4 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
nsgdsandClaude Opus 4.8	2465b41843	fix(agent): don't let a materialized default budget defeat context-window scaling (#4122) ... * fix(agent): don't let a materialized default budget defeat context scaling #1230 scales agent_input_token_budget to the model's context window unless the user explicitly set a budget, detected via is_setting_overridden(). But the settings-save path materializes every DEFAULT_SETTINGS key into settings.json (load_settings merges defaults; handlers persist the merged dict), so the persisted default 6000 reads as "overridden" and the budget code takes the min(6000, ctx) branch — silently re-capping long-context models at 6000 for anyone who has ever saved a setting. This reintroduces the exact regression #1170/#1230 set out to fix. Add is_setting_customized() (saved value != default) and gate the scaling on it instead of mere presence. A persisted default is not a user choice. is_setting_overridden has exactly one consumer (this budget path), so the change is contained. Tests cover the materialized-default regression, a deliberately-chosen budget still being honoured, and the absent-key case. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(agent): rework context-budget fix per review (#4122) Address RaresKeY's review: P2 (explicitness): is_setting_customized treated a saved value equal to the default as "not explicit", which ALSO blocked a user from deliberately pinning the default budget. Reframe the default value itself as the AUTO sentinel — agent_input_token_budget == DEFAULT_BUDGET means "scale to the model's context window", any other value is an explicit cap. A materialized default still reads as auto (fixing the original regression), and any non-default value the user chooses is now honoured. Drop the now-unused is_setting_customized helper. P2 (fallback context): auto-scaling trusted get_context_length() even when it returned only the bare DEFAULT_CONTEXT fallback (no endpoint-reported / known window), over-allocating on self-hosted/proxy setups. Add get_context_length_known() (also returns whether the window was actually discovered); the budget block passes 0 when unknown so auto-scaling stays conservative instead of inflating to an unproven window. hard_max stays auto-only — a deliberate explicit budget wins (#1190); kept that contract and answered the reviewer's question rather than silently reversing it. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(agent): lock the materialized-default budget regression (review on #4121) Per WGlynn's review on the issue: add an end-to-end regression that saves an UNRELATED setting (which makes the settings-save path materialize the budget default into settings.json) and asserts the budget still auto-scales rather than re-reading as an explicit 6000 cap — locking the exact reopening shut. To make the test bite the production decision (not just re-derive it), extract `budget_is_explicit()` into src/context_budget.py and use it from the agent loop. It keys off value-vs-default (the default is the auto sentinel), NOT settings presence — which is the whole point, since the save path materializes defaults. Note: after this PR's rework, is_setting_overridden has ZERO production callers, so the merged-dict materialization smell can't reach any setting through a presence check today (WGlynn's durability concern). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(agent): bind the budget context window to its own provenance (review #4122) RaresKeY caught a correctness bug in the fallback-context guard: stream_agent_loop kept only the `known` flag from get_context_length_known() and budgeted off the passed-in `context_length`, which can come from a *different* lookup. Two failures: - local endpoints are re-queried, so the passed value can be a stale DEFAULT_CONTEXT fallback while the fresh probe proves the real (smaller) served context — we'd scale off the stale value; - callers that don't pass context_length (scheduled tasks, teacher escalation, skill test runs, bg_monitor) were capped at 6000 even when a long window is discoverable. Extract budget_context_for_model() which returns the freshly-probed window when known else 0, binding the flag to the value it proves; the agent loop uses it. Regression tests cover the stale-fallback, no-arg-caller, and probe-error paths. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(agent): fix stale budget comments + tighten to the contract (review #4122) - settings.py: an explicit budget is clamped to the window only — hard_max is auto-only (#1190); drop the incorrect "and to hard_max". - is_setting_overridden docstring: drop the stale "adaptive budgets" example; point value-sensitive callers at context_budget.budget_is_explicit. - Tighten the budget-block comments to the contract (default = auto sentinel, non-default = explicit cap, hard_max = auto-only ceiling). Comment/docstring-only; no behaviour change. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(agent): correct budget issue citations (#1190 → merged #1230/#1273) The context-budget contract (auto-sentinel, explicit budgets honoured, hard_max auto-only) merged via #1230 — #1190 was the earlier, closed, superseded PR. Re-point the contract comments at #1230 (the live source, already cited for the auto-sentinel two lines up in settings.py). The configurable hard_max setting (`agent_input_token_hard_max`) was a reviewer requirement first raised on #1190, omitted from the merged #1230, and actually added in #1273 — credit #1273 for it and correct the test comment's history (it previously implied this PR completed the requirement). Comment/docstring-only; no behaviour change. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-15 15:17:28 +09:00
nsgdsandClaude Opus 4.8	389b651e22	fix(images): render agent-generated images in chat (#2809) ... * fix(images): render agent-generated images in chat When a chat model calls generate_image mid-conversation (agentic flow), the image does not display — it survives only as a URL the model echoes in prose. generate_image runs as a text-only MCP server, so result['image_url'] is never populated and the existing buildImageBubble render path never fires. Promote the image URL out of the tool's stdout in tool_execution so the agent loop's existing forwarding renders it via buildImageBubble — deterministically, no dependence on the model echoing the URL. Backend-only; reuses dev's image bubble, forwarding, and the tool's existing parseable output. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(images): fully-qualified, valid generated-image links The chat model often mangled the generated-image URL it echoed in prose (relative path, or copying the 'image_url:' label into the link href). Build a fully-qualified link by prefixing the existing app_public_url setting (empty default keeps relative paths), and present it as a clean 'Direct link:' the model can echo verbatim (the frontend auto-links bare https URLs). One file; independent of how the image is rendered. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(images): cover _promote_image_fields; make exit-code guard self-contained Adds the unit tests requested in review on #2809: absolute URL, relative URL, no URL (result unchanged), and non-zero exit_code (not promoted). Moves the dict/exit_code==0 guard from the call site into _promote_image_fields so the function is self-contained and the failure case is unit-testable; call-site behavior is unchanged. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-05 13:04:33 +02:00
nsgdsandClaude Opus 4.8	65b876a7b9	Support vLLM 0.20.2 / NIM reasoning-parser output end-to-end (surface + agent context + render) (#602) ... * fix(stream): read 'reasoning' SSE field for vLLM 0.20.2 / NIM vLLM 0.20.2 / NVIDIA NIM emit reasoning-parser output in the `reasoning` delta field; older builds use `reasoning_content`. stream_llm() read only the latter, so reasoning from models like Nemotron-3-Nano (--reasoning-parser) was silently dropped and never rendered. Accept either field. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(agent): keep reasoning_content only on the latest assistant turn The agent loop echoed each round's reasoning back as `reasoning_content` on every assistant turn, assuming vendors ignore it. Nemotron's chat template re-injects ALL prior reasoning_content as <think> blocks, and the loop is trimmed only once (before it starts) — so reasoning accumulated unbounded across rounds, bloating context and feeding the model its own prior reasoning, which reinforced repetition/looping. Strip reasoning_content from earlier assistant turns so only the most recent round carries it (still satisfies DeepSeek's thinking-mode follow-up requirement). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(agent-ui): wrap each round's reasoning in its own <think> block The streamed think-tag wrapper gated on whole-message substring checks (accumulated.includes('<think>')), which only ever wrapped ONE reasoning block per message. A multi-round agent response has a reasoning phase per round, so once round 1 closed its <think>...</think>, rounds 2+ reasoning was emitted unwrapped and leaked into the visible answer. Replace the substring checks with a stateful open/close flag that toggles per think/answer cycle, so each round's reasoning gets its own collapsible block. Single-turn chat is unchanged (one open, one close). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(stream): reasoning/reasoning_content delta surfaces as thinking chunk Covers @pewdiepie-archdaemon's requested regression: a streamed {reasoning: ...} delta emits a thinking chunk while {content: ...} streams as normal content; plus the older reasoning_content field for backward compat. Mirrors the #591 scenario. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-02 11:48:17 +09:00
nsgdsandClaude Opus 4.8	e68ce433f3	fix: don't bill self-hosted models reached by a container/service hostname (#596) ... * fix(cost): treat dotless container hostnames as local (free) getModelCost() substring-matches model names against a cloud price table, so a self-hosted 'nemotron'/'llama' model was billed at cloud rates. isLocalEndpoint() only recognized IPs / localhost / .local, not bare Docker service names (nim-nano, llamaswap), so the local-is-free guard missed them. A single-label hostname (no dot) can never be a public API -> treat as local. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(cost): isLocalEndpoint classifies service names local, cloud FQDNs billable Covers @pewdiepie-archdaemon's requested cases: llamaswap/nim-nano + localhost/private-IPs/.local => local (free); api.openai.com/openrouter.ai/etc => not local. Drives the real function via node --input-type=module (same approach as test_reply_recipients_js.py), skips when node is absent. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-02 11:47:58 +09:00