mirror of
https://github.com/nesquena/hermes-webui.git
synced 2026-07-20 22:51:07 +00:00
nesquena-hermes
e3a7c93dc6
* Harden interrupted recovery control filtering * Redesign live-to-final assistant replies * Fix live activity anchor test fixture * Fix CI lint issues for live reply tests * Strengthen live progress prompt contract * Recover PR #3401 refresh on origin/master * Repair live-to-final refresh regressions * Fix live worklog refresh regressions * Show live footer timer on initial stream start * Restore live stream shell after reload * Preserve per-frame live SSE replay cursors * Preserve reasoning as Worklog Thinking cards * Quiet Worklog Thinking card styling * Align Worklog Thinking card styling * Scope live Worklog Thinking cards by segment * Suppress exact duplicate settled Thinking * Close #3401 merge review test gaps * fix(#3401): resolve 4 deep-review regressions (inline-think, reconnect-dup, neon skin, busy-gate worklog) Deep review (Codex diff-vs-master + live-browser drive) of the live-to-final refactor surfaced 4 regressions vs master that the rewritten suite no longer guarded: 1. Inline <think>…</think>answer reasoning vanished — _assistantReasoningPayloadText used $-anchored regexes so a leading think block + visible answer extracted nothing and the Thinking card never rendered. Removed the 3 $ anchors to match the (non-anchored) display stripper. Live: inline-think thinking-only turn now renders. 2. (CORE) reconnect/reload duplicated the live reply — _rememberRunJournalCursor advanced a closure-local seq but never wrote INFLIGHT[activeSid].lastRunJournalSeq, so a reload replayed the journal from after_seq=0 over restored lastAssistantText. Now mirrors the cursor onto INFLIGHT + schedules a throttled persist. 3. Neon skin silently broke — PR deleted the :root[data-skin="neon"] CSS but left Neon in the picker. Restored the neon CSS block from master. 4. Settled tool-worklog rebuild gated purely on !S.busy — dropped every prior settled turn's worklog when renderMessages re-ran during an active stream (switch-back to an in-progress session). Restored master's !S.busy || (S.toolCalls && S.toolCalls.length). Live: busy re-render now preserves tool cards (4→4, was 4→0). Live-verified all 4 + confirmed #3709/#3592 invariants still hold (1 thinking card, none below footer; distinct siblings preserved). + tests/test_issue3401_deep_review_fixes.py (7). * test(#3401): realign 3 stale source-shape assertions to the deep-review fixes Fix commit changed two source literals that existing stage tests scanned for: - test_live_activity_timeline.py (x2): split anchor 'if(!S.busy){' → the restored 'if(!S.busy || (S.toolCalls&&S.toolCalls.length)){' guard (fix 4). - test_run_journal_frontend_static.py: 'after_seq=0' not in source — fix 2's comment contained that literal; rephrased the comment to 'the zero floor (after_seq of 0)'. Intent of all three assertions unchanged; only the matched string updated. No code behavior change. * docs(changelog): v0.51.294 — Release JJ (stage-3401, #3401 live-to-final redesign) --------- Co-authored-by: Frank Song <franksong2702@gmail.com> Co-authored-by: Nathan-Hermes <nesquena-hermes@users.noreply.github.com> Co-authored-by: nesquena-hermes <[email protected]>
78 lines
3.1 KiB
Python
78 lines
3.1 KiB
Python
from pathlib import Path
|
|
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
|
|
|
|
def _read(relpath: str) -> str:
|
|
return (ROOT / relpath).read_text(encoding="utf-8")
|
|
|
|
|
|
def _function_block(src: str, name: str) -> str:
|
|
start = src.find(f"def {name}")
|
|
assert start != -1, f"{name} not found"
|
|
next_def = src.find("\n def ", start + 1)
|
|
assert next_def != -1, f"end of {name} not found"
|
|
return src[start:next_def]
|
|
|
|
|
|
def test_tool_start_callback_emits_existing_tool_sse_event_with_tool_id():
|
|
src = _read("api/streaming.py")
|
|
block = _function_block(src, "on_tool_start")
|
|
|
|
assert "put('tool'" in block, (
|
|
"The dedicated Hermes Agent tool_start_callback must emit the existing "
|
|
"tool SSE event; otherwise WebUI stays visually silent while tools run."
|
|
)
|
|
assert "'event_type': 'tool.started'" in block
|
|
assert "'tid': tool_call_id" in block, (
|
|
"Live frontend cards need the tool_call_id so tool_complete can update "
|
|
"the running card in place."
|
|
)
|
|
assert "_live_tool_event_start_ids" in block, (
|
|
"Tool start SSE emission should be idempotent per callback id."
|
|
)
|
|
assert "STREAM_LIVE_TOOL_CALLS" in block and "'done': False" in block
|
|
|
|
|
|
def test_tool_complete_callback_emits_existing_tool_complete_sse_event_with_tool_id():
|
|
src = _read("api/streaming.py")
|
|
block = _function_block(src, "on_tool_complete")
|
|
|
|
assert "put('tool_complete'" in block, (
|
|
"The dedicated Hermes Agent tool_complete_callback must emit the existing "
|
|
"tool_complete SSE event so the frontend can settle the running tool card."
|
|
)
|
|
assert "'event_type': 'tool.completed'" in block
|
|
assert "'tid': tool_call_id" in block
|
|
assert "_live_tool_event_complete_ids" in block, (
|
|
"Tool completion SSE emission should be idempotent per callback id."
|
|
)
|
|
assert "result_snippet = _tool_result_snippet(function_result)" in block
|
|
assert "_checkpoint_activity[0] += 1" in block
|
|
|
|
|
|
def test_legacy_progress_events_are_suppressed_when_structured_callbacks_are_wired():
|
|
src = _read("api/streaming.py")
|
|
block = _function_block(src, "on_tool")
|
|
|
|
assert "event_type in (None, 'tool.started') and 'tool_start_callback' in _agent_params" in block
|
|
assert "event_type == 'tool.completed' and 'tool_complete_callback' in _agent_params" in block
|
|
assert block.index("'tool_start_callback' in _agent_params") < block.index("put('tool'")
|
|
assert block.index("'tool_complete_callback' in _agent_params") < block.index("put('tool_complete'")
|
|
|
|
|
|
def test_tool_callback_events_keep_existing_frontend_event_contract():
|
|
messages = _read("static/messages.js")
|
|
ui = _read("static/ui.js")
|
|
|
|
assert "source.addEventListener('tool',e=>{" in messages
|
|
assert "source.addEventListener('tool_complete',e=>{" in messages
|
|
assert "String(d&&d.tid" in messages or "explicitTid=String(d&&d.tid" in messages, (
|
|
"frontend tool handlers must still consume explicit server tid when present"
|
|
)
|
|
assert "upsertLiveToolCall(d,'start')" in messages
|
|
assert "upsertLiveToolCall(d,'complete')" in messages
|
|
assert "data-live-tid" in ui
|
|
assert "existing.replaceWith(replacement)" in ui
|