AssignAgent activates a plan and starts an agent session.
ManagePullRequest evaluates PR state/CI checks and merges when ready.
ReportToIssue posts progress comments on Forgejo issues.
Co-Authored-By: Virgil <virgil@lethean.io>
Brain memories can now be stored in a separate database, co-located
with Qdrant vectors on the homelab. Defaults to the app's main DB
when no BRAIN_DB_* env vars are set (zero-config for existing installs).
- Add brain.database config with BRAIN_DB_* env var support
- Register 'brain' database connection in Boot.php
- Set BrainMemory model to use 'brain' connection
- Update BrainService transactions to use brain connection
- Update migration to use brain connection, drop workspace FK
(cross-database FKs not supported)
- Add migration to drop FK on existing installs
- Update default URLs from *.lthn.lan to *.lthn.sh
Co-Authored-By: Virgil <virgil@lethean.io>
Adds a private http() helper that wraps Http::timeout() with
conditional withoutVerifying() for self-signed .lan certs behind
Traefik. Boot singleton auto-detects .lan URLs at construction.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Make embedding model swappable via BRAIN_EMBEDDING_MODEL env var.
Switch default from nomic-embed-text to embeddinggemma (Gemma 3
based, 2x better cluster separation in benchmarks).
Default Ollama URL now points to ollama.lan (Linux homelab GPU).
Co-Authored-By: Virgil <virgil@lethean.io>
- Move BrainMemory::create() inside BrainService::remember() for
full atomicity (DB + Qdrant in single transaction)
- Add forWorkspace() scope to recall() MariaDB query (tenant isolation)
- Wrap forget() in DB::transaction (MariaDB first, then Qdrant)
- Check qdrantDelete() response and log warnings on failure
- Validate embed() response is a non-empty array
Co-Authored-By: Virgil <virgil@lethean.io>
Snapshots YAML template content in a new `plan_template_versions` table
whenever a plan is created from a template. Plans reference their version
via `template_version_id` so existing plans are unaffected by future
template file edits.
Key changes:
- Migration 0006: create `plan_template_versions` table (slug, version,
name, content JSON, content_hash SHA-256); add nullable FK
`template_version_id` to `agent_plans`
- Model `PlanTemplateVersion`: `findOrCreateFromTemplate()` deduplicates
identical content by hash; `historyFor()` returns versions newest-first
- `AgentPlan`: add `template_version_id` fillable and `templateVersion()`
relationship
- `PlanTemplateService::createPlan()`: snapshot raw template before
variable substitution; store version id and version number in metadata;
add `getVersionHistory()` and `getVersion()` public methods
- Tests: `TemplateVersionManagementTest` covering model behaviour, plan
creation snapshotting, deduplication, history ordering, and service
methods
Closes#35
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Document each PROVIDER_PATTERNS entry with real User-Agent examples,
add inline comments to BROWSER_INDICATORS and NON_AGENT_BOTS with
categorised UA examples, document MCP_TOKEN_HEADER with token format
details, and add class-level usage examples and detection priority
ordering.
Closes#31
Refs: DOC-001
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ProcessContentTaskTest: set mock properties directly instead of
shouldReceive('__get') which doesn't reliably intercept property
access on Mockery mocks of non-existent classes.
HasStreamParsing: fix parseJSONStream chunked read bug where the
inner parse loop restarted at position 0 with stale state from
a previous partial parse. Track scan position across chunks.
AgentDetection: fix Postman regex \bPostman\b → \bPostman/ so it
matches PostmanRuntime (no word boundary between n and R).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Enhance `validateVariables()` in `PlanTemplateService` to produce
actionable errors instead of the generic "Required variable '...' is missing".
Changes:
- Extracted `buildVariableError()` helper that composes the message from
the variable's `description`, `format`, `example`, and `examples` fields
- Added `naming_convention` key to the returned array so callers have
a constant reminder that variable names use snake_case
- Added a `NAMING_CONVENTION` private const to avoid string duplication
Tests (6 new cases in `PlanTemplateServiceTest`):
- description included in error message
- single `example` value included
- `examples` list (first two) included
- `format` hint included alongside example
- `naming_convention` present in both valid and invalid results
- bare variable (no description) still produces useful "missing" message
Closes#30
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Log a warning for each AI provider registered without an API key so
that misconfiguration is surfaced at boot time (not silently on the
first API call). Each message names the environment variable to set:
ANTHROPIC_API_KEY – Claude
GOOGLE_AI_API_KEY – Gemini
OPENAI_API_KEY – OpenAI
Providers without a key remain registered but are marked unavailable
via isAvailable(), preserving backward compatibility.
- Add Log::warning() calls in registerProviders() for empty keys
- Extend AgenticManagerTest with a dedicated 'API key validation
warnings' describe block (7 new test cases)
- Update DX-002 in TODO.md as resolved
Closes#29
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Track progress in a per-batch JSON state file after each article so
a mid-run crash leaves a recoverable checkpoint
- Add `maxRetries` parameter to generateBatch() with per-article retry
loop (default: 1 extra attempt)
- Add `resumeBatch()` to re-process only failed/pending articles,
skipping those already successfully generated in a prior run
- Add `loadBatchProgress()` public method for inspecting state
- State stores per-article status, attempt counts, error messages,
and timestamps for full observability
Tests: 6 new scenarios covering state persistence, resume capability,
retry logic, and the no-state error case
Closes#27
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wrap stream() in try/catch to prevent silent failures.
On exception, log the error and yield a structured error event:
['type' => 'error', 'message' => string]
Adds tests for connection errors, runtime exceptions, error event
format, and Log::error invocation. Closes ERR-001 in TODO.md.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Cache the list of permitted tool names in `AgentToolRegistry::forApiKey()`
using a 1-hour TTL to avoid O(n) filtering on every request (PERF-002).
- Add `Cache::remember()` in `forApiKey()` storing tool names keyed by API
key ID (`agent_tool_registry:api_key:{id}`)
- Add `flushCacheForApiKey(int|string $id)` for explicit invalidation
- Add `CACHE_TTL` constant (3600 s) for easy tuning
- Invalidate cache in `AgentApiKeyService::updatePermissions()` and `revoke()`
so permission changes take effect immediately
- Add `tests/Unit/AgentToolRegistryTest.php` covering cache hit/miss,
per-key isolation, scope filtering, TTL constant, and flush behaviour
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add phpunit.xml for standalone test execution.
Apply Laravel Pint formatting fixes across all source files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Core\Mod\Tenant -> Core\Tenant
- Core\Service\Agentic -> Core\Mod\Agentic\Service
Part of namespace restructure to align with L1/L2 module conventions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updates all classes to use the new modular namespace convention.
Adds Service/ layer with Core\Service\Agentic for service definition.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
