mirror of
https://github.com/dtzp555-max/ocp.git
synced 2026-07-21 21:15:09 +00:00
main
3
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
4f9e2ff281 |
feat(server): OCP_LOCAL_TOOLS — positive local-tools system-prompt wrapper (single-user, default off) (#182)
Motivation (the OpenClaw case). OCP's `-p` path prepends OCP_SYSTEM_PROMPT_WRAPPER, which tells the model it has NO local filesystem/shell/env access. Correct for a shared/multi-tenant gateway. But an OpenClaw agent pointed at its own local OCP runs the model SERVER-SIDE via `claude -p`, which already passes --allowedTools and has the CLI's built-in tools — and on a loopback instance the OCP host IS the operator's machine, so those are local tools. The wrapper gags them: the agent replies "I don't have filesystem access" for tools it actually holds. OCP_LOCAL_TOOLS=1 swaps in a positive wrapper for that case. (It does NOT enable client-side tool_calls for OpenClaw/Cline — that remains unsupported by design; OCP is a text-prompt bridge.) Safety: changes ONLY the system-prompt text, never the tool surface. Tools are governed solely by --allowedTools/--disallowedTools; AUTH_MODE=multi still --disallowedTools the whole FS/web/agent surface regardless of the wrapper. Fail-closed boot gate mirroring OCP_TUI_FULL_TOOLS (ADR 0007): refuse to start when =1 is combined with CLAUDE_AUTH_MODE=multi, a non-loopback bind, or PROXY_ANONYMOUS_KEY. Scope/alignment: no new endpoint/header/field/wire operation. The wrapper text is OCP-owned prompt composition (same class as OCP_SYSTEM_PROMPT_WRAPPER and CLAUDE_SYSTEM_PROMPT), passed via the already-cited `claude --system-prompt` flag (unchanged). ALIGNMENT.md Rule 2: nothing invented on the wire. - lib/prompt.mjs: pure selectPromptWrapper() + localToolsSafetyError() (unit-tested). - server.mjs: single hoisted flag LOCAL_TOOLS_ACTIVE = OCP_LOCAL_TOOLS && !TUI_MODE (the wrapper is only applied on the -p path; TUI composes its own prompt, so the flag is inert under TUI — announced with a warning rather than a misleading "ON"). Wrapper selection, boot gate, and the CONFIG_EPOCH fold all key off it, so toggling the flag + restarting invalidates the standard response cache (#177). Default path byte-for-byte unchanged. - README env-var row + tool-model note; CHANGELOG Unreleased entry. Tests (+14): unit-test both ternary branches and every gate condition; plus an INTEGRATION harness that boots real server.mjs with a fake `claude` capturing the --system-prompt — asserting the POSITIVE wrapper reaches a request under =1 and the EXACT negative wrapper when unset, the boot gate refuses all three unsafe configs, the safe config boots, TUI announces inert, and toggling the flag re-spawns (cache invalidated). Mutation-verified: reverting the wiring / neutering the gate / reverting the epoch fold each turns a test RED. 443 passed, 0 failed. Noticed but scoped out (Iron Rule 11): the structured-output cache path (handleChatCompletions, the response_format branch) does not fold CONFIG_EPOCH at all — a pre-existing gap from #177/#153, independent of this flag. Happy to fix in a follow-up. Co-authored-by: vvlasy-openclaw <vvlasy@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
 |
fe12419386 |
feat(server): SPOT-derived prompt budget — MAX_PROMPT_CHARS follows models.json (ADR 0009) (#179)
* feat(server): SPOT-derived prompt budget — MAX_PROMPT_CHARS default follows models.json (ADR 0009)
Maintainer directive (2026-07-18): the hand-set 150,000-char default (~37.5k English
tokens) is obsolete in the long-context era. Instead of a new constant that would rot
the same way, the default now derives from the SPOT:
MAX_PROMPT_CHARS (default) = max(models.json contextWindow) x 3 chars/token
= 200000 x 3 = 600,000 chars today (~150-200k tokens)
x3 is the CJK-safe multiplier: English runs ~4 chars/token, CJK ~1-1.5, so a
1M-token-derived char cap would let CJK text sail past the model's real window into
an upstream rejection; at x3 the cap fires at roughly the model's true window and OCP
truncates gracefully (tail-first) instead. Pure derivePromptCharBudget() in
lib/prompt.mjs with a 150k floor guarding degenerate SPOT states (empty models[],
absent contextWindow) - a zero budget would truncate every request to nothing.
CLAUDE_MAX_PROMPT_CHARS (env) and the runtime settings API remain ABSOLUTE overrides;
derivation applies only when neither is set. If models.json ever advertises a larger
window (e.g. 1M for the 1M-native models), the budget scales automatically - that
advertisement is a separate deliberate decision (quota burn, OpenClaw compaction, TUI
paste limits) explicitly NOT made here; see ADR 0009.
Behavior change (intended): requests between 150k and 600k chars previously truncated
now pass through whole - longer TTFT + higher quota use for those requests. Truncation
mechanism/logging unchanged; only the default's provenance changed.
ALIGNMENT.md Rule 2: no cli.js citation applies - the truncation guard is OCP-internal
prompt shaping; no endpoint, header, or wire field changes.
Tests: +4, doubly mutation-proven (max->min fails the largest-window test; dropping
the floor fails the floor test). Suite 347 passed / 0 failed. ADR 0009 + index row +
README env-table row included (release_kit: env var default change documented).
Co-Authored-By: Claude <claude-opus-4-8> <noreply@anthropic.com>
* fix(server): empty CLAUDE_MAX_PROMPT_CHARS falls back to derived default (PR #179 review)
Reviewer regression: `!= null` treated an EMPTY env value ("CLAUDE_MAX_PROMPT_CHARS="
in an EnvironmentFile/.env) as explicit -> parseInt("") = NaN -> guard disabled + a
false "[System] Note: 0 older messages were truncated" injected into every prompt.
Extracted resolvePromptCharBudget() (truthiness contract, matching the old
`parseInt(env || default)` behavior) into lib/prompt.mjs so the semantics are
mutation-tested: switching back to != null fails the empty-string test. +2 tests, 349/0.
Co-Authored-By: Claude <claude-opus-4-8> <noreply@anthropic.com>
---------
Co-authored-by: dtzp555 <dtzp555@gmail.com>
Co-authored-by: Claude <claude-opus-4-8> <noreply@anthropic.com>
|
||
|
|
e6f1a6aac1 |
fix(server): wire CLAUDE_SYSTEM_PROMPT (dead since APPEND_SYSTEM_PROMPT retirement) (#175)
* fix(server): wire CLAUDE_SYSTEM_PROMPT into the composed system prompt (was dead since APPEND_SYSTEM_PROMPT retirement) The var was read (SYSTEM_PROMPT, server.mjs), documented in the file header as "appended to all requests", and echoed on /health.systemPrompt — but nothing on the request path consumed it: extractSystemPrompt() composed only the wrapper + client system messages. The wiring was lost when APPEND_SYSTEM_PROMPT was retired, leaving the header comment and the buildCliArgs comment describing behavior that did not exist (caught by the PR #170 independent reviewer). Wire, not delete, because: - the /health `systemPrompt` field is part of the grandfathered B.2 contract (ADR 0006, frozen at v3.16.4) — removal would need an ADR; wiring keeps the shape and makes the field honest; - fleet check: no deployment sets the var (Mac prod plist, Oracle systemd unit, PI231 /etc/ocp/ocp.env all clean), so wiring changes behavior for NOBODY today; - with the var unset, appendOperatorPrompt returns its input string unchanged — the default path is byte-for-byte identical. Mechanics: new pure lib/prompt.mjs `appendOperatorPrompt(base, operatorAppend)` (trimmed; whitespace-only treated as unset so a stray space in a service unit cannot inject "\n\n " into every request), applied as the LAST segment in both extractSystemPrompt branches — an operator-wide directive reads as the final instruction, after client system messages. TUI-mode is untouched (panes keep the interactive CLI's own system prompt); documented in the README row. ALIGNMENT.md Rule 2: no cli.js citation applies. No endpoint, header, or wire field is added or altered; the change affects only the CONTENT OCP passes to the already-established `--system-prompt` flag (file header § verified v2.1.104), i.e. OCP-owned prompt composition. /health shape unchanged. Tests: +3, doubly mutation-proven (unconditional-base revert → 2 failures; trim removal → 2 failures). Suite 341 passed / 0 failed. Co-Authored-By: Claude <claude-opus-4-8> <noreply@anthropic.com> * docs(readme): cache-staleness caveat on CLAUDE_SYSTEM_PROMPT row (reviewer advisory) --------- Co-authored-by: dtzp555 <dtzp555@gmail.com> Co-authored-by: Claude <claude-opus-4-8> <noreply@anthropic.com> |