-without-notify_on_complete hint — both can fire on the same call. Each is independently actionable. Tests: - 4 new cases in tests/tools/test_notify_on_complete.py - test_homebrew_ci_poller_via_statusCheckRollup_emits_hint (positive) - test_homebrew_ci_poller_via_gh_pr_checks_piped_to_jq_emits_hint (positive) - test_canonical_column2_awk_poller_does_not_emit_homebrew_hint (negative) - test_canonical_gh_pr_checks_exit_code_loop_does_not_emit_hint (negative) - test_non_ci_background_command_does_not_emit_homebrew_hint (negative) - 30/30 passing (was 26)
mathias3
pushed a commit
to mathias3/hermes-agent
that referenced
this pull request
May 28, 2026
…sResearch#33142) Background processes whose command contains `gh pr view --json statusCheckRollup` or `gh pr checks | jq` now get a runtime hint in the result pointing at the canonical green-ci-policy snippets. The homebrew shape has caused at least seven silent CI-watcher failures in the past two weeks (NousResearch#31329, NousResearch#31448, NousResearch#31695, NousResearch#31709, NousResearch#31745, NousResearch#32264, NousResearch#33131) — each one a different jq/awk/grep variation of the same fundamental problem (stdout buffering, jq null-key edge cases, conclusion-vs-status confusion, TTY-only banner grepping). The skill that documents this anti-pattern is excellent, but a skill only fires if the agent loads it. The tool surface fires on every misuse. This is the embed-footguns-in-tool-surface pattern from PR NousResearch#31289 applied to a recurring failure mode that's outgrown skill-only enforcement. Detector is deliberately narrow — flags two specific shapes: 1. Any command containing `statusCheckRollup` (the JSON-API path — conclusion vs status field semantics keep burning us). 2. `gh pr view` / `gh pr checks` combined with `jq` (gh pr checks doesn't emit JSON, so any `| jq` here is confused intent; the canonical column-2 poller uses awk-on-tabs, not jq). Does NOT flag the blessed column-2 awk-on-tabs poller (which uses `awk -F"\t" "\==\"pending\""`) or the exit-code-driven `gh pr checks $PR >/dev/null` snippet. Hint composes with the existing background-without-notify_on_complete hint — both can fire on the same call. Each is independently actionable. Tests: - 4 new cases in tests/tools/test_notify_on_complete.py - test_homebrew_ci_poller_via_statusCheckRollup_emits_hint (positive) - test_homebrew_ci_poller_via_gh_pr_checks_piped_to_jq_emits_hint (positive) - test_canonical_column2_awk_poller_does_not_emit_homebrew_hint (negative) - test_canonical_gh_pr_checks_exit_code_loop_does_not_emit_hint (negative) - test_non_ci_background_command_does_not_emit_homebrew_hint (negative) - 30/30 passing (was 26)
Bryce-huang
pushed a commit
to wbkunlun/hermes-agent
that referenced
this pull request
May 29, 2026
…sResearch#33142) Background processes whose command contains `gh pr view --json statusCheckRollup` or `gh pr checks | jq` now get a runtime hint in the result pointing at the canonical green-ci-policy snippets. The homebrew shape has caused at least seven silent CI-watcher failures in the past two weeks (NousResearch#31329, NousResearch#31448, NousResearch#31695, NousResearch#31709, NousResearch#31745, NousResearch#32264, NousResearch#33131) — each one a different jq/awk/grep variation of the same fundamental problem (stdout buffering, jq null-key edge cases, conclusion-vs-status confusion, TTY-only banner grepping). The skill that documents this anti-pattern is excellent, but a skill only fires if the agent loads it. The tool surface fires on every misuse. This is the embed-footguns-in-tool-surface pattern from PR NousResearch#31289 applied to a recurring failure mode that's outgrown skill-only enforcement. Detector is deliberately narrow — flags two specific shapes: 1. Any command containing `statusCheckRollup` (the JSON-API path — conclusion vs status field semantics keep burning us). 2. `gh pr view` / `gh pr checks` combined with `jq` (gh pr checks doesn't emit JSON, so any `| jq` here is confused intent; the canonical column-2 poller uses awk-on-tabs, not jq). Does NOT flag the blessed column-2 awk-on-tabs poller (which uses `awk -F"\t" "\==\"pending\""`) or the exit-code-driven `gh pr checks $PR >/dev/null` snippet. Hint composes with the existing background-without-notify_on_complete hint — both can fire on the same call. Each is independently actionable. Tests: - 4 new cases in tests/tools/test_notify_on_complete.py - test_homebrew_ci_poller_via_statusCheckRollup_emits_hint (positive) - test_homebrew_ci_poller_via_gh_pr_checks_piped_to_jq_emits_hint (positive) - test_canonical_column2_awk_poller_does_not_emit_homebrew_hint (negative) - test_canonical_gh_pr_checks_exit_code_loop_does_not_emit_hint (negative) - test_non_ci_background_command_does_not_emit_homebrew_hint (negative) - 30/30 passing (was 26) #AI commit#
mosaiq-systems
pushed a commit
to mosaiq-systems/hermes-agent
that referenced
this pull request
May 29, 2026
…sResearch#33142) Background processes whose command contains `gh pr view --json statusCheckRollup` or `gh pr checks | jq` now get a runtime hint in the result pointing at the canonical green-ci-policy snippets. The homebrew shape has caused at least seven silent CI-watcher failures in the past two weeks (NousResearch#31329, NousResearch#31448, NousResearch#31695, NousResearch#31709, NousResearch#31745, NousResearch#32264, NousResearch#33131) — each one a different jq/awk/grep variation of the same fundamental problem (stdout buffering, jq null-key edge cases, conclusion-vs-status confusion, TTY-only banner grepping). The skill that documents this anti-pattern is excellent, but a skill only fires if the agent loads it. The tool surface fires on every misuse. This is the embed-footguns-in-tool-surface pattern from PR NousResearch#31289 applied to a recurring failure mode that's outgrown skill-only enforcement. Detector is deliberately narrow — flags two specific shapes: 1. Any command containing `statusCheckRollup` (the JSON-API path — conclusion vs status field semantics keep burning us). 2. `gh pr view` / `gh pr checks` combined with `jq` (gh pr checks doesn't emit JSON, so any `| jq` here is confused intent; the canonical column-2 poller uses awk-on-tabs, not jq). Does NOT flag the blessed column-2 awk-on-tabs poller (which uses `awk -F"\t" "\==\"pending\""`) or the exit-code-driven `gh pr checks $PR >/dev/null` snippet. Hint composes with the existing background-without-notify_on_complete hint — both can fire on the same call. Each is independently actionable. Tests: - 4 new cases in tests/tools/test_notify_on_complete.py - test_homebrew_ci_poller_via_statusCheckRollup_emits_hint (positive) - test_homebrew_ci_poller_via_gh_pr_checks_piped_to_jq_emits_hint (positive) - test_canonical_column2_awk_poller_does_not_emit_homebrew_hint (negative) - test_canonical_gh_pr_checks_exit_code_loop_does_not_emit_hint (negative) - test_non_ci_background_command_does_not_emit_homebrew_hint (negative) - 30/30 passing (was 26)
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…sResearch#33142) Background processes whose command contains `gh pr view --json statusCheckRollup` or `gh pr checks | jq` now get a runtime hint in the result pointing at the canonical green-ci-policy snippets. The homebrew shape has caused at least seven silent CI-watcher failures in the past two weeks (NousResearch#31329, NousResearch#31448, NousResearch#31695, NousResearch#31709, NousResearch#31745, NousResearch#32264, NousResearch#33131) — each one a different jq/awk/grep variation of the same fundamental problem (stdout buffering, jq null-key edge cases, conclusion-vs-status confusion, TTY-only banner grepping). The skill that documents this anti-pattern is excellent, but a skill only fires if the agent loads it. The tool surface fires on every misuse. This is the embed-footguns-in-tool-surface pattern from PR NousResearch#31289 applied to a recurring failure mode that's outgrown skill-only enforcement. Detector is deliberately narrow — flags two specific shapes: 1. Any command containing `statusCheckRollup` (the JSON-API path — conclusion vs status field semantics keep burning us). 2. `gh pr view` / `gh pr checks` combined with `jq` (gh pr checks doesn't emit JSON, so any `| jq` here is confused intent; the canonical column-2 poller uses awk-on-tabs, not jq). Does NOT flag the blessed column-2 awk-on-tabs poller (which uses `awk -F"\t" "\==\"pending\""`) or the exit-code-driven `gh pr checks $PR >/dev/null` snippet. Hint composes with the existing background-without-notify_on_complete hint — both can fire on the same call. Each is independently actionable. Tests: - 4 new cases in tests/tools/test_notify_on_complete.py - test_homebrew_ci_poller_via_statusCheckRollup_emits_hint (positive) - test_homebrew_ci_poller_via_gh_pr_checks_piped_to_jq_emits_hint (positive) - test_canonical_column2_awk_poller_does_not_emit_homebrew_hint (negative) - test_canonical_gh_pr_checks_exit_code_loop_does_not_emit_hint (negative) - test_non_ci_background_command_does_not_emit_homebrew_hint (negative) - 30/30 passing (was 26)
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
3 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.
Salvage of #30420 onto current main (was 195 commits behind). Closes #30398.
Summary
Adds
ctx.register_tts_provider()plugin hook so TTS engines that don't fit the shell-template grammar (Python SDKs without CLI, streaming, voice-listing APIs, OAuth flows) can register a Python backend. Coexists with the existingtts.providers.<name>: type: commandregistry from #17843 — does not replace it.Resolution order
tts.providers.<name>: type: command→ command-provider dispatchTTSProvider→ plugin dispatch (new)Built-ins-always-win enforced at 3 layers (registry rejection + dispatcher short-circuit + picker filter). Command-providers-win-over-plugins enforced at 2 layers (caller + defensive re-check).
Changes (kshitijk4poor's, +2037/-1, 13 files)
agent/tts_provider.py—TTSProvider(ABC)mirroringimage_gen_provider.py/video_gen_provider.pyagent/tts_registry.py— registry with_BUILTIN_NAMESreject-shadow invarianthermes_cli/plugins.py(+38) —register_tts_provider()onPluginContexttools/tts_tool.py(+148) —_dispatch_to_plugin_provider()+ walrus-elif wiring, built-in elif chain untouchedhermes_cli/tools_config.py(+62) —_plugin_tts_providers()injects rows into Text-to-Speech pickerwebsite/docs/user-guide/features/tts.md(+79) — new "Python plugin providers" section with decision tablewebsite/docs/user-guide/features/plugins.md(+1) — TTS row mentions both surfacesValidation
_dispatch_to_plugin_providerreal callname="edge")get_provider("edge")isNoneContext
This realizes the
register_tts_provider()Teknium flagged as a future nice-to-have in commit a401f81 ("docs(plugins): correct TTS/STT pluggability"). The 10 built-in providers (edge,openai,elevenlabs,minimax,gemini,mistral,xai,piper,kittentts,neutts) stay inline — this PR does NOT migrate any of them.Original PR: #30420
Contributor: @kshitijk4poor (also filed design issue #30398 themselves)
Infographic