Commit Graph

13 Commits

  • feat: align memory phase 1 and make it stronger (#11300)
    ## Align with the new phase-1 design
    
    Basically we know run phase 1 in parallel by considering:
    * Max 64 rollouts
    * Max 1 month old
    * Consider the most recent first
    
    This PR also adds stronger parallelization capabilities by detecting
    stale jobs, retry policies, ownership of computation to prevent double
    computations etc etc
  • memories: add extraction and prompt module foundation (#11200)
    ## Summary
    - add the new `core/src/memories` module (phase-one parsing, rollout
    filtering, storage, selection, prompts)
    - add Askama-backed memory templates for stage-one input/system and
    consolidation prompts
    - add module tests for parsing, filtering, path bucketing, and summary
    maintenance
    
    ## Testing
    - just fmt
    - cargo test -p codex-core --lib memories::
  • Leverage state DB metadata for thread summaries (#10621)
    Summary:
    - read conversation summaries and cwd info from the state DB when
    possible so we no longer rely on rollout files for metadata and avoid
    extra I/O
    - persist CLI version in thread metadata, surface it through summary
    builders, and add the necessary DB migration hooks
    - simplify thread listing by using enriched state DB data directly
    rather than reading rollout heads
    
    Testing:
    - Not run (not requested)
  • feat: resumable backfill (#10745)
    ## Summary
    
    This PR makes SQLite rollout backfill resumable and repeatable instead
    of one-shot-on-db-create.
    
    ## What changed
    
    - Added a persisted backfill state table:
      - state/migrations/0008_backfill_state.sql
    - Tracks status (pending|running|complete), last_watermark, and
    last_success_at.
    - Added backfill state model/types in codex-state:
      - BackfillState, BackfillStatus (state/src/model/backfill_state.rs)
    - Added runtime APIs to manage backfill lifecycle/progress:
      - get_backfill_state
      - mark_backfill_running
      - checkpoint_backfill
      - mark_backfill_complete
    - Updated core startup behavior:
    - Backfill now runs whenever state is not Complete (not only when DB
    file is newly created).
    - Reworked backfill execution:
    - Collect rollout files, derive deterministic watermark per path, sort,
    resume from last_watermark.
    - Process in batches (BACKFILL_BATCH_SIZE = 200), checkpoint after each
    batch.
      - Mark complete with last_success_at at the end.
    
    ## Why
    
    Previous behavior could leave users permanently partially backfilled if
    the process exited during initial async backfill. This change allows
    safe continuation across restarts and avoids restarting from scratch.
  • feat: add phase 1 mem db (#10634)
    - Schema: thread_id (PK, FK to threads.id with cascade delete),
    trace_summary, memory_summary, updated_at.
    - Migration: creates the table and an index on (updated_at DESC,
    thread_id DESC) for efficient recent-first reads.
      - Runtime API (DB-only):
          - `get_thread_memory(thread_id)`: fetch one memory row.
    - `upsert_thread_memory(thread_id, trace_summary, memory_summary)`:
    insert/update by thread id and always advance updated_at.
    - `get_last_n_thread_memories_for_cwd(cwd, n)`: join thread_memory with
    threads and return newest n rows for an exact cwd match.
    - Model layer: introduced ThreadMemory and row conversion types to keep
    query decoding typed and consistent with existing state models.
  • feat: reduce span exposition (#10171)
    This only avoids the creation of duplicates spans
  • chore: unify log queries (#10152)
    Unify log queries to only have SQLX code in the runtime and use it for
    both the log client and for tests
  • chore: improve client (#10149)
    <img width="883" height="84" alt="Screenshot 2026-01-29 at 11 13 12"
    src="https://github.com/user-attachments/assets/090a2fec-94ed-4c0f-aee5-1653ed8b1439"
    />
  • feat: add log db (#10086)
    Add a log DB. The goal is just to store our logs in a `.sqlite` DB to
    make it easier to crawl them and drop the oldest ones.