Commit Graph

816 Commits

Author SHA1 Message Date
Jari Mustonen
d8a600f2ad context-engine: pass runtime context to ContextEngineFactory (#67243)
Merged via squash.

Prepared head SHA: 9aca6a5af1
Co-authored-by: jarimustonen <1272053+jarimustonen@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-04-28 18:21:14 -07:00
Peter Steinberger
8f4cbbbe66 perf(prompt): stabilize channel prompt suffix 2026-04-29 00:49:57 +01:00
Peter Steinberger
f4a9d34f98 fix(model): explain rejected session overrides 2026-04-28 23:33:24 +01:00
Peter Steinberger
c500e8704f fix(gateway): recover stale session lanes 2026-04-28 20:37:29 +01:00
Peter Steinberger
1e9faa2a59 docs: document inter-session prompt guards 2026-04-28 20:34:55 +01:00
Peter Steinberger
cb8c513ce3 fix(telegram): honor final-only streaming mode 2026-04-28 20:28:06 +01:00
Tak Hoffman
f256eeba43 fix(active-memory): use bundled recall tool
Fixes #73502.

Active Memory now allows its hidden recall sub-agent to use both bundled memory tool contracts: memory_recall for memory-lancedb and memory_search/memory_get for memory-core. The prompt prefers memory_recall when available and falls back to the legacy tool pair when that is the active backend surface.

Also updates Active Memory docs, QA mock fixtures, and debug parsing compatibility for the two recall paths.
2026-04-28 09:03:47 -05:00
Peter
ba17b8b728 docs(active-memory): document cacheTtlMs bounds (#65708) (openclaw#65737)
Verified:
- pnpm install --frozen-lockfile
- pnpm build
- pnpm check
- pnpm test (local full suite failed in unrelated plugin/logging shards; PR-specific docs/changelog checks and GitHub checks passed)
- GitHub status checks for c2c5a94df8 completed without failure

Co-authored-by: WuKongAI-CMU <210765158+WuKongAI-CMU@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-04-28 08:42:16 -05:00
quengh
373e7fc242 feat(active-memory): add allowedChatIds/deniedChatIds per-conversation filters (openclaw#67977)
Verified:
- pnpm install --frozen-lockfile
- git diff --check
- pnpm exec oxfmt --check --threads=1 extensions/active-memory/index.ts extensions/active-memory/index.test.ts docs/concepts/active-memory.md CHANGELOG.md
- OPENCLAW_TEST_HEAVY_CHECK_LOCK_HELD=1 OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=.vitest-cache-pr67977 pnpm test extensions/active-memory/index.test.ts extensions/active-memory/config.test.ts
- gh pr checks 67977 --repo openclaw/openclaw --required

Co-authored-by: quengh <3940773+quengh@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-04-28 08:37:55 -05:00
Vincent Koc
fe7865aad6 docs: cover Anthropic beta header suppression and claude-cli fallback prelude
- docs/concepts/model-providers.md: add proxy-route shaping rule for the
  09ec5d2c4d fix that suppresses implicit Anthropic beta headers
  (`claude-code-20250219`, `interleaved-thinking-2025-05-14`, OAuth markers)
  on non-direct endpoints, parallel to the existing OpenAI
  `compat.supportsDeveloperRole` rule.
- docs/gateway/cli-backends.md: add a "Fallback prelude from claude-cli
  sessions" section for a96f1fa5ef so users know that non-CLI fallback
  candidates after a claude-cli failure are now seeded with a context prelude
  harvested from Claude Code's `~/.claude/projects/` JSONL (preferring the
  latest `/compact` summary, coalescing tool blocks, skipping same-provider
  `--resume` fallbacks).
2026-04-28 01:42:25 -07:00
Peter Steinberger
78a12706ec fix(docs): make docs formatter mintlify-safe 2026-04-28 08:13:21 +01:00
Peter Steinberger
12962dd883 fix(models): keep agent primaries strict 2026-04-28 08:01:42 +01:00
Peter Steinberger
424560c6c2 docs: normalize mintlify component closings 2026-04-28 07:54:15 +01:00
Peter Steinberger
a644e30245 fix(memory-core): retry unavailable dreaming model 2026-04-28 06:15:28 +01:00
Peter Steinberger
3d53b39917 fix(gateway): honor configured vision models 2026-04-28 06:10:14 +01:00
Peter Steinberger
540cbe24be fix: allow memory flush model override 2026-04-28 05:50:55 +01:00
Gustavo Madeira Santana
d59f001507 test(qa-matrix): cover allowBots modes 2026-04-28 00:47:40 -04:00
Peter Steinberger
66a0aa47e4 docs(google): clarify gemini 3.1 pro alias 2026-04-28 05:41:30 +01:00
Peter Steinberger
35c9dd06b2 fix(cli): respect replace mode in model picker 2026-04-28 05:26:25 +01:00
Peter Steinberger
870d993eb8 fix(ui): request configured model list 2026-04-28 05:21:08 +01:00
Peter Steinberger
4b4cde7187 fix(memory): back off qmd open failures 2026-04-28 04:16:25 +01:00
Gustavo Madeira Santana
ae616777f3 test(qa-matrix): cover approval metadata scenarios 2026-04-27 23:10:51 -04:00
Peter Steinberger
a0a0ab4d9e fix(memory): resolve custom embedding provider ids 2026-04-28 03:11:19 +01:00
Peter Steinberger
0294aebe6f feat(providers): add DeepInfra provider plugin (#73038)
* feat(providers): add DeepInfra provider plugin

* feat(deepinfra): add media provider surfaces

* fix(deepinfra): satisfy provider boundary checks

* docs: add gitcrawl maintainer skill

* test: include deepinfra in live media sweeps

* fix: remove stale tts contract import
2026-04-28 01:12:54 +01:00
Peter Steinberger
32d76e2429 fix(memory): bound lancedb recall embedding queries 2026-04-28 00:58:30 +01:00
Peter Steinberger
ff2b2e769f fix(cron): preserve job model fallbacks 2026-04-28 00:03:01 +01:00
Peter Steinberger
d2320e4d4b fix(models): keep user model switches strict 2026-04-27 23:32:44 +01:00
Peter Steinberger
496a5eb56f fix: dedupe silent reply prompt guidance 2026-04-27 23:31:13 +01:00
Peter Steinberger
d519dc6976 docs(channels): add channel docking concept 2026-04-27 22:37:58 +01:00
Peter Steinberger
582debbec8 docs(channels): explain dock commands 2026-04-27 22:32:44 +01:00
Gustavo Madeira Santana
b9fd13e8d7 qa-matrix: add streaming tool progress scenarios 2026-04-27 16:21:37 -04:00
Gustavo Madeira Santana
24068f19c6 matrix: stream tool progress in previews 2026-04-27 16:21:34 -04:00
Gustavo Madeira Santana
c5678194d4 docs(qa): document Telegram and Discord QA lanes against code
Both lanes had only one paragraph each in qa-e2e-automation.md. Adds a
"Telegram and Discord QA reference" section verified against
extensions/qa-lab/src/live-transports/{telegram,discord}/* with:

- shared CLI flags table (--scenario, --output-dir, --repo-root, --sut-account,
  --provider-mode, --model, --alt-model, --fast, --credential-source,
  --credential-role) — none of these were enumerated for either lane.
- Telegram QA: 8 scenario ids
  (telegram-canary/-mention-gating/-mentioned-message-reply/-help-command/
  -commands-command/-tools-compact-command/-whoami-command/-context-command),
  output artifact paths (telegram-qa-report.md, -summary.json,
  -observed-messages.json), and the redaction toggle.
- Discord QA: 3 scenario ids
  (discord-canary/-mention-gating/-native-help-command-registration), output
  artifact paths, and the SUT-application-id-must-match-bot-user-id check.
- Convex credential pool: documents Discord support (only Telegram was
  mentioned before) and the per-kind payload shapes for the
  admin/add validator. Cross-links to testing.md for the broker endpoint
  contract.

Slims the duplicate Operator-flow paragraphs for Telegram and Discord into a
single one-block pointer that links to the new reference section.
2026-04-27 13:48:03 -04:00
Gustavo Madeira Santana
dd1a94f089 docs(qa): reorg, audit against code, and refresh stale content
Reorg
- Rename the architecture page title to "QA overview" (slug stays
  /concepts/qa-e2e-automation so inbound links keep working).
- Move "Adding a channel to QA" + scenario-helper-name reference from
  testing.md into qa-e2e-automation.md under "Transport adapters". Architecture
  belongs with the architecture page.
- Drop the duplicate live-transport coverage table from testing.md; canonical
  copy stays in qa-e2e-automation.md under a new "Live transport coverage"
  heading so qa-matrix.md can deep-link to it.
- Slim testing.md QA-specific runners section to ops only, with cross-links.

Audit (against extensions/qa-lab/src/cli.ts, qa-channel/src/config-schema.ts,
and live-transport runtimes)
- qa-e2e-automation.md gains a "Command surface" table covering all 14
  openclaw qa <subcommand> forms; previously only ~7 of 14 were named.
- Document missing OPENCLAW_QA_TELEGRAM_CAPTURE_CONTENT and
  OPENCLAW_QA_DISCORD_CAPTURE_CONTENT env vars (Matrix already had it).
- Cross-link qa coverage from the Reporting section.
- qa-channel.md completes the config-key list (enabled, name, accounts,
  defaultAccount were missing from the schema doc) and pollTimeoutMs range.
- Drop stale "Follow-up work" framing in qa-channel.md (provider/model matrix,
  scenario discovery, orchestration) — all three already shipped.
- Replace "vertical slice" language with current behavior; fix misplaced
  debugger-UI paragraph.

Discoverability
- Add a Note callout to testing.md pointing at the three QA pages
  (QA overview, Matrix QA, QA channel) so maintainers landing on testing.md
  see the QA stack in the prologue.

Glossary entries for the renamed/new doc titles.
2026-04-27 13:40:11 -04:00
Gustavo Madeira Santana
abca187df5 docs(qa): add dedicated Matrix QA reference page
Adds a focused reference for the Docker-backed Matrix QA lane (CLI flags,
seven scenario profiles, eight env vars including the redaction toggle and
Tuwunel image override, scenario taxonomy, output artifact layout, and triage
tips). Source-of-truth checked against extensions/qa-matrix/src/cli.ts,
shared/live-transport-cli.ts, runners/contract/{runtime,scenario-catalog}.ts,
and substrate/harness.runtime.ts.

Registered in docs/docs.json alongside QA E2E automation.
2026-04-27 13:40:11 -04:00
Peter Steinberger
877b5a14f1 fix(sessions): batch store cap maintenance 2026-04-27 14:51:53 +01:00
Peter Steinberger
0ac0357486 docs(memory): explain qmd collection compatibility 2026-04-27 14:44:01 +01:00
Peter Steinberger
4ebec8b5dc fix(memory): group qmd collection searches 2026-04-27 14:37:12 +01:00
Peter Steinberger
c00ef238be docs(tools): clarify sessions_spawn profile gating 2026-04-27 14:31:54 +01:00
Peter Steinberger
73ba282b54 docs(memory): clarify qmd mask compatibility 2026-04-27 14:26:56 +01:00
Peter Steinberger
b181930c23 fix(memory): skip qmd vectors in lexical mode 2026-04-27 14:09:42 +01:00
Peter Steinberger
0e586bb48a fix(agents): improve fallback failure observability 2026-04-27 13:10:12 +01:00
Peter Steinberger
35335214b3 fix(compaction): avoid preserving duplicate user turns 2026-04-27 12:30:59 +01:00
Peter Steinberger
3bc29dd604 fix(sqlite): bound WAL sidecar growth 2026-04-27 12:25:10 +01:00
Peter Steinberger
da822a56d8 refactor(vllm): own nemotron thinking payloads 2026-04-27 12:15:54 +01:00
Peter Steinberger
775ed36c16 feat(memory): support asymmetric embedding input types 2026-04-27 11:25:40 +01:00
Peter Steinberger
4003e4389a fix(memory-core): support dreaming model override 2026-04-27 11:08:21 +01:00
Peter Steinberger
dfe58a1b8e fix(agents): treat TUI client label as current session 2026-04-27 10:45:26 +01:00
Peter Steinberger
1b81f75654 docs(providers): document cerebras setup 2026-04-27 10:22:21 +01:00
Peter Steinberger
e899b32e1d fix(agents): collapse local model timeout knobs 2026-04-27 10:16:50 +01:00