v3.0.0: AgentFeedback: new home, new names, fresh start

The project moved to github.com/AgentFeedback/agentfeedback
and is the open-source, self-hostable AgentFeedback
(agentfeedback.dev); a hosted version with the
same API runs at agentfeedback.io. Every name
changes and v3 is a fresh start: no migration from or compatibility with
2.x deployments and skill installs. The HTTP API (1.1), payloads and hash forms are unchanged.

• Skills agent-feedback → agentfeedback 4.0 and
  agent-feedback-triage → agentfeedback-triage 3.0: new directory and
  invocation names (/agentfeedback-triage). Client environment variables
  keep their names (AGENT_FEEDBACK_*); the spool moves to ~/.cache/agentfeedback and triage digests to
  ${TMPDIR:-/tmp}/agentfeedback-triage/. The skills work against a
  self-hosted service or https://api.agentfeedback.io.
• Service: Go module github.com/agentfeedback/agentfeedback; binary
  agentfeedback (cmd/agentfeedback, /opt/agentfeedback, runs as user
  agentfeedback); image ghcr.io/agentfeedback/agentfeedback; default
  database /data/agentfeedback.db; metrics renamed agentfeedback_*
  (agentfeedback_submissions_unprocessed, agentfeedback_db_bytes,
  agentfeedback_sqlite_busy_total).
• Deploy: stack directory infra/agentfeedback, compose service
  agentfeedback, volume agentfeedback-data, server directory
  ~/agentfeedback, variables AGENTFEEDBACK_IMAGE and
  AGENTFEEDBACK_BIND_ADDRESS.
• Removed: the 1.x PostgreSQL export script and migration and uninstall
  docs, and the docs/agent-usage.md redirect.
• CI lowercases the image name (the org name has capitals).

v2.2.1: Documentation sweep

Docs and skill documentation only; the service and scripts behave as in
v2.2.0.

• Skill agent-feedback-triage 2.1: the optional clustering contract
  moved to reference/clustering.md, read only when clustering is used, and
  repeated rules were collapsed: SKILL.md is a third shorter per invocation.
  Install the whole directory, including reference/. Resolutions now start
  with their verdict (FIXED, INVALID, DUPLICATE-OF-<id>). Fixed: the
  close-out commands' path to the sibling skill, digest exit codes, the
  meaning of unchanged versus updated, and cluster.py's statuses, reasons
  and exit codes.
• Skill agent-feedback (contract unchanged): corrected the machine
  override, --sweep age/lock/outcome behaviour, backlog-warning scope, TSV
  column 5, slots usage, 1xx/3xx outcomes, export digest tools, and added
  AGENT_FEEDBACK_TRIAGE_ROOTS.
• api.md states its version (1.1), the non-JSON responses and the
  include=payload row shape.
• operate.md: the retention purge runs as root, backups create
  their directory, openssl and DEPLOY_DIR are documented, and uninstall
  covers the triage variables.
• CLAUDE.md routes to develop.md, the single home for
  commands, rules and gates; the README quickstart checks out the latest tag
  and keeps an existing key.

v2.2.0: Triage skill renamed; batched, measured clustering

• Skill feedback-triage is now agent-feedback-triage 2.0. The
  invocation name and the install directory change: update installers,
  links and prompts that name skills/feedback-triage, and remove the old
  copy (operate.md lists both names). Digests move to
  ${TMPDIR:-/tmp}/agent-feedback-triage/. No service/API or storage changes.
• The triage skill is direct invocation only: disable-model-invocation: true
  (Claude Code) and a description that forbids loading it from phrasing
  about the queue. Invoke it as /agent-feedback-triage or by name.
• Docs: install guidance for the triage skill, the rule to re-measure after
  any cluster.py prompt, threshold or batching change, and the eval
  script's disclosure boundary in security.md.
• cluster.py batches comparisons: up to 8 reports per request, every pair
  asked once over a shared state, so 24 reports need 15 requests instead of
  276 (which exceeded the old cap and skipped advice). One request per pair
  remains the fallback for batch sizes below 4 and for chunks over the
  model's token budget; a pair too large alone is marked unassessed without
  a request. One invalid answer in a batch marks only that pair.
• --max-pairs is replaced by --max-requests (default 200); the old
  flag is rejected because its unit changed. New --batch-size (default 8).
• Probability sums tolerate the model's per-option two-decimal rounding.
• Calibration recorded in the skill: on 112 labelled pairs, no different
  pair was grouped at the 0.8 threshold; consent, dry-run, key handling and
  complete-link grouping are unchanged. scripts/eval-cluster.py repeats
  the measurement and refuses to send any report whose exact remote was not
  approved with --allow-repo.
• Go module dependency updates (indirect only).

v2.1.0: Optional advisory triage clustering

• Skill feedback-triage 1.1 adds a Python 3.9+ helper that compares
  report mechanisms through TypeSafe and suggests clusters. The manual
  workflow remains the default; no service/API or storage changes.
• Disclosure requires explicit approval for each exact repository identity.
  Preview is local; unapproved or unidentified reports are never sent.
  No credential is copied, no queue item is marked, and no report is removed.
• Advice retains source IDs, the digest hash and individual probabilities.
  Groups require agreement for every member pair, not transitive matches.
  Uncertain, unavailable and invalid answers fall back to manual triage;
  bounded requests preserve partial results without dropping reports.

v2.0.0: SQLite, generic events, triage skill

Breaking operational contract, compatible API.

• Storage: PostgreSQL replaced by SQLite (modernc.org/sqlite, pure Go).
  One container, one named volume, no database service. Physical backups via
  feedback backup, logical via GET /api/v1/export; restore and migration
  via feedback import (all-or-nothing, header/count/digest verified, hashes
  recomputed, --family filter, ids never reused). See
  operate.md
  for the 1.x migration procedure; scripts/export-v1-postgres.sh produces
  the import file from a 1.x deployment with ids, timestamps, processing state
  and hashes preserved.
• API 1.1 (api.md): additive. family and payload_hash on
  every record, POST /api/v1/events, resolution when marking processed,
  keyset pagination (before_id, has_more, next_before_id, total),
  include=payload, GET /api/v1/export, six-digit timestamps. Every 1.0
  request and response field is unchanged.
• Service: stdlib net/http, Prometheus with bounded labels plus backlog,
  database size and busy counters. OpenTelemetry, chi, sqlc and the
  PostgreSQL-specific configuration are gone. GRACEFUL_SHUTDOWN_TIMEOUT
  default is now 30s; the fixed 5s drain sleep is removed. Payloads are
  returned byte-exact (large integers no longer round).
• Deployment: scripts/deploy.sh <sha> installs the compose file,
  preserves the host .env, pins the image there and runs docker compose pull && up. Requires the GHCR package to be pullable by the host. The
  crane streaming path is gone.
• Skill agent-feedback 3.0: new submit-event.sh; process.sh list
  pages through the whole queue and takes --include-processed (the old
  --all errors), done takes --resolution; query.sh export;
  submit-review.sh --sweep scans REVIEW_LOG_DIR and
  AGENT_FEEDBACK_REVIEW_DIRS only (set the latter where hardcoded cache
  paths were relied on). Fixes: spool persistence is verified (an unwritable
  spool now fails loudly instead of reporting spooled), review receipts are
  validated before a run is marked submitted, large prose no longer passes
  through argv, --dry-run applies the server's validation, rejected spool
  files are kept 30 days as documented.
• New skill feedback-triage 1.0: end-to-end queue processing with one
  consolidated interview. scripts/digest.sh pulls and groups the open queue.
• Docs rewritten for agents first: README route table, api.md,
  operate.md, develop.md, security.md. Template-era documents removed;
  docs/agent-usage.md redirects to api.md.

Upgrade: follow the migration procedure; the 1.x PostgreSQL volume is not
read by 2.x. Producers need skill 3.0 only for the new features; 2.1 clients
keep working against the 2.0.0 service.

v1.0.1: Public documentation and release workflow

Public documentation and release workflow

• Replaced the long README with a 56-line overview and linked setup, security, development, deployment, and operations guides.
• Added guarded annotated-tag/stable-release tooling and documented SemVer publication for every delivered change.
• Updated Go to toolchain 1.27.1, stable Go dependencies, container bases, and GitHub Actions.
• Aligned the service version with v1.0.1 and expanded private environment-file ignores.

Compatibility

No API or database migration changes. Companion skill version 2.1 is unchanged. Back up before upgrades; deploy the CI-published commit-SHA image (source release tags are not container tags).

Verification

Local service check gate, PostgreSQL-backed race/integration tests, 55 hermetic client checks, and 35 live HTTP checks passed. The documented Compose build/start, first submission/list, readiness, and teardown were exercised in isolation. Publication tooling requires successful CI on this exact commit before tagging.

Publication audit

Reachable history was checked for secrets, unintended private details, and AI authorship attribution. No additional sensitive content requiring a rewrite was identified; v1.0.0 remains unchanged. Scanning cannot establish the absence of all secrets, and existing clones/caches cannot be erased by a history rewrite.

v1.0.0 initial release

First stable release of agent-feedback: a self-hosted Go/PostgreSQL inbox for AI coding-agent review results and tooling/documentation friction reports.

Included

• JSON REST API for immutable submissions, deduplication, filtering, retrieval, and processed-state tracking.
• Companion Bash skill with credential redaction, local failed-write spooling, recovery, and querying.
• Public setup and API documentation, deployment configuration, backup/recovery guidance, and MIT licensing.
• Linux/amd64 and Linux/arm64 container builds.

Verification

The tagged commit passed CI: formatting/vet/build and generated SQL cleanliness, PostgreSQL race/integration tests, live HTTP contract checks, ShellCheck, hermetic client tests, and multi-architecture container publication.
CI: https://github.com/foae/agent-feedback/actions/runs/34053149811

Deployment

This service is intended for a single trust domain, not an internet-facing multi-tenant service. Read the README security and privacy guidance before collecting real telemetry. The companion skill has its own version number.

Container image for this release: ghcr.io/foae/agent-feedback:e7069aa265122aa4865993ae016760d0874b65b0

Known maintenance item

GitHub Actions reports Node.js 20 deprecation warnings for existing action versions; all jobs passed. Updating those action versions is separate from the readiness fix.