sutra dae06a203f fix: add self-knowledge docs rule to system prompt (#90882) ...

Summary:
- This PR replaces the generated Documentation prompt wording with self-knowledge docs-authority guidance and updates prompt tests plus the system-prompt docs.
- PR surface: Source 0, Tests +27, Docs +6. Total +33 across 4 files.
- Reproducibility: yes. from source for the prompt gap: current main and v2026.6.8 have only broad docs-first  ... ledge failure example. I did not run a fresh current-main live model conversation in this read-only review.

Automerge notes:
- PR branch already contained follow-up commit before automerge: fix: strengthen self-knowledge docs prompt
- PR branch already contained follow-up commit before automerge: test: narrow cli prompt tool assertion
- PR branch already contained follow-up commit before automerge: fix: condense self-knowledge docs prompt
- PR branch already contained follow-up commit before automerge: fix: clarify self-knowledge docs authority
- PR branch already contained follow-up commit before automerge: Merge branch 'main' into sutrah/self-knowledge-docs-prompt

Validation:
- ClawSweeper review passed for head 88a7db5d2a.
- Required merge gates passed before the squash merge.

Prepared head SHA: 88a7db5d2a
Review: https://github.com/openclaw/openclaw/pull/90882#issuecomment-4637990339

Co-authored-by: Sutra Hsing <sutrahsing@163.com>
Co-authored-by: sutra <sutrahsing@163.com>

2026-06-19 03:38:36 +00:00

..

active-memory.md

fix(active-memory): preserve verbose recall summaries (#90739)

2026-06-13 23:38:58 -07:00

agent-loop.md

fix(logging): avoid stalled warnings for active model calls

2026-06-16 06:27:40 +08:00

agent-runtimes.md

refactor: unify OpenAI provider identity (#88451)

2026-05-31 00:29:44 +01:00

agent-workspace.md

fix: raise bootstrap file default limit

2026-06-01 04:02:51 +01:00

agent.md

fix(agents): guard vanished workspaces

2026-05-31 21:14:54 -04:00

architecture.md

…

channel-docking.md

…

commitments.md

…

compaction.md

refactor: internalize OpenClaw agent runtime (#85341)

2026-05-27 19:24:04 +01:00

context-engine.md

feat(context-engine): pass runtime settings into lifecycle (#88750)

2026-06-16 16:23:19 -07:00

context.md

fix(context): report compactable transcript counts

2026-06-09 02:16:11 +09:00

delegate-architecture.md

Move cron persistence to SQLite (#88285)

2026-05-30 21:03:41 +01:00

dreaming.md

feat(dreaming): score candidates with shadow trial results

2026-05-31 23:40:20 -04:00

experimental-features.md

fix(agents): compact lean local tool catalogs

2026-06-08 10:33:41 +09:00

features.md

docs: surface Windows Hub across docs

2026-06-03 16:09:24 -07:00

mantis-slack-desktop-runbook.md

Add Slack approval QA checkpoints (#85141)

2026-05-22 22:04:15 -07:00

mantis.md

Fold Telegram RTT sampling into live QA evidence (#92550)

2026-06-14 17:02:33 +08:00

markdown-formatting.md

…

memory-builtin.md

refactor(memory): use the per-agent sqlite database

2026-06-19 01:20:06 +08:00

memory-honcho.md

…

memory-qmd.md

fix(gateway): arm qmd startup maintenance

2026-06-11 01:13:41 +09:00

memory-search.md

fix(memory): move local llama.cpp runtime to provider plugin

2026-06-09 14:30:35 +08:00

memory.md

feat(embeddings): add OpenAI-compatible core provider (#85269)

2026-05-27 14:37:17 +02:00

message-lifecycle-refactor.md

refactor: remove channel turn runtime aliases

2026-05-27 11:37:23 +01:00

messages.md

refactor(auto-reply): unify transient failure visibility

2026-06-03 13:55:36 +05:30

model-failover.md

refactor(auth): store auth profiles in sqlite (#89102)

2026-06-03 16:14:15 -07:00

model-providers.md

feat(plugins): externalize official provider batch

2026-06-19 01:05:52 +08:00

models.md

fix(status): correct pinned model clear hint (#93231)

2026-06-15 10:15:54 +00:00

multi-agent.md

docs: refresh contributor docs

2026-05-22 22:58:27 +01:00

oauth.md

docs: clarify legacy openai-codex auth (#90028)

2026-06-03 16:18:51 -07:00

parallel-specialist-lanes.md

…

personal-agent-benchmark-pack.md

Convert QA scenarios to YAML files (#92915)

2026-06-14 17:31:18 -07:00

presence.md

…

progress-drafts.md

fix(agents): add typed tool progress updates

2026-05-29 11:06:13 +01:00

qa-e2e-automation.md

Standardize QA coverage IDs on dotted names (#94702)

2026-06-18 17:25:26 -07:00

qa-matrix.md

…

queue-steering.md

refactor: internalize OpenClaw agent runtime (#85341)

2026-05-27 19:24:04 +01:00

queue.md

fix(logging): avoid stalled warnings for active model calls

2026-06-16 06:27:40 +08:00

retry.md

…

session-pruning.md

…

session-tool.md

fix(agents): expose session status route context

2026-05-31 22:25:47 +01:00

session.md

Policy: add data handling conformance checks (#87056)

2026-06-02 10:48:07 -07:00

soul.md

Move Codex soul context to developer instructions (#84331)

2026-05-19 16:47:32 -07:00

streaming.md

docs(streaming): document Telegram block-mode preview chunk sizing

2026-06-10 16:30:25 +05:30

system-prompt.md

fix: add self-knowledge docs rule to system prompt (#90882)

2026-06-19 03:38:36 +00:00

timezone.md

fix(agents): honor disabled envelope timestamps at model boundary (#93238)

2026-06-16 12:13:24 +08:00

typebox.md

refactor: extract gateway client package (#87797)

2026-05-29 02:23:42 +01:00

typing-indicators.md

…

usage-tracking.md

fix(usage): warn on broken footer templates

2026-06-13 19:16:02 +05:30