fix: log plugin memory provider fallback failure at debug level

Address review feedback on PR #1002: replace silent `except Exception: pass`
with `logger.debug(...)` so plugin loading failures are visible in debug logs.

Refs #990

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

hermes_cli/plugins.py

@@ -211,6 +211,43 @@ class PluginContext:
         }
         logger.debug("Plugin %s registered CLI command: %s", self.manifest.name, name)
 
+    # -- memory provider registration ----------------------------------------
+
+    def register_memory_provider(self, provider) -> None:
+        """Register a memory provider supplied by this plugin.
+
+        The provider must be an instance of ``agent.memory_provider.MemoryProvider``.
+        Only one plugin-registered memory provider is accepted; a second
+        attempt is rejected with a warning.
+
+        The registered provider is retrievable via
+        ``get_plugin_memory_provider()`` and is picked up by ``run_agent.py``
+        when ``memory.provider`` in *config.yaml* matches the provider's
+        ``name`` property.
+        """
+        from agent.memory_provider import MemoryProvider
+
+        if not isinstance(provider, MemoryProvider):
+            logger.warning(
+                "Plugin '%s' tried to register a memory provider that does not "
+                "inherit from MemoryProvider. Ignoring.",
+                self.manifest.name,
+            )
+            return
+        if self._manager._plugin_memory_provider is not None:
+            logger.warning(
+                "Plugin '%s' tried to register a memory provider, but one is "
+                "already registered by another plugin. Only one plugin-supplied "
+                "memory provider is allowed at a time.",
+                self.manifest.name,
+            )
+            return
+        self._manager._plugin_memory_provider = provider
+        logger.info(
+            "Plugin '%s' registered memory provider: %s",
+            self.manifest.name, provider.name,
+        )
+
     # -- context engine registration -----------------------------------------
 
     def register_context_engine(self, engine) -> None:
@@ -323,6 +360,7 @@ class PluginManager:
         self._plugin_tool_names: Set[str] = set()
         self._cli_commands: Dict[str, dict] = {}
         self._context_engine = None  # Set by a plugin via register_context_engine()
+        self._plugin_memory_provider = None  # Set by a plugin via register_memory_provider()
         self._discovered: bool = False
         self._cli_ref = None  # Set by CLI after plugin discovery
         # Plugin skill registry: qualified name → metadata dict.
@@ -699,6 +737,11 @@ def get_plugin_context_engine():
     return get_plugin_manager()._context_engine
 
 
+def get_plugin_memory_provider():
+    """Return the plugin-registered memory provider, or None."""
+    return get_plugin_manager()._plugin_memory_provider
+
+
 def get_plugin_toolsets() -> List[tuple]:
     """Return plugin toolsets as ``(key, label, description)`` tuples.
 

optional-skills/dogfood/adversarial-ux-test/SKILL.md

@@ -1,190 +0,0 @@
----
-name: adversarial-ux-test
-description: Roleplay the most difficult, tech-resistant user for your product. Browse the app as that persona, find every UX pain point, then filter complaints through a pragmatism layer to separate real problems from noise. Creates actionable tickets from genuine issues only.
-version: 1.0.0
-author: Omni @ Comelse
-license: MIT
-metadata:
-  hermes:
-    tags: [qa, ux, testing, adversarial, dogfood, personas, user-testing]
-    related_skills: [dogfood]
----
-
-# Adversarial UX Test
-
-Roleplay the worst-case user for your product — the person who hates technology, doesn't want your software, and will find every reason to complain. Then filter their feedback through a pragmatism layer to separate real UX problems from "I hate computers" noise.
-
-Think of it as an automated "mom test" — but angry.
-
-## Why This Works
-
-Most QA finds bugs. This finds **friction**. A technically correct app can still be unusable for real humans. The adversarial persona catches:
-- Confusing terminology that makes sense to developers but not users
-- Too many steps to accomplish basic tasks
-- Missing onboarding or "aha moments"
-- Accessibility issues (font size, contrast, click targets)
-- Cold-start problems (empty states, no demo content)
-- Paywall/signup friction that kills conversion
-
-The **pragmatism filter** (Phase 3) is what makes this useful instead of just entertaining. Without it, you'd add a "print this page" button to every screen because Grandpa can't figure out PDFs.
-
-## How to Use
-
-Tell the agent:
-```
-"Run an adversarial UX test on [URL]"
-"Be a grumpy [persona type] and test [app name]"
-"Do an asshole user test on my staging site"
-```
-
-You can provide a persona or let the agent generate one based on your product's target audience.
-
-## Step 1: Define the Persona
-
-If no persona is provided, generate one by answering:
-
-1. **Who is the HARDEST user for this product?** (age 50+, non-technical role, decades of experience doing it "the old way")
-2. **What is their tech comfort level?** (the lower the better — WhatsApp-only, paper notebooks, wife set up their email)
-3. **What is the ONE thing they need to accomplish?** (their core job, not your feature list)
-4. **What would make them give up?** (too many clicks, jargon, slow, confusing)
-5. **How do they talk when frustrated?** (blunt, sweary, dismissive, sighing)
-
-### Good Persona Example
-> **"Big Mick" McAllister** — 58-year-old S&C coach. Uses WhatsApp and that's it. His "spreadsheet" is a paper notebook. "If I can't figure it out in 10 seconds I'm going back to my notebook." Needs to log session results for 25 players. Hates small text, jargon, and passwords.
-
-### Bad Persona Example
-> "A user who doesn't like the app" — too vague, no constraints, no voice.
-
-The persona must be **specific enough to stay in character** for 20 minutes of testing.
-
-## Step 2: Become the Asshole (Browse as the Persona)
-
-1. Read any available project docs for app context and URLs
-2. **Fully inhabit the persona** — their frustrations, limitations, goals
-3. Navigate to the app using browser tools
-4. **Attempt the persona's ACTUAL TASKS** (not a feature tour):
-   - Can they do what they came to do?
-   - How many clicks/screens to accomplish it?
-   - What confuses them?
-   - What makes them angry?
-   - Where do they get lost?
-   - What would make them give up and go back to their old way?
-
-5. Test these friction categories:
-   - **First impression** — would they even bother past the landing page?
-   - **Core workflow** — the ONE thing they need to do most often
-   - **Error recovery** — what happens when they do something wrong?
-   - **Readability** — text size, contrast, information density
-   - **Speed** — does it feel faster than their current method?
-   - **Terminology** — any jargon they wouldn't understand?
-   - **Navigation** — can they find their way back? do they know where they are?
-
-6. Take screenshots of every pain point
-7. Check browser console for JS errors on every page
-
-## Step 3: The Rant (Write Feedback in Character)
-
-Write the feedback AS THE PERSONA — in their voice, with their frustrations. This is not a bug report. This is a real human venting.
-
-```
-[PERSONA NAME]'s Review of [PRODUCT]
-
-Overall: [Would they keep using it? Yes/No/Maybe with conditions]
-
-THE GOOD (grudging admission):
-- [things even they have to admit work]
-
-THE BAD (legitimate UX issues):
-- [real problems that would stop them from using the product]
-
-THE UGLY (showstoppers):
-- [things that would make them uninstall/cancel immediately]
-
-SPECIFIC COMPLAINTS:
-1. [Page/feature]: "[quote in persona voice]" — [what happened, expected]
-2. ...
-
-VERDICT: "[one-line persona quote summarizing their experience]"
-```
-
-## Step 4: The Pragmatism Filter (Critical — Do Not Skip)
-
-Step OUT of the persona. Evaluate each complaint as a product person:
-
-- **RED: REAL UX BUG** — Any user would have this problem, not just grumpy ones. Fix it.
-- **YELLOW: VALID BUT LOW PRIORITY** — Real issue but only for extreme users. Note it.
-- **WHITE: PERSONA NOISE** — "I hate computers" talking, not a product problem. Skip it.
-- **GREEN: FEATURE REQUEST** — Good idea hidden in the complaint. Consider it.
-
-### Filter Criteria
-1. Would a 35-year-old competent-but-busy user have the same complaint? → RED
-2. Is this a genuine accessibility issue (font size, contrast, click targets)? → RED
-3. Is this "I want it to work like paper" resistance to digital? → WHITE
-4. Is this a real workflow inefficiency the persona stumbled on? → YELLOW or RED
-5. Would fixing this add complexity for the 80% who are fine? → WHITE
-6. Does the complaint reveal a missing onboarding moment? → GREEN
-
-**This filter is MANDATORY.** Never ship raw persona complaints as tickets.
-
-## Step 5: Create Tickets
-
-For **RED** and **GREEN** items only:
-- Clear, actionable title
-- Include the persona's verbatim quote (entertaining + memorable)
-- The real UX issue underneath (objective)
-- A suggested fix (actionable)
-- Tag/label: "ux-review"
-
-For **YELLOW** items: one catch-all ticket with all notes.
-
-**WHITE** items appear in the report only. No tickets.
-
-**Max 10 tickets per session** — focus on the worst issues.
-
-## Step 6: Report
-
-Deliver:
-1. The persona rant (Step 3) — entertaining and visceral
-2. The filtered assessment (Step 4) — pragmatic and actionable
-3. Tickets created (Step 5) — with links
-4. Screenshots of key issues
-
-## Tips
-
-- **One persona per session.** Don't mix perspectives.
-- **Stay in character during Steps 2-3.** Break character only at Step 4.
-- **Test the CORE WORKFLOW first.** Don't get distracted by settings pages.
-- **Empty states are gold.** New user experience reveals the most friction.
-- **The best findings are RED items the persona found accidentally** while trying to do something else.
-- **If the persona has zero complaints, your persona is too tech-savvy.** Make them older, less patient, more set in their ways.
-- **Run this before demos, launches, or after shipping a batch of features.**
-- **Register as a NEW user when possible.** Don't use pre-seeded admin accounts — the cold start experience is where most friction lives.
-- **Zero WHITE items is a signal, not a failure.** If the pragmatism filter finds no noise, your product has real UX problems, not just a grumpy persona.
-- **Check known issues in project docs AFTER the test.** If the persona found a bug that's already in the known issues list, that's actually the most damning finding — it means the team knew about it but never felt the user's pain.
-- **Subscription/paywall testing is critical.** Test with expired accounts, not just active ones. The "what happens when you can't pay" experience reveals whether the product respects users or holds their data hostage.
-- **Count the clicks to accomplish the persona's ONE task.** If it's more than 5, that's almost always a RED finding regardless of persona tech level.
-
-## Example Personas by Industry
-
-These are starting points — customize for your specific product:
-
-| Product Type | Persona | Age | Key Trait |
-|-------------|---------|-----|-----------|
-| CRM | Retirement home director | 68 | Filing cabinet is the current CRM |
-| Photography SaaS | Rural wedding photographer | 62 | Books clients by phone, invoices on paper |
-| AI/ML Tool | Department store buyer | 55 | Burned by 3 failed tech startups |
-| Fitness App | Old-school gym coach | 58 | Paper notebook, thick fingers, bad eyes |
-| Accounting | Family bakery owner | 64 | Shoebox of receipts, hates subscriptions |
-| E-commerce | Market stall vendor | 60 | Cash only, smartphone is for calls |
-| Healthcare | Senior GP | 63 | Dictates notes, nurse handles the computer |
-| Education | Veteran teacher | 57 | Chalk and talk, worksheets in ring binders |
-
-## Rules
-
-- Stay in character during Steps 2-3
-- Be genuinely mean but fair — find real problems, not manufactured ones
-- The pragmatism filter (Step 4) is **MANDATORY**
-- Screenshots required for every complaint
-- Max 10 tickets per session
-- Test on staging/deployed app, not local dev
-- One persona, one session, one report

run_agent.py

@@ -1193,6 +1193,18 @@ class AIAgent:
                     from plugins.memory import load_memory_provider as _load_mem
                     self._memory_manager = _MemoryManager()
                     _mp = _load_mem(_mem_provider_name)
+                    # Fall back to a user plugin that called register_memory_provider()
+                    if _mp is None:
+                        try:
+                            from hermes_cli.plugins import get_plugin_memory_provider as _gpm
+                            _candidate = _gpm()
+                            if _candidate and _candidate.name == _mem_provider_name:
+                                _mp = _candidate
+                        except Exception as _gpm_err:
+                            logger.debug(
+                                "get_plugin_memory_provider() failed during fallback lookup: %s",
+                                _gpm_err,
+                            )
                     if _mp and _mp.is_available():
                         self._memory_manager.add_provider(_mp)
                     if self._memory_manager.providers:

tests/hermes_cli/test_plugins.py

@@ -19,6 +19,7 @@ from hermes_cli.plugins import (
     PluginManifest,
     get_plugin_manager,
     get_pre_tool_call_block_message,
+    get_plugin_memory_provider,
     discover_plugins,
     invoke_hook,
 )
@@ -609,3 +610,105 @@ class TestPreLlmCallTargetRouting:
 # in PluginContext (hermes_cli/plugins.py).  The tests referenced _plugin_commands,
 # commands_registered, get_plugin_command_handler, and GATEWAY_KNOWN_COMMANDS
 # integration — all of which are unimplemented features.
+
+
+# ── TestRegisterMemoryProvider ─────────────────────────────────────────────
+
+
+class TestRegisterMemoryProvider:
+    """Regression tests for PluginContext.register_memory_provider() — issue #990.
+
+    The MemPalace plugin (and any user plugin following the developer guide)
+    calls ``ctx.register_memory_provider(provider)`` inside ``register(ctx)``.
+    Before the fix, PluginContext had no such method and the plugin failed to
+    load with: 'PluginContext' object has no attribute 'register_memory_provider'.
+    """
+
+    def _make_memory_plugin(self, plugins_dir: "Path", name: str) -> None:
+        """Write a minimal user plugin that registers a stub MemoryProvider."""
+        from agent.memory_provider import MemoryProvider
+
+        plugin_dir = plugins_dir / name
+        plugin_dir.mkdir(parents=True, exist_ok=True)
+        (plugin_dir / "plugin.yaml").write_text(
+            f"name: {name}\nversion: 0.1.0\ndescription: Stub memory plugin\n"
+        )
+        # The register() body imports and calls register_memory_provider — this
+        # is the exact pattern documented in memory-provider-plugin.md and used
+        # by third-party plugins such as MemPalace.
+        (plugin_dir / "__init__.py").write_text(
+            "from agent.memory_provider import MemoryProvider\n"
+            "\n"
+            "class _StubProvider(MemoryProvider):\n"
+            "    @property\n"
+            f"    def name(self): return '{name}'\n"
+            "    def is_available(self): return True\n"
+            "    def initialize(self, session_id, **kw): pass\n"
+            "    def get_tool_schemas(self): return []\n"
+            "\n"
+            "def register(ctx):\n"
+            "    ctx.register_memory_provider(_StubProvider())\n"
+        )
+
+    def test_register_memory_provider_succeeds(self, tmp_path, monkeypatch):
+        """A user plugin calling register_memory_provider() loads without error."""
+        plugins_dir = tmp_path / "hermes_test" / "plugins"
+        self._make_memory_plugin(plugins_dir, "mempalace")
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path / "hermes_test"))
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        assert "mempalace" in mgr._plugins
+        assert mgr._plugins["mempalace"].enabled, (
+            mgr._plugins["mempalace"].error
+        )
+
+    def test_plugin_memory_provider_stored(self, tmp_path, monkeypatch):
+        """The provider instance is accessible via get_plugin_memory_provider()."""
+        import hermes_cli.plugins as plugins_mod
+
+        plugins_dir = tmp_path / "hermes_test" / "plugins"
+        self._make_memory_plugin(plugins_dir, "mempalace")
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path / "hermes_test"))
+
+        mgr = PluginManager()
+        # Swap the singleton so get_plugin_memory_provider() sees our manager
+        monkeypatch.setattr(plugins_mod, "_plugin_manager", mgr)
+        mgr.discover_and_load()
+
+        provider = get_plugin_memory_provider()
+        assert provider is not None
+        assert provider.name == "mempalace"
+
+    def test_second_registration_rejected(self, tmp_path, monkeypatch):
+        """Only one plugin-registered memory provider is accepted."""
+        plugins_dir = tmp_path / "hermes_test" / "plugins"
+        self._make_memory_plugin(plugins_dir, "first_provider")
+        self._make_memory_plugin(plugins_dir, "second_provider")
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path / "hermes_test"))
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        # The manager should hold exactly one provider
+        assert mgr._plugin_memory_provider is not None
+        assert mgr._plugin_memory_provider.name in {"first_provider", "second_provider"}
+
+    def test_non_provider_rejected(self, tmp_path, monkeypatch):
+        """Passing a non-MemoryProvider object logs a warning and is ignored."""
+        plugins_dir = tmp_path / "hermes_test" / "plugins"
+        plugin_dir = plugins_dir / "bad_provider"
+        plugin_dir.mkdir(parents=True, exist_ok=True)
+        (plugin_dir / "plugin.yaml").write_text("name: bad_provider\n")
+        (plugin_dir / "__init__.py").write_text(
+            "def register(ctx):\n"
+            "    ctx.register_memory_provider('not-a-provider')\n"
+        )
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path / "hermes_test"))
+
+        mgr = PluginManager()
+        mgr.discover_and_load()
+
+        # Plugin still loads (warning only), but no provider is stored
+        assert mgr._plugin_memory_provider is None

tests/test_optional_adversarial_ux_skill_catalog.py

@@ -1,25 +0,0 @@
-from pathlib import Path
-
-from tools.skills_hub import OptionalSkillSource
-
-
-REPO_ROOT = Path(__file__).resolve().parents[1]
-
-
-def test_optional_skill_source_scans_adversarial_ux_test():
-    source = OptionalSkillSource()
-    metas = {meta.identifier: meta for meta in source._scan_all()}
-
-    assert "official/dogfood/adversarial-ux-test" in metas
-    assert metas["official/dogfood/adversarial-ux-test"].name == "adversarial-ux-test"
-    assert "tech-resistant user" in metas["official/dogfood/adversarial-ux-test"].description
-
-
-def test_optional_skill_catalog_docs_list_adversarial_ux_test():
-    optional_catalog = (REPO_ROOT / "website" / "docs" / "reference" / "optional-skills-catalog.md").read_text(encoding="utf-8")
-    bundled_catalog = (REPO_ROOT / "website" / "docs" / "reference" / "skills-catalog.md").read_text(encoding="utf-8")
-
-    assert "**adversarial-ux-test**" in optional_catalog
-    assert "official/dogfood/adversarial-ux-test" in optional_catalog
-    assert "`adversarial-ux-test`" in bundled_catalog
-    assert "dogfood/adversarial-ux-test" in bundled_catalog

website/docs/reference/optional-skills-catalog.md

@@ -16,7 +16,6 @@ For example:
 
 ```bash
 hermes skills install official/blockchain/solana
-hermes skills install official/dogfood/adversarial-ux-test
 hermes skills install official/mlops/flash-attention
 ```
 
@@ -57,12 +56,6 @@ hermes skills uninstall <skill-name>
 | **blender-mcp** | Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. |
 | **meme-generation** | Generate real meme images by picking a template and overlaying text with Pillow. Produces actual `.png` meme files. |
 
-## Dogfood
-
-| Skill | Description |
-|-------|-------------|
-| **adversarial-ux-test** | Roleplay the most difficult, tech-resistant user for a product — browse in-persona, rant, then filter through a RED/YELLOW/WHITE/GREEN pragmatism layer so only real UX friction becomes tickets. |
-
 ## DevOps
 
 | Skill | Description |

website/docs/reference/skills-catalog.md

@@ -59,12 +59,9 @@ DevOps and infrastructure automation skills.
 
 ## dogfood
 
-Internal dogfooding and QA skills used to test Hermes Agent itself.
-
 | Skill | Description | Path |
 |-------|-------------|------|
 | `dogfood` | Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports. | `dogfood/dogfood` |
-| `adversarial-ux-test` | Roleplay the most difficult, tech-resistant user for a product — browse in-persona, rant, then filter through a RED/YELLOW/WHITE/GREEN pragmatism layer so only real UX friction becomes tickets. | `dogfood/adversarial-ux-test` |
 | `hermes-agent-setup` | Help users configure Hermes Agent — CLI usage, setup wizard, model/provider selection, tools, skills, voice/STT/TTS, gateway, and troubleshooting. | `dogfood/hermes-agent-setup` |
 
 ## email