Commit Graph
10 Commits
Author SHA1 Message Date
retoorandClaude Sonnet 5.5 bc11475f29 Send per-app provider attribution titles from one gateway app registry
Add openai_gateway/apps.py as the single list of internal gateway apps and
send X-OpenRouter-Title (plus legacy X-Title and HTTP-Referer) per app to
every upstream. Label the Devii agent, bots, modifier, quiz grading, SEO
metadata, community and sync callers. Shorten two app references that
exceeded the 30 character limit and were recorded as default.
Also includes the pending Muse Code, route health and Responses work.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-04 18:45:09 +01:00
retoorandClaude Sonnet 5 569f1dcc64 Add OpenCode Zen support, model health/stats dashboard, and gateway fallback fixes
AI gateway:
- Add a generic, admin-selectable `client_profile` field on gateway_providers
  (e.g. "opencode") so a provider needing special request headers (OpenCode
  Zen's client-identity spoofing) is configured like any other provider, not
  hardcoded by name.
- Track per-(provider, model) reliability/speed/latency health in memory,
  seeded from the existing gateway_usage_ledger at startup - purely
  observational, never influences routing.
- New Stats tab on /admin/gateway: request volume, latency, per-model
  breakdowns, and reliability weight, charted with a vendored Chart.js and
  devplace's own theme tokens.
- Record which model a failed request actually fell back to
  (fallback_used_route), surfaced in the Recent Failures table.
- Stop excluding context_length errors from fallback, and skip a primary
  attempt outright when its known context window is already too small for
  the estimated request size, going straight to the fallback.
- gateway_usage_ledger's provider/fallback_used_route columns and indexes
  are ensured centrally in database/schema.py's init_db(), the single point
  of truth for this table's schema.
- Non-OpenAI upstream routing and client-model passthrough; trust only the
  upstream's own X-Gateway-Model header for served-model attribution.

Devii agent:
- Fix a real lockup: plan/verify tools could be individually disabled via
  the admin tool toggles while still being required by the protocol gate,
  permanently bricking any task that needed tools. They can no longer be
  disabled, and the gate now also checks the tool is actually offered.
- Fix compaction being silently calibrated for a 1M-token model while
  running a much smaller one: context budget is now percentage-based and
  the summarizer's own request is sized to fit the real model.
- Give a specific, actionable retry message when plan()'s own arguments get
  cut off by the output limit, and tighten its schema to discourage
  overlong plans.

Other:
- Backup service: offload completed backups to a remote Hetzner Storage Box.
- Container manager: fix orphan blob leaks from sync races, add a two-phase
  plan/execute `system prune` CLI command.
- Admin gateway UI: replace the JS-rendered model/provider tables with
  server-rendered forms and pages.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DhmEkvutuwtzFVcLbTrhdo
2026-09-09 07:38:24 +02:00
retoorandClaude Sonnet 5 d9ff99c4a0 Let the gateway target non-OpenAI upstreams and allow client model passthrough
gateway_thinking_dialect overrides the URL-sniffed protocol dialect for a
reverse-proxied upstream (e.g. Ollama) whose URL carries no identifying
token; upstream_capabilities() uses the same effective dialect to stop
sending stream_options to upstreams that don't support it. gateway_allow_client_model
lets a client-requested model name through even with force-model on, for
an upstream that serves many models with no single stable alias.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XjW4qocnaJxhugUi5ca8Wo
2026-09-07 13:36:42 +02:00
retoorandClaude Sonnet 5 a693a6f4d8 Add admin-unlimited workspaces, AI gateway model fallback, and real streaming/thinking control
Admin-unlimited Dev Workspaces: an admin-owned workspace is now exempt from the
max-workspace-count limit, the max-tunnel-count limit, and the whole
idle-stop/idle-warn/retention-delete lifecycle. Resolved once in
quota.resolve() as Limits.unlimited (owner uid checked against
get_admin_uids()), consumed at the three enforcement points
(provision.ensure, provision.publish_tunnel,
WorkspaceService._advance_lifecycle). Also hardens
get_admin_uids()/get_primary_admin_uid() against a partially-schemaed users
table (uid/role column guard), which a fresh test/init_db() path could hit.

AI gateway per-model automatic fallback: any gateway_models route
(chat/embed/image) can now name a fallback_model, picked on /admin/gateway
from a select box of other configured public model names of the same kind
only (never an internal upstream model id). When a route fails after its own
retries are exhausted, the gateway retries once, automatically, against the
fallback's own provider/pricing/key, before any bytes reach the client
(including for a streaming response). One hop only, no chains or cycles;
self-reference and cross-kind fallbacks are rejected at write time.

AI gateway real upstream streaming and thinking-default control: stream:true
is now forwarded to the upstream and relayed to the client as real SSE
chunks (measured TTFT/inter-token latency) instead of a simulated split
response, and every chat/vision call explicitly disables model "thinking" by
default (admin-overridable via gateway_thinking), with per-dialect handling
for DeepSeek, OpenRouter, and Ollama.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TjdKTWgWpW2SMNW8SFqxz5
2026-09-03 08:47:57 +02:00
retoor c53e2a3319 Update 2026-07-19 18:57:43 +02:00
retoor 6ceca3d0d4 docs: document server-side rendering pipeline, response timing middleware, and Telegram pairing API
- Add comprehensive documentation for backend content rendering in AGENTS.md, detailing the new `render_content` and `render_title` Jinja globals built on mistune with media processing, emoji shortcodes, and XSS protection
- Document the `X-Response-Time` header and bottom-left render time indicator in README.md
- Update bot token pricing documentation to clarify fallback vs gateway cost headers
- Add `email_accounts` to soft-delete tables and `idx_users_role` composite index in database schema
- Implement `telegram_pairings` and `telegram_links` table creation with column migration and indexes
- Add `/profile/{username}/telegram` endpoint to docs API with request/unpair actions
- Register `TelegramService` in main.py lifespan and add `response_timing` middleware emitting `X-Response-Time` header
- Introduce `TelegramPairForm` model and `guard_public_host_sync` synchronous host validation function
2026-06-18 22:09:34 +00:00
retoor 7fc9b0f715 chore: add retoor header to all devplacepy source files and update style agent header rule
The diff adds the mandatory `retoor <retoor@molodetz.nl>` header comment to every `.py` file under `devplacepy/` (including `__init__.py` and `routers/__init__.py`), and updates the `StyleAgent` in `agents/style.py` to instruct agents to only add the header on created or already-edited files rather than sweeping the entire repo. The `agents/base.py` operating protocol is also revised to reorder and clarify tool discipline rules.
2026-06-11 23:58:46 +00:00
retoor c4f2937415 fix: normalize unicode escape sequences and reformat multi-line expressions across codebase 2026-06-09 16:48:08 +00:00
retoor 97eb58fc19 feat: add project file system with CRUD, upload, inline editing, and video attachment support
- Add new `/projects/{slug}/files` endpoint group for per-project filesystem operations including directory and file CRUD, upload, and inline editing with public read and owner write access
- Extend attachment system to support video formats (webm, ogv, mov, m4v) with proper file icons and MIME types
- Implement configurable allowed file types via `allowed_file_types` site setting, replacing hardcoded `ALLOWED_UPLOAD_TYPES` with dynamic `allowed_extensions()` and `is_extension_allowed()` functions
- Add `delete_all_project_files()` call in `delete_content_item()` to clean up project files when a project is deleted
- Create database indexes on `project_files` table for `(project_uid, path)` and `(project_uid, parent_path)` to optimize file lookups
- Introduce `docs_prose.py` module with `render_prose()` function that renders Markdown content inside `data-render` divs using mistune, enabling dynamic prose rendering in documentation pages
- Enhance docs search with Markdown-aware text stripping (`_demarkdown()`) and improved HTML/script/style sanitization for better search indexing
- Update documentation API samples to reflect new attachment response fields (`is_image`, `is_video`, `mime_type`) and note video format support
- Update README to document the new project files endpoint and clarify AI gateway attribution for guest Devii sessions
2026-06-08 20:51:09 +00:00
retoor e0535bb7c5 feat: add api key auth, devii agent, openai gateway, and admin service management
This commit introduces a comprehensive set of new features including API key authentication with CLI management commands (get, reset, backfill), a Devii agentic assistant with WebSocket terminal and session bootstrap, an OpenAI-compatible LLM gateway service, and an admin service management panel. It also adds Playwright browser automation for bot support, configures internal gateway URLs, refactors content editing/deletion to support JSON API responses, and updates documentation across AGENTS.md, README.md, and the developer docs site.
2026-06-08 15:38:33 +00:00