The mobile client's regenerate-after-failure flow sends a discard index
equal to the server's rendered count (its optimistic user bubble for the
failed turn was never persisted). find_raw_cut treated this as out of
range, surfacing as "Chat rewind failed: discard_from_rendered_index out
of range" and blocking the retry.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- search_rag reranker now logs wall-clock time around the ollama.generate
call, the candidate count / top-N going in, and the final reordering.
The "final indices" + swap-count line is info level so it's always
visible; detailed before/after previews stay at debug for when you want
to inspect reranker quality.
- New OllamaClient::generate_no_think convenience that sets Ollama's
top-level think:false on the request, plumbed through try_generate via
a new internal generate_with_options. Used only by the reranker today;
avoids the chain-of-thought tax on reasoning models (Qwen3/VL,
DeepSeek-R1 distills, GPT-OSS) when the task has nothing to reason
about. Server-side no-op on non-reasoning models.
- OpenRouter chat_with_tools "missing choices[0]" error now includes the
actual response body — extracts structured {error: {code, message}}
when OpenRouter surfaces it (common for upstream-provider issues like
rate limits and content moderation), otherwise falls back to a
truncated raw-JSON view.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Switch the "Agentic tool call" log from {:?} (Debug) to {} (Display) on
serde_json::Value. Display produces compact JSON — `{"date":"2023-08-15"}`
instead of `Object {"date": String("2023-08-15")}` — which is what the
model actually sent and what a human reading the log wants to see.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Few-shot injection on /insights/generate/agentic: compresses prior
training_messages into trajectory blocks (tool calls + result summaries)
and injects into the system prompt. Hardcoded default ids with optional
request override.
- New fewshot_source_ids column on photo_insights (+ migration) to track
which exemplars influenced a given row, for downstream training-set
filtering. Chat amend rows stamp None with a lineage note.
- Ollama client now remembers which server (primary/fallback) most
recently succeeded and tries it first on the next call, via a shared
Arc<AtomicBool>. Avoids re-404ing the primary on every agent iteration
when the chosen model only lives on the fallback.
- Demote noisy logs: daily_summary "Summary match" lines to debug;
inner chat_with_tools non-2xx body log from error to warn (outer
layer owns the terminal-error signal).
- Drift-guard tests for summarize_tool_result covering the success /
empty / error / unknown shape for every tool.
- Tidy: three pre-existing clippy warnings cleaned up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
On copied or restored files (e.g. a backup library), the OS stamps
created at copy time while modified is preserved from the source, so
the earlier of the two is a better proxy for when the content
originated. Adds utils::earliest_fs_time and threads it through the
three spots that fall back to filesystem dates: photos-list sort,
memories grouping, and insight-generation timestamp.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Inject the max-iterations budget into the agentic system prompt for
both insight generation and chat turns. Chat does this per-turn by
appending a note to the replayed system message and restoring it
before persistence so the note doesn't accumulate across turns.
- Stop deleting entity_photo_links at the start of agentic insight
generation. The clear made recall_facts_for_photo always return
empty, wasting a tool call and discarding knowledge from prior runs.
Re-linking the same entity is already an INSERT OR IGNORE no-op.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Introduces USER_NAME (default "Me") as the single source for the message
sender label and the first-person persona across daily summaries, SMS
context, insight generation, and chat. Eliminates the "Me:" transcript /
"what I did" ambiguity that confused smaller models, and unhardcodes
"Cameron" from prompt text + the knowledge-graph owner entity. Set
USER_NAME=Cameron in .env to preserve the existing owner entity row
(keyed on UNIQUE(name, entity_type)) — otherwise the next run creates
a fresh owner entity and orphans the existing facts/photo-links.
Also:
- search_messages redirect: when the model calls it with date/contact
but no query, return a hint pointing at get_sms_messages instead of
a bare missing-parameter error (prevents same-turn retry loops)
- sharpen search_messages vs get_sms_messages tool descriptions so
content-vs-time-based intent is unambiguous
- extract build_daily_summary_prompt (+ DAILY_SUMMARY_MESSAGE_LIMIT,
DAILY_SUMMARY_SYSTEM_PROMPT) shared by daily_summary_job and
test_daily_summary binary — prompt tweaks now land in both
- EMBEDDING_MODEL const; fixes both insert sites that stored
"mxbai-embed-large:335m" while generate_embeddings actually runs
"nomic-embed-text:v1.5"
- test_daily_summary: add --num-ctx / --temperature / --top-p /
--top-k / --min-p flags wired into OllamaClient setters, and print
the configured knobs at the top of each run
- OllamaClient::generate now logs prompt/gen token counts and tok/s
via log_chat_metrics (symmetric with chat_with_tools)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a search_messages tool that hits the Django FTS5/semantic/hybrid
endpoint for keyword-quality text search over message bodies, and an
LLM-based reranker inside tool_search_rag (gated by SEARCH_RAG_RERANK,
default on). Reranker pulls ~3x candidates from the vector index, asks
the chat model to rank by relevance, and falls back to vector order on
parse failure.
The reranker shares the active chat turn's OllamaClient so num_ctx and
sampling match — otherwise Ollama unloads/reloads the model on every
rerank call. (Unverified end-to-end; caught by inspection, awaiting
e2e confirmation.)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Add LlmClient::chat_with_tools_stream and SSE endpoint
POST /insights/chat/stream that emits text deltas, tool_call /
tool_result pairs, truncated notice, and a terminal done frame as the
agentic loop runs.
- Ollama: parses NDJSON from /api/chat stream, accumulates content
deltas, emits Done with tool_calls from the final chunk.
- OpenRouter: parses OpenAI-compatible SSE, reassembles tool_call
argument deltas by index, asks for stream_options.include_usage.
- InsightChatService spawns the loop on a tokio task, feeds events
through an mpsc channel, persists training_messages at the end.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
load_history now groups preceding tool_call + tool_result scaffolding
under each assistant reply as `tools: [{name, arguments, result}]`.
Result bodies over 2000 chars are truncated for payload size with a
`result_truncated` flag; the full value remains in training_messages.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Rewind: POST /insights/chat/rewind truncates training_messages at a
given rendered index, dropping the target message plus any preceding
tool-call scaffolding. The initial user prompt is protected.
Metrics: log prompt_eval_count/duration and eval_count/duration from
every Ollama chat response, rendered as tokens + ms + tok/s.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds POST /insights/chat and GET /insights/chat/history. Replays the
stored agentic conversation through the same backend the insight was
generated with (or a per-turn override), runs a short tool-calling
loop, and persists the extended history in append or amend mode.
Backend switching: same-backend or hybrid->local replay verbatim;
local->hybrid is rejected in v1 (would require on-the-fly vision
description rewrite).
Per-(library, file) async mutex serialises concurrent turns. Soft
context budget drops oldest tool_call+result pairs when the
serialized history exceeds num_ctx - 2048 tokens.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Add OPENROUTER_ALLOWED_MODELS env var and GET /insights/openrouter/models
endpoint returning the curated list verbatim. Drop the live capability
precheck in hybrid mode — trust the operator's allowlist; bad ids surface
as a chat-call error.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a `backend` column to photo_insights (default 'local', migration
2026-04-20-000000) and a corresponding optional `backend` field on the
agentic request. When a request sets backend=hybrid:
- The local Ollama vision model is called once via describe_image to
produce a text description.
- The description is inlined into the first user message as text —
no base64 image is ever sent to the chat model.
- The agentic tool-calling loop and title generation route through an
OpenRouterClient (dispatched via &dyn LlmClient), letting the user
pick any tool-capable model from OpenRouter per request.
- describe_photo is removed from the offered tools since the description
is already present.
Embeddings and vision stay on local Ollama regardless of backend.
Hybrid mode requires OPENROUTER_API_KEY; handlers return a clear error
when hybrid is requested without it, and also when the selected
OpenRouter model lacks tool-calling support.
AppState gains an optional openrouter client built from
OPENROUTER_API_KEY / OPENROUTER_BASE_URL / OPENROUTER_DEFAULT_MODEL /
OPENROUTER_EMBEDDING_MODEL / attribution headers. Default model is
anthropic/claude-sonnet-4.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
OpenAI-compatible client for OpenRouter. Translates canonical wire shapes at
the boundary: tool-call arguments stringify on send / parse on receive
(accepting both string and native-object forms); images rewritten from the
base64 images field into content-parts with image_url entries; role=tool
messages inherit tool_call_id from the preceding assistant's tool calls.
/models parsed into ModelCapabilities via supported_parameters (tool use)
and architecture.input_modalities (vision). 15-minute capabilities cache.
Bearer auth; HTTP-Referer / X-Title attribution headers optional.
Not wired into request routing yet — first consumer arrives with hybrid
backend mode. 11 unit tests cover the translation helpers.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Preparation for a second LLM backend (OpenRouter) and hybrid vision-local /
chat-remote mode. Shared wire types (ChatMessage, Tool, ToolCall, etc.) move
into a new src/ai/llm_client.rs and are re-exported from ollama.rs so
existing imports keep working. OllamaClient now implements LlmClient.
No behavior change; callers still hold the concrete OllamaClient. Caller
migration to Arc<dyn LlmClient> is deferred to the PR that wires hybrid
backend routing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Doubled default row caps for search_rag/get_sms_messages/get_calendar_events/recall_entities and exposed an optional `limit` parameter on each so the agent can tune per call. Render all LLM-facing timestamps as server-local time with explicit offset so smaller models stop misreading UTC as wall-clock time.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Silence forward-looking dead_code on unused DAO modules, annotate
individual placeholder items, rewrite tautological assert!(true/false)
in token tests as panic! arms, and pick up fmt drift.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The /photos/gps-summary handler validated the incoming path against
the primary library's root with new_file=false, which requires the
path to exist on disk. For a viewer opened on a file from a
non-primary library, tapping the GPS link produced activePath =
<folder from lib 2>, the primary-only check failed, and the server
400'd — so the map came up empty.
Validation here is purely a traversal guard (the DAO does a prefix
LIKE against rel_path), so we now accept the path as long as any
configured library can resolve it without escaping its root.
Also applies cargo fmt drift on files touched this session.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The /video/generate and /image/metadata handlers assumed files live under
the resolved library only, which broke when a mobile client passed no
library (union mode) but the file lived in a non-primary library. Both
now fall back to scanning every configured library for an existing file.
InsightGenerator held a single base_path, so vision-model loads and
filename-date fallbacks failed for non-primary libraries. It now takes
Vec<Library> and probes each root in resolve_full_path.
/image/metadata responses now carry library_id/library_name so the
mobile viewer can surface which library a file belongs to.
Thumbnail generation at startup is now spawned on a background thread
so the HTTP server can accept traffic while large libraries backfill.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Tags and insights now follow content across libraries via content_hash
lookups on the read path, so the same file indexed at different rel_paths
in multiple libraries shares its annotations. Recursive tag search scopes
hits to the selected library by checking each tagged rel_path against
the library's disk (with a content-hash sibling fallback so tags attached
under one library's rel_path still match a content-equivalent file in
another). The /image and /image/metadata handlers fall back across
libraries when the file isn't under the resolved one, so union-mode
search results (which carry no library attribution in the response)
still serve correctly.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Adds a `libraries` registry table and threads library_id through
per-instance metadata tables (image_exif, photo_insights,
entity_photo_links, video_preview_clips). File-path columns renamed to
rel_path to make the relative-to-root semantics explicit. Adds
content_hash + size_bytes on image_exif to support future hash-keyed
thumbnail/HLS dedup. Tags and favorites stay library-agnostic so they
share across libraries by rel_path.
Behavior is unchanged: a single primary library (id=1) is seeded from
BASE_PATH on first boot; all handlers and DAOs route through it as a
transitional shim until the API gains a library query param.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Expose Ollama sampling params through the insight generation endpoints
so users can tune creativity/determinism per request. All four are
optional — omitted values fall through to the model's server-side
defaults.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds normalize_entity_type() which lowercases and canonicalises synonyms
(location→place, human→person, etc.) before every upsert. The SQL lookup
now uses lower(entity_type) on both sides so existing dirty rows (Person,
Location) correctly deduplicate against normalised writes without a migration.
Adds a pre-flight similarity check in tool_store_entity: before upserting,
searches active entities of the same type using the first name token. Any
non-exact matches are appended to the tool response so the agentic loop
can choose to reuse an existing entity ID rather than create a duplicate.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a standalone binary that walks a directory and runs the agentic
insight loop over every image/video, skipping files already processed.
Supports --path, --model, --max-iterations, --timeout-secs, --num-ctx,
and --reprocess flags for flexible overnight/VPS batch runs.
Also adds OllamaClient::with_request_timeout() builder method so slow
large models are not cut off by the default 120s limit.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Captures prompt_eval_count and eval_count from Ollama /api/chat responses
during the agentic loop and returns them in POST /insights/generate/agentic
so the frontend can display context window usage to the user.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Sanitise tool call arguments before re-sending in conversation history: non-object values (bool, string, null) that some models produce are normalised to {} to prevent Ollama 500s
- Map 'error parsing tool call' Ollama 500 to HTTP 400 with a descriptive message listing compatible models (llama3.1, llama3.2, qwen2.5, mistral-nemo)
- Add reverse_geocode tool backed by existing Nominatim helper; description hints model can chain it after get_location_history results
- Make get_sms_messages contact parameter optional (was required, forcing the model to guess); executor now passes None to fall back to all-contacts search
- Log tool result outcomes at warn level for errors/empty results, info for successes; log SMS API errors with full detail; log full request body on Ollama 500
- Strengthen system prompt to require 3-4 tool calls before final answer
- Try fallback server when checking model capabilities (primary-only check caused 500 for models only on fallback)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- cargo fmt applied across all modified source files
- Collapse nested if let Some / if !is_empty into a single let-chain (clippy::collapsible_match)
- All other warnings are pre-existing dead-code lint on unused trait methods
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Verify custom model exists on at least one configured server before starting agentic loop; returns HTTP 400 with descriptive error if not found
- has_tool_calling field auto-serialised in GET /insights/models via existing ModelCapabilities Serialize derive
- model_version stored from OllamaClient.primary_model (already correct in T006 implementation)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Register the agentic insight endpoint that validates tool-calling capability,
runs the agentic loop, and returns the stored PhotoInsightResponse. Returns 400
for unsupported models, 500 for other errors. Max iterations configurable via
AGENTIC_MAX_ITERATIONS env var (default 10).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add 6 tool executor methods (search_rag, get_sms_messages, get_calendar_events,
get_location_history, get_file_tags, describe_photo) and the agentic loop that
uses Ollama's chat_with_tools API to let the model decide which context to gather
before writing the final photo insight.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Threads SqliteTagDao through InsightGenerator and AppState (both default
and test_state). Adds Send+Sync bounds to TagDao trait with unsafe impls
for SqliteTagDao (always Mutex-protected) and TestTagDao (single-threaded).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
