Commit Graph

33 Commits

Author SHA1 Message Date
Deshraj Yadav a2ae930e9f fix(mem0-agent): add required userConfig title to the plugin manifest
The loader validates userConfig.<key>.title as a required string; without it the
install fails with 'invalid manifest file'. Manifest shape now matches the v1
plugin's exactly.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-29 01:58:09 -07:00
Deshraj Yadav e11d2a4a06 fix(mem0-agent): emit the Claude Code manifest at hooks/hooks.json
Claude Code auto-discovers a plugin's hooks at <plugin>/hooks/hooks.json. The
generator was writing to hooks/generated/, so the manifest existed but was never
loaded and no hook would have fired on install.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-29 01:49:27 -07:00
Deshraj Yadav ba1de5f87b fix(mem0-agent): non-blocking stdin, clean session_state, lint
Found by running the CLI live against a scratch project:
- hook_input() blocked forever on an open stdin pipe with no data. A real hook
  writes JSON and closes the pipe, but any manual invocation hung; now polled
  with select() and never blocks.
- the open-thread snapshot was filling with progress lines and file-modification
  lists -- v1's exact failure -- so it now filters turns through the same
  hard-drop rules the capture gate uses.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 02:12:23 -07:00
Deshraj Yadav 4d5f2e653c feat(mem0-agent): capture gate, eval harness, and mixed-window fix
- triggers.py: hard-drop rules now filter PER TURN, so a durable fact sitting
  between two progress lines survives instead of being dropped with them. The
  eval harness caught this: 3 mixed-window fixtures were being destroyed
  client-side before the extractor ever saw them.
- widened flag rules for 13 plainly durable windows the gate was missing
  (standing preferences, X-over-Y decisions, stated rules, diagnoses, verified
  procedures); verified procedures moved from aggressive to balanced
- eval/: 56 labeled fixtures from the audited v1 corpus plus offline and live
  runners with a --check regression gate
- un-ignore integrations/mem0-agent/eval (root .gitignore excluded it silently)

Offline scorecard: hard_drop_recall 1.000, extract_recall 1.000,
flag_precision 1.000, 0 misclassified.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 02:02:37 -07:00
Deshraj Yadav 3ea00cf88c feat(mem0-agent): read path, hooks, maintenance, CLI and skills
- pack.py: single-call context pack, budgeted, sanitized, cached, with
  served-id tracking that turns a citation into POSITIVE feedback
- assist.py: error-signature lookup (never raw stdout, which returned 0 results in v1)
- maintain.py: transactional consolidation (add merged -> verify -> delete sources)
- transcript.py: JSONL parsing into non-overlapping windows via a cursor
- cli.py: the twelve commands the hooks invoke; detached assist queues a block
  that the next prompt hook drains, keeping the hot path network-free
- hooks generated from one spec; plugin manifest, MCP wiring, five skills

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 01:56:38 -07:00
Deshraj Yadav e102b21180 feat(mem0-agent): WS0+WS1 foundation - verified contract, config, client core
Encodes the platform contract validated against the live API:
- project_id/org_id pinned in request body (query params are ignored)
- latest_only=True enforced on every read
- metadata.type as the read-time taxonomy (categorization lags ~4h)
- NOT filters take a list; delete_all takes query params; fields repeated

Includes project config (write-gate instructions, 6 custom categories, decay),
verified filter recipes, circuit breaker, session-scoped state, keychain auth,
and identity/project resolution.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 01:45:10 -07:00
Kartik 5e7adc4d12 chore: update changelog, bump versions to Python 2.0.13, TypeScript 3.1.1, OpenCode plugin 0.2.2 (#6504) 2026-07-22 23:27:47 +05:30
Rod Boev b05cce581b fix(opencode-plugin): recover MEM0_API_KEY from shell profiles (#6404) 2026-07-20 20:41:41 +05:30
Kartik ccbe5861a1 docs: remove criteria retrieval docs for non-existent feature (#6282) 2026-07-14 20:06:05 +05:30
Kartik d6d2588ef5 fix(mem0-plugin): store assistant-authored summaries with role="assistant" (#6316) 2026-07-14 20:03:36 +05:30
Kartik 8488abe603 docs: correct custom categories, per-call custom_categories is supported (#6218) 2026-07-10 20:08:32 +05:30
Kartik 41c8f00851 chore(integrations): plugin updates, pi-agent auto-recall, and version bumps (#6011) 2026-07-01 20:57:32 +05:30
Kartik c325bd3b8e docs(changelog): consolidate per-package changelogs into the SDK changelog page (#6007) 2026-06-30 14:09:41 +05:30
Terrasse cc59d122db docs: remove instructions for unavailable Cursor marketplace plugin (#5971) 2026-06-29 20:35:07 +05:30
Harsh Vardhan Gupta bbbfcfea07 fix(deps): bump undici to >=6.27.0 (CVE-2026-12151) (#5861) 2026-06-26 15:32:09 +05:30
Rod Boev 1f66aadfa3 fix(openclaw): normalize Windows skill-loader URLs before fileURLToPath (#5679) 2026-06-25 16:36:11 +05:30
Kartik ac8f862ff7 fix(mem0-plugin): store files_touched as a list to stop double JSON-encoding (#5806) 2026-06-25 09:06:11 +05:30
Bartok ced4af681f fix(claude-plugin): rerank auto-injected memory context by default (#5690) 2026-06-23 16:52:35 +05:30
Harsh Vardhan Gupta ca86a164bd fix(pi-agent-plugin): resolve undici CVE-2026-9697 / CVE-2026-9678 (#5669) 2026-06-19 16:21:18 +05:30
Harsh Vardhan Gupta 1dcee153b9 fix(deps): patch js-yaml, ai, python-dotenv vulnerabilities (CVE-2026-53550, CVE-2025-48985, CVE-2026-28684) (#5641)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-18 17:13:15 +05:30
Harsh Vardhan Gupta 96b31c4bc0 fix(form-data): upgrade to >=4.0.6 across pnpm workspaces (CVE-2026-12143) (#5618)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 13:44:05 +05:30
ChrisFloofyKitsune 9ed1983b85 refactor(opencode): use existing mem0 SDK instead of delegating to MCP, load skills properly instead of dumping them in .opencode (#5323)
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
2026-06-17 21:18:39 +05:30
Harsh Vardhan Gupta 4492e75d04 fix(deps): bump esbuild >=0.28.1 across all npm packages (#5563)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-15 17:04:11 +05:30
Rod Boev 3951ad4705 fix(openclaw): reduce skills-mode triage prompt footprint (#5502) 2026-06-15 11:18:39 +05:30
Kartik 73c975ba68 chore: bump version to 0.1.3, update mem0ai to ^3.0.7, and adjust CHANGELOG (#5521) 2026-06-13 18:10:50 +05:30
Kartik 931d579ba5 chore(openclaw): release v1.0.13 and backfill v1.0.12 changelog (#5519) 2026-06-13 17:59:04 +05:30
Kartik f4773a0baf fix(mem0-plugin): accurate per-editor telemetry attribution + OpenCode telemetry (#5518) 2026-06-13 16:48:29 +05:30
mjzcng 821152bd14 Fix OpenClaw Mem0 custom categories payload (#5345)
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai>
2026-06-12 19:48:53 +05:30
Yufeng He b9ad8fa8b2 fix(openclaw): skip runtime setup during metadata registration (#5383) 2026-06-12 19:32:59 +05:30
Kartik f681889b14 fix(pi-agent-plugin): make command results visible and relevance-filtered (#5504) 2026-06-12 19:13:31 +05:30
Kartik b5ec46be5b fix(plugin): guard bare $USER refs in on_session_start.sh for Windows (#5492) 2026-06-12 19:13:19 +05:30
Harsh Vardhan Gupta 168ad358d5 fix(deps): resolve all open MEDIUM Dependabot alerts (npm overrides + Python pins) (#5489)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-12 15:15:26 +05:30
Kartik 2c796d144f refactor: consolidate agent/editor plugins under integrations/ (#5491)
Co-authored-by: Claude <noreply@anthropic.com>
2026-06-12 10:31:35 +05:30